Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, our method treats them as a regularization objective on top of a minimal safe goal-reaching reward. Like the spice in a good stew, we find that a little human data goes a long way: our method uses only 30 minutes of human demonstrations, 2500x fewer than comparable imitation learning approaches. Resulting policies coordinate with held-out human trajectories and complete training in 15 hours on a single consumer-grade GPU. Videos and full source code are available at https://spiced-self-play.com/.

In challenging real-world reinforcement learning applications, communication delays or sensor failures often cause frame dropping, in which the agent cannot receive the dropped states and associated rewards. To address the performance degradation caused by frame dropping, the Decision Transformer under Random Frame Dropping (DeFog) was developed by incorporating additional mechanisms into the decision transformer to tackle frame dropping. Although DeFog can mitigate performance degradation in frame-dropping environments, since DeFog is an offline learning method, it struggles to effectively generalize to novel states not adequately represented in the training dataset. In this study, we propose OnDeFog, which integrates the mechanisms in DeFog with the online decision transformer (ODT), an online reinforcement learning method that learns policies through direct environmental interaction. Comprehensive experimental evaluation demonstrates that our proposed OnDeFog achieves superior performance compared to ODT in environments characterized by high dropping frame rate and outperforms DeFog on datasets containing a large amount of low-reward data.

Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for such a capability. Although POMDP-based planning has advanced significantly, its application to real-world problems is often limited by the difficulty of obtaining faithful POMDP models. We present Vectorized Online planning wIth Learned diffusion model for POMDP Agents (VOiLA), a framework that learns task-agnostic POMDP models for online planning under uncertainty. VOiLA learns transition and observation samplers using conditional diffusion models and learns observation-likelihood models for particle-based belief updates. To enable efficient online planning, the diffusion samplers are distilled into compact feedforward generators and integrated with Vectorized Online POMDP Planner (VOPP), an online POMDP planner designed to leverage GPU parallelization. Experimental results indicate the distillation strategy reduces sampling cost by up to nearly three orders of magnitude, making learned generative POMDP models practical for online planning. Evaluation of VOiLA on three benchmark problems indicate that VOiLA achieves equal or better performance than Recurrent Soft Actor Critic while using less than 10% training data, and generalizes much better to unseen environment configurations. Physical robot evaluation indicates VOiLA uses the models learned using only simulated data and generates a policy that successfully accomplish the task in 10 of 10 runs.

In the agentic web era, LLM-based agents increasingly invoke web services as tools, yet most interfaces remain \emph{static endpoints} that poorly express long-horizon workflows with loops, conditionals, joins, and retries. We present ToolPro, which represents an agent's tool intent as an \emph{executable tool program} that compactly encodes multi-step service interactions with explicit effect types. ToolPro combines constraint-guided program construction, effect-aware replay for exactly-once state-modifying calls, and a profile-driven policy that decides when program execution outperforms stepwise calling. We instantiate ToolPro over MCP-style services with WebAssembly sandboxing and evaluate it on diverse workflows of real-world applications. ToolPro reduces end-to-end latency by up to 53.4\% and client-side traffic by up to 96.1\%, with larger gains under higher network latency and workflow complexity.

This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context. Major components of the CoD framework include: (1) algorithm design and infrastructure for end-to-end reinforcement learning (RL) with long rollout sequences interleaving solve-task and update-context episodes; (2) tasks and environments for incentivizing and eliciting the targeted meta-capability in LLMs during training, as well as for faithfully measuring progress during evaluation. We present proof-of-concept implementations of the CoD framework, including a GRPO-style RL algorithm with fine-grained credit assignment, as well as tasks and environments tailored to the targeted meta-capability (rather than domain-specific LLM capabilities or standard task-by-task RL). Empirical results validate the efficacy of end-to-end RL training in the CoD setting, and demonstrate the potential for out-of-distribution generalization -- within the training domains, across different domains, and from CoD to Ralph-loop settings -- of the elicited meta-capability. Our investigation of CoD connects several lines of prior works, and opens up new opportunities for advancing LLMs and AI agents. To facilitate further research and applications, we release our implementations at \url{https://github.com/agentscope-ai/Trinity-RFT/tree/research/cod/examples/research_cod}.

Biological experiment protocols are written in natural language, whereas automation systems rely on predefined control commands, creating a semantic gap that limits autonomous execution. Microplate-based automatic experiments are particularly challenging due to the need to simultaneously control well mapping, sample-reagent combinations, replicate placement, and parallel dispensing. This study proposes an agent-based protocol translation framework that converts natural-language microplate-based protocols into executable control commands for a robotic laboratory platform. A Parser Agent formalizes the natural-language protocol into a structured representation, and a rule-based mapping engine deterministically incorporates the operational constraints of the robotic laboratory platform to generate device-level control commands. A heterogeneous LLM Validation Agent verifies completeness, parameter accuracy, and execution order, and triggers a self-correction loop with structured feedback when errors are detected. A sweep involving 7 Parsers and 3 Validators on randomly selected ELISA protocols evaluates how model scale and Validator type affect translation accuracy and pass rates under cross-model verification. The accuracy-latency trade-off is further verified by comparing the rule-based mapping of the proposed framework with LLM end-to-end direct mapping. Finally, Bradford assay-based protein quantification using a microplate was demonstrated on a robotic laboratory platform, validating end-to-end autonomous execution from natural-language protocols to real-world experiments. The proposed framework provides a flexible approach to narrowing the semantic gap between natural-language protocols and microplate-based self-driving laboratories.

Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to orchestrate compiler options. The search process iteratively refines optimization configurations using measured runtime feedback to diagnose regressions and guide latency-improving edits. AutoPass operates in an inference-only, training-free setting and requires no offline training or task-specific fine-tuning, making it readily applicable to new benchmarks and platforms. We implement AutoPass on the LLVM compiler and evaluate it on server-grade x86-64 and embedded ARM64 systems. AutoPass outperforms expert-tuned heuristics and classical autotuning methods, achieving geometric-mean speedups of 1.043x and 1.117x over LLVM -O3 on x86-64 and ARM64, respectively.

LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back into proof search through a two-phase protocol: Best-of-N sampling first, then a critic-guided MCTS pass that ingests Phase 1 failures as explicit negative examples. The protocol preserves every theorem solved by its own Phase 1 sweep, so Phase 2's additional solves are attributable to feedback-driven exploration. VERITAS reaches 40.6% on miniF2F (vs. an independently run Best-of-5 at 36.9%, Portfolio 26.2%) and 7.3% on VERITAS-CombiBench, a 55-theorem combinatorics benchmark we release on which Best-of-5 (1.8%) falls below Portfolio (3.6%), exposing that unguided sampling hurts when correct lemma names must be recovered iteratively from verifier feedback. Artifacts are available on GitHub.

Recent work on Kan-Do-Calculus (KDC) has established that the boundary between passive observation and active intervention in causal inference is a category-theoretic bi-adjunction, with interventions modeled by left Kan extensions and conditioning by right Kan extensions. This paper introduces two causal discovery algorithms under latent confounding, building on the information-geometric and categorical consequences of KDC. In smooth statistical settings, Radon-Nikodym derivatives between observational and interventional measures induce local causal vector fields; failures of these fields to close under Lie brackets become computable Frobenius residuals, which we interpret as witnesses of failed visible integrability and possible latent or unmodeled structure. Our first algorithm, BRIDGE (Bracket Residuals for Interventional Discovery and Geometric Estimation), combines an interventional density or Radon-Nikodym-ratio engine with a geometric screen that proposes a high-recall family of admissible arrows, identifies non-closing visible pairs as latent-obstruction candidates, and passes the reduced family to downstream score-based or differentiable discovery routines. The second algorithmic contribution, Spectral Kan-Do Flow Matching (SKFM), learns amortized intervention fields and factors latent curvature spectrally, exposing the direct Lie-space endpoint toward which BRIDGE points. A detailed set of experiments show that both algorithms are capable of discovering causal models with latent confounders while collapsing the super-exponential space of possible DAGs by many orders of magnitude. This paper introduces a new paradigm in causal discovery, where latent structure is inferred directly from the geometry of intervention-induced flows.

When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped. Current retry strategies treat both cases identically (try again and hope for the best), leaving human supervisors unable to tell whether a retry was warranted or whether the system should have halted instead. We introduce the Argent Signaling Protocol (ASP), a compact machine-readable header that accompanies every AI-generated response with structured quality signals: certainty (@C), grounding (@G), stochasticity (@S), and an assumption index that classifies the evidentiary basis of each claim. These signals enable a controller to distinguish repairable failures from containment failures and route each case differently. We evaluate ASP in two modes. In standalone mode, a 27-question document-grounded QA benchmark over the Array BioPharma/Ono license agreement compares baseline prompts against ASP-instrumented controller actions across three local GGUF models. On Qwen~(0.8B), ASP improves pass rate from 11.1% to 33.3% and mean term coverage from 36.7% to 65.4%; on Dobby~(8B), ASP produces 4 fail-to-pass recoveries, raising pass rate from 33.3% to 44.4%; on SmolLM3~(3B), ASP alternates between repair and containment per question. Aggregate improvement is meaningful (12/81 to 21/81 passes). In multi-agent mode, an ASP sidecar sits between a retrieval agent and a downstream decision agent; the sidecar blocks 100% of ungrounded upstream outputs from reaching the downstream agent (24/27 blocked, 0 ungrounded propagations).

Autonomous coding agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that pull-request-level telemetry cannot explain. We argue the missing signal lives before the PR, in how concurrent agents claim, divide, and collide over shared work. We study this process through grite, our open-source coordination substrate that needs no central server and stores its records inside git itself, so its append-only, signed event log captures the coordination process directly. We show that (i) this shared substrate reduces duplicate and conflicting work at bounded overhead - the share of work that merely re-does a teammate's task falls from 78% to 0% while useful throughput more than triples; (ii) every agent's copy of the log converges to the same state with no write silently dropped, where a file-based tracker loses concurrent writes; and (iii) the log is a mineable artefact from which concrete failure modes - conflicting edits, lock starvation, redundant rediscovery, race-to-close - are automatically recoverable with provenance, several invisible in pull-request history. We release the dataset, harness, and mining toolkit.

Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks. Our four-stage pipeline consists of domain-specific feature extraction from agent observations, decision tree distillation achieving 97.9% +/- 1.2% fidelity to neural policies, automated translation to PRISM probabilistic model checker specifications with complete feature-to-state-variable correspondence, and compositional verification of Probabilistic Computation Tree Logic (PCTL) properties via pairwise decomposition with union-bound aggregation and empirical neighbor modeling. Evaluating Vector-Quantized Variational Information Bottleneck (VQ-VIB) policies for multi-drone coordination with 5-7 agents, we verify 18 temporal logic properties across safety, liveness, and cooperation, achieving 88.9% property satisfaction with all five safety thresholds satisfied (0.3% collision probability vs. 1% threshold). Monte Carlo validation of original neural policies confirms that verified safety properties transfer with <=0.6 percentage-point deviation (95% CI). Discrete VQ-VIB messages provide +11.6 to +13.6 percentage-point fidelity advantages over continuous methods, enabling 3-4x faster verification. Our framework provides empirically validated safety verification for distilled policy abstractions, serving as a practical bridge between deep MARL and formal safety workflows for multi-robot deployment.

Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and \emph{``Flat''} RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

This paper develops a general framework for analyzing multi-agent systems with feedback loops between agents actions and collective observations. The framework is built on two fundamental agent-level variables: power, which measures agent influence on collective outcomes, and response functions, which determine how agents react to observations. We derive how macroscopic properties, including total power, useful power, entropy, order, fragility, and mobility, emerge from these two variables of heterogeneous agents. To study the trade off between growth and resilience, we introduce a system-level utility function parameterized by a risk-appetite coefficient and derive an optimal degree of order that balances productivity, stability, and adaptability. The analysis suggests that stronger synchronization can increase collective output but may also increase systemic fragility and reduce mobility. We further argue that order, entropy, information, and useful energy are task-dependent and system-relative concepts whose meanings depend on the objectives of the system. By measuring and designing agent power distributions and response functions, it may be possible to better understand, predict, and optimize collective behavior and identify the conditions under which collective intelligence and optimal order emerge.

When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a formal framework for measuring how evaluator biases spread across interacting LLM agents. In a controlled 3-agent experiment using DeepSeek-chat with three distinct evaluator bias profiles (structured, balanced, evidence-based), we measure the Cross-Agent Contagion Matrix Gamma_3 and find that evaluator biases consistently propagate between agents (gamma in [0.157, 0.352]), even within the same underlying model. We identify three propagation regimes governed by the spectral radius rho(Gamma_N), and demonstrate that homogeneous-model agents produce contagion coefficients 3-5x weaker than cross-model coefficients observed in prior work (MM-EPC: gamma approx 0.85-1.3), placing them in the suppression regime. We show that increasing evaluator committee size from k=1 to k=3 reduces effective contagion by 72.4%, providing an actionable mitigation strategy. We release the open-source Contagion Network experimental framework.

Estimation-of-distribution algorithms (EDAs) are a powerful class of evolutionary methods for black-box optimization, especially when little is known about the structure of the objective. Whereas classical evolutionary algorithms rely on hand-designed mutation and crossover operators, hard to devise for unknown problem structures, and a source of bias, EDAs sidestep operator design entirely: they fit a probability distribution to the best individuals and sample the next generation from it. EDAs are well established on continuous parameter spaces, but they have not previously been generalized to sparse ones, in which most coefficients of a good solution are exactly zero. Existing sparse black-box optimizers therefore reintroduce exactly what EDAs were designed to avoid: hand-crafted sparsity operators, bi-level schemes alternating between support set and active values, zeroing thresholds, and other baked-in assumptions. We close this gap by proposing multivariate zero-inflated Gaussian (ZIG) distributions as EDA sampling laws. A latent Gaussian model with separate indicator and value dimensions represents sparsity patterns, correlations among active parameters, and the interactions between the two, so sparsity patterns and active values are optimized jointly, hierarchy-free. We show that the latent parameters of this model are identifiable from observed samples, unlike in the missing-data settings where related constructions originate, and introduce practical amortized inversion-based estimators for them. The estimators accurately recover latent correlation structures, and on the Lunar Lander benchmark the resulting ZIG-EDA converges faster and reaches higher final returns than a dense Gaussian EDA, a hand-crafted sparse evolutionary algorithm, and an ad-hoc sparse EDA, while finding controllers with only a small fraction of parameters active.

This work presents a tool for the synthesis and simulation of probabilistic architectures for solving combinatorial optimization problems by mapping them to the Ising model. The proposed approach automatically constructs the Ising Hamiltonian and determines the number of probabilistic elements (p-bits) based on problem characteristics such as size and topology. Furthermore, the tool introduces an adaptive strategy for selecting the most suitable update algorithm among Gibbs Sampling, Simulated Annealing (SA), Simulated Quantum Annealing (SQA), and cluster-based methods. Experimental results using benchmark problems demonstrate improved convergence behavior and flexibility compared to fixed approaches. The proposed framework enables systematic evaluation of probabilistic computing strategies and supports the development of future hardware implementations based on MTJs and p-bits.

Information lattice learning (ILL) learns interpretable rules of a signal by alternately projecting the signal onto a partition lattice that encodes a hierarchy of abstractions and lifting selected rules back to the signal domain. When the signal is a probability mass function, we show the probabilistic rules learned by ILL admit a natural probabilistic graphical model (PGM) interpretation and develop this interpretation in detail. A partition in ILL induces a deterministic quotient variable, and a rule is the marginal law of that quotient variable. A rule set is therefore a collection of marginal constraints over interpretable abstractions. General lifting is the feasible family of all joint distributions satisfying those constraints, while special lifting chooses a maximum-ignorance reconstruction, implemented in ILL by an L2 uniformity principle closely related to maximum entropy. Under a Shannon-entropy lifting, the same constraints yield a log-linear factor graph whose factors are indexed by learned abstractions. The information lattice itself, however, is not a Bayesian network: its edges encode refinement and coarsening of abstractions, not conditional dependence. Thus ILL is best viewed as structure learning for interpretable constraint-based factor graphs over quotient variables. This view clarifies how ILL relates to graphical models and maximum entropy models, while suggesting new directions for inference, identifiability, and hybrid symbolic-probabilistic learning.

Graph-based representations are widely used in protein modeling, yet many existing approaches rely primarily on sequence adjacency or geometric proximity, which only partially reflect the principles governing protein folding. Proteins instead adopt complex three-dimensional conformations organized around secondary structure elements, such as $α$-helices and $β$-sheets, which encode recurring local motifs and stabilizing hydrogen-bond interactions. In this work, we introduce a secondary-structure-aware graph neural network for protein representation learning. Residue-level node representations are augmented with secondary structure assignments, and graph edges are constructed from hydrogen-bond interactions filtered by their energetic strength. This design enables the model to capture both local structural context and long-range couplings that are central to protein stability and function. We evaluate the proposed approach on commonly used protein benchmarks and observe consistent improvements over existing graph-based methods. In addition, the resulting graph representations offer enhanced biological interpretability, as the learned connectivity aligns with established structural motifs. These findings suggest that incorporating secondary structure and energy-filtered hydrogen-bond topology provides an effective inductive bias for protein representation learning. The code is released at https://github.com/mohamedmohamed2021/SSProNet

Transformer feed-forward networks (FFNs) are often treated as nonlinear stores of computation, yet how nonlinear a trained FFN block actually is has rarely been measured. We treat each FFN as a position-wise input-to-output map and split it into the exact least-squares linear approximation plus a residual. The held-out variance the closed-form linear map explains defines a block's linear recoverability (R^2_lin), an optimiser-free measure of its linearity. Across all twelve blocks of GPT-2, Pythia-160m, and llama-160m, R^2_lin is highly heterogeneous and non-monotone with depth, ranging from near-linear (>0.99) to strongly nonlinear (<0.3) between adjacent blocks, and is not set by the activation function: same-width GELU models GPT-2 and Pythia-160m have sharply different profiles, so recoverability is a learned property of individual trained blocks, not an architectural one. A low-rank bilinear probe of the residual recovers only a few points of R^2, with gain uncorrelated with residual nonlinearity: the unrecovered computation is not a single position-wise product but higher-order or distributed structure. The measurement also serves as a targeted compression signal: recoverable blocks admit large single-layer replacements (GPT-2's early FFN at 8x fewer parameters for +0.77 perplexity), while low-recoverability blocks flag where this is unsafe. It further exposes a methodological pitfall: trained linear baselines can badly under-converge on ill-conditioned transformer activations, so we report the exact closed-form least-squares ceiling throughout.

Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge. Classic approaches incentivize exploration by rewarding an agent based on its "learning progress", which measures how much a newly acquired observation improves a world model's predictive ability. However, evaluating these rewards traditionally requires expensive inner loops of gradient descent updates within each trajectory, rendering them computationally impractical at scale. In this work, we investigate whether the emergent in-context learning (ICL) capabilities of sequence models can eliminate this bottleneck by serving as immediate, update-free world models. Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress, using solely the prediction errors and counterfactual context manipulations of an in-context learner. We first prove that in general Markov decision processes, this is in fact impossible in an unbiased way: the resulting intrinsic rewards either suffer from nuisance terms that bias their estimation of true learning progress, or they cannot be implemented using an in-context learner's prediction errors. Conversely, we prove a positive result for a broad subclass of non-temporal settings, encompassing active learning and Bayesian Experimental Design: here, ICL-derived rewards successfully bound and asymptotically converge to the true learning progress. We corroborate our theory with controlled experiments across continuous and symbolic environments, demonstrating that our ICL-driven framework successfully trains curious data-collection policies that explore optimally.

Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space. Recent approaches leverage vision-language models to generate concept embeddings, reducing the need for manual concept annotations. However, these models suffer from a critical limitation: as the number of concepts approaches the embedding dimension, information leakage increases, enabling the model to exploit spurious or semantically irrelevant correlations and undermining interpretability. In this work, we propose Concept Flow Models (CFMs), which replace the flat bottleneck with a hierarchical, concept-driven decision tree. Each internal node in the hierarchy focuses on a localized subset of discriminative concepts, progressively narrowing the prediction scope. Our framework constructs decision hierarchies from visual embeddings, distributes semantic concepts at each hierarchy level, and trains differentiable concept weights through probabilistic tree traversal. Extensive experiments on diverse benchmarks demonstrate that CFMs match the predictive performance of flat CBMs, while substantially mitigating information leakage by reducing effective concept usage. Furthermore, CFMs yield stepwise decision flows that enable transparent and auditable model reasoning with hierarchical class structures.

Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

Voice attribute editing models modify characteristics such as age and gender while preserving speaker identity. In large-scale speech datasets, however, attribute annotations are often noisy or inconsistent, which can cause conditional generative models to produce unstable edits. In this work, we show that idempotency provides an effective mechanism for improving robustness to noisy labels. An idempotent operator is one for which repeated application does not change the result, i.e., f(f(x)) = f(x). Enforcing this property acts as an implicit regularizer that reduces sensitivity to mislabeled examples. We introduce RIVET, a training framework that incorporates an idempotency objective to improve robustness to label noise. We evaluate RIVET under controlled label noise and on the GLOBE dataset with naturally noisy annotations. RIVET improves editing success and better preserves speaker identity than standard training, showing that idempotency improves robustness in voice editing models.

Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserving acceptable performance on past knowledge. One unresolved challenge is that existing methods modify a fixed set of layers for all new knowledge samples, reducing flexibility and increasing catastrophic forgetting. Another is requiring access to previous knowledge and extensive pre-processing to obtain data statistics. To address these challenges, we introduce LOKI, a novel approach that uses dynamic layer selection based on the Hilbert-Schmidt Independence Criterion and projects gradient updates onto the null-space of the model weights, bypassing the requirement for previous knowledge access. We show that LOKI achieves superior performance to existing approaches across a wide variety of experiments, achieving up to a 14\% improvement in average accuracy.

The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the \emph{Word RAM} model with random-access memory and unit-cost operations on $\bigO(\log n)$-bit words. As a result, Word RAM algorithms can be substantially more efficient than their Turing machine counterparts, raising the question: \emph{Can CoT transformers efficiently simulate Word RAM algorithms?} For instance, can they sort $n$ items in $\bigO(n \log n)$ steps or run Dijkstra's algorithm in $\bigO(E + V \log V)$ steps? We answer affirmatively, up to poly-logarithmic overhead. We first establish this for finite-precision transformers with poly-logarithmic width and rightmost unique hard attention, then strengthen the result to two more practical settings with finite width and log-precision: \emph{continuous} CoT, where reasoning takes the form of vectors rather than tokens, and a \emph{hybrid} architecture in which transformer layers sit atop a recurrent (linear RNN) layer. In all three cases, we find that CoT \emph{can} efficiently simulate any Word RAM algorithm with only a poly-logarithmic overhead in $n$. This overhead reduces to log-square when the Word RAM has a ``flat'' instruction set, and only logarithmic for multiplication-free flat instructions -- in stark contrast to known CoT simulations of Turing machines, which require quadratic overhead over Word RAM.

Aligning language models with human preferences often requires optimising multiple behavioural objectives. A practical approach is to apply these objectives sequentially using preference optimisation methods such as Direct Preference Optimisation (DPO), but it remains unclear whether later training uniformly degrades preferences learned earlier or whether the effect depends on the relationship between objectives. We study sequential DPO across four preference settings covering distributional conflict, multi-attribute interaction, strong safety signal, and compatible response-quality objectives. Using Llama-3.1-8B-Instruct with LoRA adapters, we evaluate all objectives after every stage with a fixed base-model reference. We find that sequential DPO does not produce a single forgetting pattern; preference change ranges from partial degradation to stability, pair-level redistribution, or positive transfer depending on objective relationship, signal strength, and training order. Pair-level analysis using length-normalised policy margins shows that aggregate metrics can mask heterogeneous changes across preference pairs, whereas quartile decomposition reveals that high-confidence pairs can either degrade or improve depending on the setting. Mechanistic diagnostics show that Stage~2 gradients and adapter updates are near-orthogonal to the previous objective across all settings, providing little evidence that direct gradient opposition is the primary driver. These findings suggest that future sequential alignment pipelines should account for objective compatibility and signal strength, rather than assuming that later objectives affect earlier preferences uniformly.

Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization. Existing adaptive curriculum learning methods typically prioritize prompts of intermediate difficulty, treating problem selection as a standard bandit problem with independent arms and overlooking the structured, heterogeneous nature of the task space. In this work, we frame problem sampling as a manifold-structured bandit problem with endogenous non-stationarity: problems are related through the model's latent representation space, and sampling decisions can steer how learning signals evolve across that space. To operationalize this perspective, we introduce Bayesian Manifold Curriculum (BMC), a structure-aware framework that organizes problems into a hierarchical task tree and applies Bayesian learning to guide sampling. Empirically, we find that different sampling strategies induce non-trivial tradeoffs between productivity (learning signal), diversity (coverage of the task manifold), and utility (evaluation relevance). These results show that prioritizing difficulty alone is insufficient for strong downstream performance, highlighting the importance of incorporating structure and type-awareness into problem sampling.

Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established for large language models, these relationships are emerging for large models in particle physics. As with language, empirical studies show that the performance scales as a power law. However, unlike natural language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining dataset itself to be engineered to influence the scaling. For the task of classifying hadronic jets produced in collisions of high-energy particle beams, we show that the scaling behavior can be engineered towards requiring more data rather than larger models by inclusion of pretraining data which is more diverse and better aligned with the downstream classification task.

Transferring the camera motion of a reference video to a freshly generated one lets creators reuse cinematic moves. Yet reference and target often live at incompatible scales -- a sweep across a galaxy versus a nudge across a desk -- and naively reusing the recovered trajectory yields either imperceptible or violently exaggerated motion. We trace this to a geometric fact: translation-induced image motion scales as ||T||/Z, so a monocular trajectory is meaningful only up to a depth-scale gauge. We distill this into the Parallax Number Pi = ||Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt, and prove that it -- not the raw trajectory -- is the quantity that scale-faithful transfer must preserve. ParaScale is a plug-and-play module that reads Pi off any reference video and re-realizes it against the target scene's own depth, per frame, leaving rotation untouched. Sitting between pose extraction and pose injection, it requires no retraining and drops into any pose-conditioned generator. We further introduce the Parallax Consistency Error (PCE), a scale-symmetric metric that -- unlike the similarity-aligned TransErr -- exposes scene-scale mismatch. Across scale regimes spanning four orders of magnitude and multiple backbones, ParaScale keeps the realized parallax on the identity line and cuts PCE by more than 3x over uncalibrated transfer with no loss of visual fidelity.

Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.

Deep neural networks (DNNs) exhibit attractive performance in various fields but often suffer from low interpretability. The neural additive model (NAM) and its variant called the neural basis model (NBM) use neural networks (NNs) as nonlinear shape functions in generalized additive models (GAMs). Both models are highly interpretable and exhibit good performance and flexibility for NN training. NAM and NBM can provide and visualize the contribution of each feature to the prediction owing to GAM-based architectures. However, when using two-input NNs to consider feature interactions or when applying them to high-dimensional datasets, training NAM and NBM becomes intractable due to the increase in the computational resources required. This paper proposes incorporating the feature selection mechanism into NAM and NBM to resolve computational bottlenecks. We introduce the feature selection layer in both models and update the selection weights during training. Our method is simple and can reduce computational costs and model sizes compared to vanilla NAM and NBM. In addition, it enables us to use two-input NNs even in high-dimensional datasets and capture feature interactions. We demonstrate that the proposed models are computationally efficient compared to vanilla NAM and NBM, and they exhibit better or comparable performance with state-of-the-art GAMs.

Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal complexity, inherent noise, and limited labeled data. While recent self-supervised learning (SSL) methods, based on various encoder architectures such as convolutional neural networks, have been proposed to learn representations from unlabeled data, they often fall short in capturing long-range dependencies and noise-invariant features. Structured state space models (S4) excel at long-sequence modeling, but existing S4 architectures fail to capture the unique characteristics of multichannel physiological waveforms. In this work, we propose SL-S4Wave, a self-supervised learning framework that combines contrastive learning with a tailored encoder built on structured state space models. The encoder incorporates multi-layer global convolution using multiscale subkernels, enabling the capture of both fine-grained local patterns and long-range temporal dependencies in noisy, high-resolution multichannel waveforms. Extensive experiments on real-world datasets demonstrate that SL-S4Wave (1) consistently outperforms state-of-the-art supervised and self-supervised baselines in a challenging arrhythmia detection task, (2) achieves high performance with significantly fewer labeled examples, showcasing strong label efficiency, and (3) maintains robust performance on long waveform segments, highlighting its capacity to model complex temporal dynamics in long sequences that most existing approaches fail to efficiently model, and (4) transfers effectively to unseen arrhythmia types, underscoring its robust cross-domain generalization. We additionally evaluate SL-S4Wave on multiple EEG tasks, achieving superior performance over strong baselines, demonstrating generalizability of our approach beyond cardiac waveforms.

Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a severe performance collapse. We attribute this degradation to the spatially agnostic nature of existing reduction methods, which violate the two-dimensional structural premise required by the selective scanning mechanism. In this work, we propose STORM, a spatial-aware token reduction framework designed to maintain structural integrity throughout the compression process. STORM reformulates reduction into a structured operation on spatial units, enforcing localized constraints to maintain both grid topology and neighborhood coherence. As a plug-and-play module, STORM equips existing reduction pipelines with explicit spatial awareness without any training. Empirical results demonstrate that STORM achieves state-of-the-art pruning accuracy across diverse vision Mamba backbones under training-free settings. Notably, STORM delivers a substantial accuracy recovery on VMamba, outperforming prior methods by up to 63.3\% in top-1 accuracy. Meanwhile, STORM incurs only a 1.0\% accuracy drop on PlainMamba, achieving performance comparable to ViT.

We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.

Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training. However, existing approaches materialize both attention distributions before computing the KL reduction, incurring $O(N_QN_K)$ memory and IO costs that become prohibitive at long context lengths. We present StreamKL, the first fused GPU primitive for attention KL divergence that eliminates this quadratic materialization. StreamKL derives a novel online formulation for the coupled two-distribution KL reduction, enabling a single one-pass forward kernel that streams query-key tiles through on-chip SRAM. For the backward pass, StreamKL recomputes attention probabilities tile-by-tile, avoiding storage of quadratic intermediates. We further design and implement efficient GPU kernels with dedicated optimizations. Experiments show StreamKL delivers up to $43\times$ and $14\times$ speedups over baseline methods in the forward and backward passes, respectively. Most importantly, StreamKL reduces the extra HBM footprint of attention distillation from $O(N_QN_K)$ to $O(1)$, enabling long-context distillation on a single GPU.

Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Variable-length tokenizers (VLTs) promise adaptive compression by varying token counts, allowing diffusion models to flexibly balance quality and compute. However, conventional VLTs modulate length by truncating ordered token sequences, which makes token semantics depend on token position and breaks representational alignment across lengths. This leads to a cross-length shift in the latent distribution that hinders a single variable-length diffusion model from operating effectively. To address this, we propose a novel variable-length tokenizer that modulates length by merging tokens. We show that encouraging similar tokens to merge enables direct cross-length representation alignment when the diffusion transformer operates according to the merging pattern. Since conventional merging methods are data-dependent, making the merging pattern inaccessible during generation, we introduce learnable global merging, which is data-independent, to ensure compatibility with diffusion transformers. On ImageNet 256$\times$256 generation, our merging-based variable-length tokenizer integrated with a diffusion transformer achieves a superior gFID-compute trade-off compared to prior VLT methods. Code is available at [this https URL](https://github.com/movinghoon/lgm)

Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-style world models advocate learning compact predictive states from high-dimensional observations to facilitate the prediction of future states, but end-to-end training of these models is nontrivial because representations may collapse if our only goal is to construct a latent state that is easy to predict. We introduce a sensorimotor world model (SMWM): a latent world model trained end-to-end with inverse dynamics regularization. This single regularizer addresses both issues: it prevents representation collapse and induces action-aligned representations. By forcing latent states to preserve information about the action underlying a transition, it biases the model toward the controllable degrees of freedom of the environment while discarding uncontrollable distractors. This yields stable latent world models trained from offline, reward-free trajectories, without frozen encoders, exponential moving averages, or complex latent regularizers. Empirically, SMWM learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.

This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable high-performance spiking neural networks (SNNs). The architecture couples a pretrained EfficientNet encoder with a CoLaNET spiking classifier. We convert the encoder's activations into spike trains via rate-coding and train the subsequent SNN classifier using local, biologically inspired learning rules, bypassing end-to-end gradient propagation. This approach achieves 99.09% accuracy on a 64-class ImageNet benchmark, demonstrating performance on par with conventional deep networks. The work presents a biologically plausible and efficient framework for adapting powerful pretrained encoders to downstream spiking neural network tasks.

Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.

Machine learning algorithms deployed for evolving streaming environments must handle the non-stationary data distributions, commonly referred to as concept drift. The presence of concept drift poses a major challenge for many real-world applications because it can severely degrade their predictive performance, hindering their ability to support robust decision-making. Consequently, the timely and efficient detection of drift events is critical for sustaining high accuracy over time. This study examines theoretically the concept drift characteristics and numerous drift detection algorithms across several categories. Furthermore, we evaluate their performance on both synthetic and real-world datasets exhibiting diverse streaming scenarios and drift characteristics, such as abrupt and gradual changes. This study aims to enhance understanding of the complex notion of concept drift characteristics and behavior of drift detectors, along with their applicability to diverse contexts.

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference. In this work, we reveal a highly non-trivial architectural characteristic of these continuous control foundation policies (e.g., pi_0, GR00T-N1.5): despite being trained on diverse physical trajectories, they exhibit severe layer-wise representational redundancy. To exploit this, we introduce a structural compression pipeline that is entirely training-free, bypassing the need of existing methods to load full-scale models to learn optimized token reductions or dynamic layer selectors. Instead, using only a single forward pass via Centered Kernel Alignment to identify redundant layer features, we remove twin layers to permanently compress the model depth by up to 50% across both the VLM backbone and the continuous control policy head. Downstream fine-tuning of this streamlined architecture yields a dual acceleration benefit: a 40-50% reduction in training time and up to 30% faster real-time inference, while matching or exceeding full-scale base model performance. We comprehensively validate our method across three simulation benchmarks (LIBERO, RoboCasa, SimplerEnv) and 10 diverse real-world manipulation tasks across 4 unique robotic embodiments. These results prove that advanced VLAs require significantly fewer layers than previously assumed, offering a highly compute-efficient paradigm for scalable robot learning.

Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near class boundaries in the embedding space, where amplified structural noise blurs decision boundaries and destabilizes predictions. Existing robust GNN methods largely treat all nodes uniformly, ignoring boundary vulnerabilities. In this paper, to improve classification performance, we tackle graph structural disentanglement by identifying boundary-region entanglement as the primary bottleneck and propose Boundary Embedding Shaping (BES), an adaptive contrastive learning GNN plug-in module that selectively suppresses spurious structural noise at decision boundaries with minimal model parameter perturbation. Extensive experiments demonstrate that BES consistently improves boundary discrimination and outperforms existing leading methods. Notably, BES boosts GCN performance by an average of 3.3% in node classification (up to 5.0% on WikiCS) and achieves superior accuracy in link prediction.

In this article, we present a robust $Q$-learning algorithm for discrete-time mean-field control problems under Wasserstein uncertainty in the common noise law. The algorithm combines a quantization-and-projection scheme with a Wasserstein dual reformulation on the common-noise space. We establish its convergence together with finite-time iteration bounds for both synchronous and asynchronous learning schemes. Numerical experiments on systemic risk and epidemic models compare the asynchronous implementation with an idealized Bellman iteration, illustrate the robustness-performance tradeoff under common-noise misspecification, and report the observed convergence behavior of the asynchronous $Q$-learning algorithm.

Classifier guidance is a way to control diffusion generation by using a noise-conditioned classifier to steer the sampling process toward a target class. One drawback of classifier guidance is that it requires two separately trained models: a classifier and a diffusion model. We therefore study a more compact alternative in which a conventionally trained speech classifier is repurposed as the backbone for diffusion generation. Starting from a frozen noise-conditioned classifier in log-Mel space, we attach a lightweight subnetwork that reuses intermediate classifier representations and train only this subnetwork under a Denoising Score Matching objective. Our work shows that a pretrained classifier can be repurposed for conditional generation, providing an appealing bridge between discriminative modeling and conditional speech synthesis resulting in high speech quality within a single-backbone model, with reduced memory footprint and computational cost.

LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, DiffusionGemma performs a larger fraction of its computation in a continuous latent space; does this make its reasoning less transparent? We study this question by decomposing transparency into two components: variable transparency, whether we understand intermediate snapshots of a model's computational state; and algorithmic transparency, whether we can use these snapshots to reconstruct the process by which the model arrived at its outputs. Naively, DiffusionGemma has poor variable transparency: its opaque serial depth, the amount of serial computation that occurs in between interpretable model states, seems at first 28.6X higher than the corresponding autoregressive Gemma 4 model. However, we show that we can map the information flowing between denoising steps through an interpretable token bottleneck with no decrease in downstream performance. Treating these intermediate states as interpretable reduces the opaque serial depth to just 1.1X that of Gemma 4. Algorithmic transparency is harder for diffusion models than for autoregressive models because all token predictions in the canvas can change at every denoising step, giving the model the power to implement complicated distributed algorithms during the denoising process. To begin bridging this gap, we conduct a suite of interpretability case studies, uncovering initial evidence of novel diffusion-specific phenomena such as non-chronological reasoning, token and sequence smearing, and intermediate-context reasoning. Finally, we test monitorability, a key application of transparency that measures whether model outputs are useful for downstream tasks. We find that DiffusionGemma is similarly monitorable to Gemma 4.

Neural Text-to-Speech (TTS) systems achieve remarkable quality on short utterances but long-form speech generation shows prosodic drift, speaker inconsistencies and sentence boundary artifacts. Existing approaches either compress sequences, increase context length or naively concatenate independently synthesized chunks. We present an inference-time approach called MagpieTTS-LF that enables MagpieTTS to produce coherent long-form speech without model retraining. Our method introduces three key innovations: (1) soft attention priors to guide monotonic alignment while preserving past and future context; (2) a stateful inference algorithm that maintains context across sentence chunks, ensuring prosodic continuity; (3) history-aware text encoding that uses past text for discourse-level prosodic planning. Experiments on long texts show significant improvements in long-range intelligibility, prosodic coherence, speaker consistency, and boundary naturalness compared to other baselines.

We study cross-lingual transfer by fine-tuning seven large language models (4B--671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding -- the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.

Translating sequential programming priors into the parallel temporal logic of hardware design remains a crucial bottleneck for large language models(LLM). To investigate this, we introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory. Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types. Evaluations reveal a strict empirical ceiling on the VerilogEval benchmark, as frontier models plateau at a 90.8% initial pass rate. These plateaus are defined by unsolvable functional errors, exposing persistent knowledge gaps immune to test time compute scaling. Furthermore, we expose a striking surface convergence gap: optimization readily eliminates syntax errors but concurrently exacerbates deeper functional failures. Our findings demonstrate that alignment techniques merely teach models to compile. While repeated sampling strategies can patch solvable errors, register-transfer level(RTL) coding capacity remains strictly bounded by pretraining knowledge. Addressing challenges in the current LLM based hardware generation pipeline requires more studies in model reasoning rather than alignment interventions.

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

While In-Context Learning (ICL) is extensively studied in Autoregressive (AR) LLMs, its mechanism within Diffusion Large Language Models (dLLMs) remains largely unexplored. Unlike AR models restricted by unidirectional causal masking, dLLMs intrinsically utilize bidirectional attention, offering extensive spatial flexibility for query placement. Unfortunately, current practices conventionally inherit AR-style trailing-query templates, often overlooking the structural paradigm shift. This paper presents a comprehensive analysis unveiling that query position is actually a first-order variable in dLLMs. Through empirical decoupling, we demonstrate that positional variance impacts generation quality on par with example semantic quality. Internally, this positional sensitivity stems from a spatial ``Recency Effect'' in attention flow and task-dependent shifts in decoding trajectories. To mitigate this instability without ground-truth labels, we reveal that traditional single-step confidence ($C_{decoded}$) fails in dLLMs. Instead, we propose Average Confidence ($\overline{C}$), a novel metric tracking the iterative decoding process. By establishing the foundational spatial ICL baselines, we introduce Auto-ICL, a training-free adaptive routing strategy that dynamically optimizes query placement, robustly approaching oracle performance across heterogeneous reasoning and perception tasks.

Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support. With the rapid development of large language models (LLMs), LLM-based KG reasoning frameworks have become increasingly popular by leveraging retrieved KG information. However, hallucinations in LLMs remain a critical issue. Even when relevant KG knowledge is incorporated, models may still generate incorrect outputs, leading to misinformation and unreliable decisions. Existing hallucination detection methods either focus on LLM internal states or verify consistency with retrieved contexts, but both overlook the structural information in KGs, resulting in suboptimal performance. To address this gap, we propose LUCID, the first halLUcination deteCtIon method for LLM-based knowleDge graph reasoning frameworks. LUCID jointly leverages LLM attention scores, KG semantics, and structural information. Specifically, it extracts node and edge features from attention scores and semantic similarities, and integrates them with KG structure using a graph neural network. We also construct manually annotated benchmark datasets for evaluation. Experiments on nine datasets show that LUCID achieves state of the art performance compared to 15 baselines.

Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a fundamental tension between cost and quality. Recent progress on cost-aware LLM request routing has shown potential to resolve this tension, but existing approaches rely on complete feedback signals, offline training, extensive per-workload tuning, and most lack SLA guarantees or inference-time adaptivity. We introduce SLARouter, an online routing algorithm that learns a cost-optimal policy from the sparse, one-sided user feedback available in production systems. SLARouter provides theoretical guarantees for both cost optimality and strict SLA compliance. Experiments across a wide range of LLM benchmarks show that SLARouter satisfies SLA constraints without the need for per-benchmark tuning, reducing operating cost by up to 2.2x over existing baselines.

Code-switch (CS) Automatic Speech Recognition (ASR) remains challenging due to limited availability of high quality CS text-speech pairs for training. Although synthetic data augmentation via Text-to-speech (TTS) has been explored, existing CS TTS approaches primarily optimise reconstruction fidelity and do not explicitly enforce language-boundary consistency, thereby limiting their effectiveness for CS ASR augmentation. This paper proposes a code-mixing guided preference-learning framework that steers synthetic speech generation toward improved code-switching fidelity using the Code Mixing Index (CMI). Experiments on the SEAME Mandarin-English conversational corpus demonstrate that the proposed method enhances the utility of synthetic data for ASR fine-tuning. Specifically, when fine-tuning Whisper Large, the proposed approach reduces Mixed Error Rate (MER) from 12.1%/17.8% to 8.9%/14.2% on the DevMAN and DevSGE sets, respectively.

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models. Code, models, and datasets are released.

In this technical report, we focus on solving the challenge of Vietnamese multi-document abstractive summarization, introduced in the International Workshop on Vietnamese Language and Speech Processing (VLSP) 2022. We choose to follow the popular hierarchical approach, i.e. condensing each document followed by aggregation and summarization. We propose a novel yet simple strategy to shorten documents that is driven by the golden summary, thus ensuring high correlation between stages of the hierarchical approach. Our method achieves a ROUGE2-F1 score of 0.2468 on the VLSP's public test set, and can produce fluent and concise summaries. Additionally, we utilize external sources for extra data, which greatly enhances the quantity of data for Vietnamese multi-document summarization. The additional data is made available for the community.

Diffusion models have achieved remarkable success in image and video generation and editing. While recent studies have extended these efforts toward motion editing, simultaneously transforming both motion and location-despite its practical importance-remains largely unexplored. To better understand robust motion-location editing, we first analyze the fundamental factors that degrade its quality. Based on this analysis, we propose TeleMorpher, one of the first one-shot frameworks to the best of our knowledge, for simultaneous motion-location editing. Our approach leverages motion priors, a target motion-centric video generated from an off-the-shelf model as motion-editing guidance, and the ground truth motion to enable more controllable and precise motion-location editing. Via this, our framework works as follows: (1) we first disentangle the protagonist and the background via pre-trained segmentation and inpainting models. (2) Then, we introduce a training-free pose warping that edits the protagonist's motion with the motion prior as the guidance. (3) The result of warped motion video is directly injected into a baseline motion editor during inference, mitigating the difference between source and target motions while preserving the appearance of the source video. (4) To enhance the reliability of quantitative evaluations, we propose two new LPIPS-based metrics that measure the background consistency before and after the motion editing and the fidelity of motion editing performance via measuring the difference between the extracted protagonist's skeletons from source and target videos. Experiments with in-the-wild videos and the TaiChi dataset demonstrate that TeleMorpher achieves superior performance across both quantitative and qualitative measurements (real-human evaluation), underscoring its effectiveness.

Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis. Existing approaches predominantly follow a "scene-level embedding" paradigm, which requires distilling high-dimensional semantic features into every 3D primitive. This strategy suffers from a fundamental architectural bottleneck: memory and computational costs scale linearly with scene complexity, inevitably triggering out-of-memory (OOM) failures in city-scale environments. To address this barrier, we propose QueryGaussian, a training-free framework for expeditious and scalable open-vocabulary 3D instance retrieval. Unlike holistic semantic distillation, QueryGaussian employs an instance-level query mechanism that decouples semantic understanding from geometric representation. Specifically, we leverage pre-trained 2D vision models to interpret user prompts and lift segmentation masks into 3D via a concurrent maximum-weight association strategy, ensuring semantic-visual consistency. To mitigate projection ambiguity, we introduce a temporal fusion module with multi-stage adaptive density clustering. Experimental results demonstrate that QueryGaussian not only matches the accuracy of state-of-the-art methods but also delivers a decisive efficiency leap, reducing GPU memory usage by over 70% and accelerating inference by 180x. Crucially, QueryGaussian enables expeditious instance retrieval on city-scale scenes containing tens of millions of Gaussians using consumer-grade hardware.

Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual forms that sacrifice human readability while remaining recoverable by LLMs. We refer to this class of model-centric textual representations as BabelTele, approached here not as a fixed protocol but as an empirical probe into LLMs' capacity to generate and interpret such representations. Through readability diagnostics, model likelihood measures, human questionnaires, and downstream task evaluations, we find that BabelTele can substantially depart from ordinary natural language while preserving core semantics for instruction-tuned LLMs. As a task-agnostic representational paradigm, BabelTele demonstrates high information density, maintaining 99.5% semantic fidelity even when the text volume is condensed to 27.9% of its original length. We further evaluate its semantic robustness in cross-model transfer, agent memory, and multi-agent communication. Results suggest that BabelTele can reduce context overhead while generally maintaining reliable downstream performance, although its effectiveness depends on the compressor-reader pair and task setting. These findings indicate that human readability, natural-language typicality, and model-side semantic recoverability can be partially decoupled, opening a path toward model-native representations in future exploration of LLM systems.

Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language space depends entirely on the integration architecture. Whether by treating visual tokens as in-context prompts within the input sequence or injecting them directly into the LLM's intermediate layers. A controlled comparison and understanding of how these architectural choices affect visual information and its internal transformation to integrate with the LLM remains underexplored. We provide a fair comparison by evaluating in-context and layer-wise injection VLM integration paradigms under identical training conditions across single image, multi-image, and video benchmarks. In doing so, we uncover a hidden evolution where visual tokens enter the LLM as disguised visual context, raw representations lacking linguistic structure, but are progressively reshaped depending on the integration paradigm, each capturing fundamentally different frequency characteristics of the visual signal. We show that this evolution inside the LLM determines what visual features the VLM can utilize effectively, how visual representations align with the language space, and ultimately how each paradigm performs across different tasks. We further demonstrate that attention allocation alone is insufficient, and that performance is driven by the quality of visual representations at each layer.

Audio editing aims to modify specific content in an existing audio clip according to a natural language instruction while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion transformers provide stronger global modeling and multimodal fusion, but existing editing architectures usually adopt a simple stack of MMDiT and DiT blocks. Applying joint attention over concatenated audio and text tokens in all blocks results in quadratic complexity with respect to token length. To balance editing performance and efficiency, we propose a hybrid two-stage diffusion transformer architecture for instruction-guided audio editing based on rectified flow matching. It performs joint attention over audio and text tokens to establish coarse semantic alignment at low-resolution stage, then switches to alternating joint-attention and cross-attention blocks to refine editing details at high-resolution stage. This coarse-to-fine strategy enables efficient and accurate instruction-guided audio editing. Experiments show that the proposed framework achieves notable performance gains on challenging editing tasks involving overlapping audio events and complex instructions, while substantially improving editing efficiency with a compact model.

Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly understood. In this work, we systematically analyze the hidden representations of eight LLMs across two English essay datasets (ASAP++, CSEE) and one Portuguese dataset (ENEM). Using linear probing, cross-prompt generalization, dimensionality reduction, and neuron-level analyses, we find consistent evidence that essay quality information is encoded in a linearly accessible form within LLM representations. These representations emerge progressively across layers, remain robust across prompting strategies, and partially transfer across essay prompts despite differences in scoring rubrics. In addition, nonlinear probes provide only marginal and inconsistent improvements over linear probes, suggesting that most essay quality information is already linearly decodable. We further identify individual ``essay scoring neurons'' whose activations strongly correlate with essay scores and whose behavior is sensitive to targeted intervention. Moreover, the layer-wise distribution of these neurons systematically shifts with essay length, with longer essays relying more heavily on deeper layers. Overall, our findings provide evidence that LLMs encode structured representations related to essay quality and offer new insights into the interpretability of LLM-based AES systems.

Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidence-grounded confidence or shortcut collapse. To resolve this ambiguity, we introduce low-entropy anchors and an entropy-shaping objective that reduces answer uncertainty while preserving baseline high-confidence tokens. We instantiate this principle in SPOT-E, a plug-and-play test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning based on Group Relative Policy Optimization (GRPO). Across all benchmarks and different VLM families, SPOT-E yields consistent gains and improved robustness under visual corruptions. Code is publicly available at: \url{https://github.com/YinBo0927/SPOT-E}

We introduce the Meaning Intelligence Framework (MIF), a nine-dimension annotation and evaluation schema for Nigerian public discourse that separates surface sentiment from true communicative intent. Existing benchmarks for Nigerian languages, including NaijaSenti and AfriSenti, treat sentiment classification as a three-way polarity task (positive, negative, neutral). We argue that the dominant failure mode of AI systems on Nigerian discourse is not translation failure but context failure: the same utterance carries opposite pragmatic force depending on speaker, audience, and situation. The MIF operationalises this insight across nine scored dimensions: register, surface sentiment, true intent, irony, coded subtext, risk tier, annotator confidence, speaker emotion, and recommended communications action. We construct a 30-item calibration dataset spanning Standard English, Nigerian English, Nigerian Pidgin, and code-mixed registers, and evaluate a frontier language model (Gemini 2.5 Flash) under zero-shot and schema-informed prompting conditions. The headline finding is the Register Gap: zero-shot register classification accuracy is 33.3%, rising to 73.3% (+40 points) when the model receives the MIF schema in-context. The composite Meaning Intelligence Score increases by 5.4 points (73.2 to 78.6) under schema-informed prompting, with the largest practical gains in register identification, coded-subtext detection (+10 points), and strategic action recommendation (+10.3 points). We release the framework specification, annotation guidelines, and the 30-item public calibration set to support reproducibility, while retaining a private holdout corpus for contamination-protected evaluation.

Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style alignment, and instruction following avoiding semantic leakage from the style reference.A key bottleneck is the lack of large-scale triplet data with clean content-style separation and broad long-tail style coverage.In this work, we propose FreeStyle, a scalable dual-reference generation framework based on community LoRA mining.We treat community LoRAs as compositional anchors for style and content, and design a rigorous generation and filtering pipeline to construct large-scale Style-Reference and Content-Reference triplets across multiple base models.To address content leakage, we adopt a two-stage curriculum with stage-specific disentanglement mechanisms: an attention-level enrichment constraint that suppresses style-reference leakage in the style-transfer stage, and a frequency-aware RoPE modulation strategy that targets positional-correspondence-based leakage in the harder dual-reference stage.We also introduce a benchmark covering both style-reference and dual-reference generation, with evaluations on style similarity, content preservation, aesthetics, instruction following, and leakage rejection. The benchmark incorporates a style-invariant Content Alignment Score (CAS) and introduces a calibrated VLM-based Rejection Score for evaluating generation reliability and leakage suppression.Extensive experiments show that our model achieves a strong balance among style alignment, content preservation, and leakage suppression.

Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical behaviors. At the core of generative recommendation lies item tokenization, which bridges item semantics and recommendation models. However, existing methods often struggle to effectively organize and inject complex user-behavioral and item-semantic contexts into recommendation models simultaneously. On the one hand, existing graph-based integration methods, such as graph serialization and graph neural networks, either suffer from scalability issues or exploit only local graph information. On the other hand, existing semantic tokenization methods typically rely on heuristics and lack explicit supervision signals, which may lead to inaccurate or suboptimal semantic representations. To address these limitations in user interest context modeling, we propose G2Rec, a scalable framework that unifies holistic graph-based user co-engagement modeling with semantic tokenization for industrial-scale generative recommendation. Overall, G2Rec enables recommendation models to capture holistic and semantically grounded user interest prototypes without requiring ground-truth user interests, thereby providing more comprehensive and accurate modeling of user behavior contexts in industrial sequential recommendation. Online deployment across product surfaces and extensive experiments on public datasets demonstrate the superiority of G2Rec over existing methods.

Humans can grasp objects effortlessly, whereas multi-fingered robots are far from this level of generality. We argue that the most natural source of robot grasping data is from humans, who pick up thousands of objects every day. We present HUG, a flow-matching model that generates diverse human grasps for any user-specified object in a single RGB-D image captured from a stereo camera. Using smart glasses, we first collect 1M-HUGs, an egocentric dataset of human grasps spanning 1M frames (27.8 hrs) and 6,707 object instances across 41 buildings. Next, to model the distribution of natural human grasps, our novel flow-matching model fuses RGB and depth observations to output a grasp parameterized by wrist translation, wrist rotation, and MANO hand pose. Predicted grasps can be retargeted to various robot hands, enabling zero-shot grasping in everyday scenes. To standardize evaluation, we build a new simulated benchmark, HUG-Bench, of 90 unseen objects from five geometric categories and various sizes, with metric-scale 3D meshes. We evaluate HUG in the real world on the 30-object test set of HUG-Bench across multiple stereo cameras, robot embodiments, and household environments. HUG outperforms the state-of-the-art grasping baselines by +23% and +34% on our challenging object set. Code, data, benchmark, checkpoints, and an interactive demo are released on our website: https://grasping.io/

We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

Perceptive legged locomotion over discontinuous terrain (e.g., stairs, gaps, and obstacles) requires adaptive behavior, as a single conservative gait cannot produce the anticipatory maneuvers needed for abrupt topology changes. Cast as multi-task reinforcement learning, this problem introduces a tension between sharing and separation. Tasks use a common locomotion base but have conflicting rewards, so a policy must share behavior while avoiding value interference. Prior work addresses only one side, with monolithic policies sacrificing specialization and hierarchical sub-policies sacrificing generalization across transitions and unseen terrain. We propose CTS-MoE, which combines a dense mixture-of-experts actor with perception-based gating to compose shared behaviors and a multi-critic with task-specific value heads to prevent interference. The model is trained end-to-end in a single-stage concurrent teacher-student setup that handles partial observability and avoids sequential distillation, with task labels used only during training. At deployment, routing depends solely on perception, allowing terrain adaptation without a high-level selector or terrain classifier. Experiments on a Unitree Go1 in simulation and on hardware across seen and unseen terrains show task-aware specialization, with lower tracking error and higher success rates than monolithic baselines. Project Website: https://cts-moe.github.io/ .

Infants are well known to develop their motor skills through dense interaction with caregivers. Although such social interaction is crucial for human development, motor-skill learning in robots is often treated as a unidirectional process in which robots passively receive demonstrations from tutors. This overlooks a key property of social interaction: it is inherently bidirectional, with tutor and learner dynamically adapting to each other. In such interactions, the robot's past experiences may function as prior constraints that shape the dynamics of their co-developed trajectories. We hypothesize that bidirectional tutoring allows such constraints to guide the formation of consistent behavioral patterns that preserve behavioral coherence and support generalization, whereas unidirectional interaction lacks such constraints and leads to broader, less consistent behavioral patterns. To examine this hypothesis, we conducted two experiments with a physical humanoid robot performing an object manipulation task: one involving human-robot interaction and another employing an AI tutor interacting with the real robot through an adaptive intervention mechanism designed to examine whether similar effects would emerge under more controlled conditions. We implement the developmental learning framework using a free-energy-principle-based neural network extended with generative replay, which supports stable sequence-by-sequence learning from single tutored episodes. Across both settings, bidirectional tutoring fostered consistent behaviors and stage-wise generalization, while the robot gradually required less tutor guidance. These results suggest that bidirectional tutoring, as an embodied and socially grounded approach, provides an effective scaffold for developmental motor learning in robots.

Long-horizon robot manipulation policies trained with reward shaping can still exploit dense rewards through inefficient interaction, while rare efficient behaviors may be forgotten during training. We argue that temporal efficiency itself provides a powerful and underutilized source of self-supervision for reinforcement learning. We introduce Temporal Self-Imitation Learning (TSIL), a reinforcement learning framework that mines temporally efficient successful trajectories generated during learning and converts them into reusable supervision for future policy improvement. TSIL progressively refines learning using configuration-conditioned adaptive temporal targets derived from fast successful trajectories, while preserving and replaying efficient behaviors through efficiency-weighted self-imitation learning. Across 15 distinct long-horizon manipulation tasks, TSIL consistently improves learning efficiency, task-completion efficiency, revisitation of fast successful behaviors, and robustness to unstable training conditions. More broadly, our results suggest that the temporal structure of successful behavior itself provides a scalable self-supervisory signal for reinforcement learning beyond manually engineered reward shaping alone.

Art has long stood as a pivotal expression of human creativity. Embodied artificial intelligence offers a route for generative models to participate in that creativity through physical action rather than disembodied digital content. In robotic music co-creation, it is challenging to connect semantic musical understanding with real-time and physically executable performance. We present Co-policy, a framework for human-robot musical co-creation that separates semantic intent grounding, constrained musical variation, and visuomotor execution. To ground musical semantics, Co-policy uses pre-inference semantic anchors and a fine-tuned Qwen-vl planner (F-Qwen) to transform speech, live musical seeds, and visual observations into structured co-creation plans. To support low-latency execution, Co-policy introduces a Gaussian-Mixture Visuomotor Policy (GMP), implemented as a conditional mixture-density policy that maps target notes and visual context to multimodal robot actions in a single forward pass. Unlike robotic playback systems that merely reproduce user-specified notes, Co-policy generates complementary musical responses under both musical and physical constraints. Real-robot chime experiments, ablations, and expert evaluation show improved intent alignment, execution accuracy, and response frequency over diffusion-policy and ablated baselines, supporting physically grounded action generation as a key requirement for embodied human-AI co-creation.

Vision-Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they remain black boxes whose physical interactions can cause irreversible harm, making generalizable and interpretable failure detection essential. We observe that successful and failed rollouts carry systematically different information-theoretic signatures. Building on this, we formalize VLA control as a closed-loop information pipeline and derive the Triple Information-theoretic (Tri-Info) signals that capture whether actions remain diverse, temporally consistent, and coupled to state transitions. Across six VLA models and three benchmark environments, Tri-Info matches the strongest baselines in-domain. Moreover, Tri-Info transfers across architectures, environments, and the sim-to-real gap without retraining, reaching 83\% accuracy on real-world tasks where prior detectors collapse to chance. This establishes Tri-Info as a simple yet powerful method that not only detects failures with strong cross-domain generalization, but also delivers interpretable diagnostics of the underlying failure modes.

Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS) a challenging problem for conventional search- and rule-based methods, which typically suffer from high computational complexity and long decision latency. While reinforcement learning (RL) has emerged as a powerful alternative, deploying learned policies with extreme energy efficiency on resource-constrained hardware remains an open challenge. We present SDQN-RMFS, an end-to-end framework that achieves high-fidelity deployment of an RL-trained policy from a full-precision artificial neural network (ANN) through to a neuromorphic chip. By computing only when triggered by sparse events, this framework unlocks ultra-low-power RMFS pathfinding. Our full-stack pipeline operates as follows: an ANN policy is first efficiently trained via a collision-allowing strategy to densify informative trajectories, and then converted into a spiking neural network (SNN) via a hard-label knowledge distillation approach. This effectively addresses the output distribution mismatch, preserving policy capability across the ANN-to-SNN pipeline while substantially reducing inference latency. Hardware experiments demonstrate up to 11,281$\times$ energy savings and a nearly two-fold reduction in latency compared to a high-performance GPU baseline, while maintaining decision quality on par with the original trained policy. These results establish physical neuromorphic inference as a practical and energy-sustainable pathway for large-scale RMFS operations.

UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce UAV-VLN-FOV, a target-visible navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a vision-language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and geometric details for target grounding. It also updates the target-relative direction online during closed-loop navigation, allowing the agent to maintain spatial alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive UAV-VLN baselines, achieving a 13.82\% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach navigation. The source code and benchmark are available at https://github.com/xuefanfu/3DG-VLN.

Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy. However, existing methods rely on discretized action chunks, making them brittle to demonstrations collected at heterogeneous control frequencies and prone to temporally inconsistent actions that degrade control stability. In this paper, we propose Frequency-Aware Flow Matching (FAFM), which outputs continuous, temporally consistent actions. To handle heterogeneous frequency input, we transform discrete action sequences into the frequency domain with the discrete cosine transform (DCT), perform flow matching over the resulting coefficients, and reconstruct continuous actions via cosine basis expansion. To generate temporally consistent actions, we regularize the first-order temporal derivative to promote smooth actions. This corresponds to a Sobolev-type constraint that suppresses high-frequency errors and discourages abrupt action changes. Our FAFM is simple, introduces no additional network parameters and applies to standalone flow-matching policies and vision-language action models. Across synthetic toy benchmark, obstacle avoidance, LapGym, and LIBERO, FAFM improves success rates, multimodal expressivity, motion smoothness, convergence speed, robustness to mechanical bias and mixed-frequency input. These gains are consistent when deployed on a real-world Franka robot. Code available at https://anonymous.4open.science/r/FAFM.

Joint spatial and temporal understanding of 3D scenes is a crucial requirement for robots deployed in everyday household environments. Such agents must not only comprehend and navigate spatial layouts, but also reason about how these spaces evolve over time. In particular, humans interact with objects daily, causing them to change position throughout the environment and making it difficult for robots to reliably associate current observations with previously seen objects. However, these interactions are not random: human habits and routines induce spatio-temporally consistent patterns in object locations, which robotic agents can potentially learn and then exploit for downstream tasks such as navigation. To this end, we introduce FlowMaps, a latent flow matching model for estimating multimodal distributions over the future locations of dynamic objects in a continuous 3D space. By learning the implicit dependencies among objects and their temporal evolution, FlowMaps predicts likely changes in object locations conditioned on past human interactions, while supporting generalization across previously unseen environments that share similar object routines. To demonstrate the utility of this method, we deploy FlowMaps in a downstream dynamic Object Navigation task in both simulated and real-world environments. Across more than 600 episodes, FlowMaps outperforms state-of-the-art approaches, showing that modeling object dynamics through continuous, multimodal spatio-temporal distributions improves robotic search and navigation in changing household environments. Code and additional material is available at https://fra-tsuna.github.io/flowmaps/.

Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard auditing methods rely on a single output inspection or static automated metrics. These approaches obscure the underlying probability distributions and fail to capture biases hidden in lower-probability generation branches. This paper introduces TreeTracer, a visual analytics tool designed to evaluate LLM bias through aggregated comparison. Using a systematic perturbation analysis pipeline, the tool replaces ontology-defined terms in each input prompt, aggregates hundreds of stochastic generations into a syntax-aligned hierarchical structure, and then performs classification-aware node merging with an auxiliary language model. The resulting structure is visualized through a custom Sankey diagram. By juxtaposing two ontology-driven trees, the workspace enables direct comparison between semantic contexts and supports systematic bias detection. Because any visualization reflects only a subset of the model's learned behavior, the system further applies contrastive inference to compute and directly display counterfactual token probabilities across contexts, reducing the risk of misinterpreting the presence of bias. We validate the workspace through case studies comparing an unaligned baseline model GPT-2 XL against the constitutionally aligned Apertus models. The visual aggregation successfully exposes hidden representational harms, such as counterfactual pronoun suppression and conversational marginalization of individuals. A preliminary user study confirms that the aggregated comparative interface reduces cognitive load and effectively supports analysts in detecting systemic biases.

Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench debugging agents (Modgil 2026). A post-release audit found the engine received dt=0 between actions, so its exponential decay never operated: the published trap is a pure-accumulator result. We correct the record (erratum, v2) and treat the flaw as an experiment. The key variable it exposes is whether a monitor's dynamics are calibrated in sample time (per observation, as in CUSUM) or wall-clock time (half-lives in seconds, as in affect models and EMA baselines). On fixed-rate streams these coincide; on agent streams, where inter-action time varies by orders of magnitude, they do not. A pre-registered sweep over uniform intervals (dt in {0..600}s) on 20 trajectories shows the wall-clock level trigger has two regimes: at dt<=1s a constant alarm (20/20; median 18 firings); at dt>=60s silent. Every critical dt lies in (1,30]s. Real agent runs measure latency at median 1.53s (p90 2.33s); real coding cadence sits inside the trap regime, vindicating the empirical finding under a corrected mechanism. The structure is a property of the calibration class, not the engine: a minimal wall-clock accumulator over the raw error stream reproduces the same cliff, while a sample-time CUSUM over the identical stream is exactly dt-invariant (20/20). A rising-edge trigger with hysteresis fires 0-3 times per trajectory in every condition. We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams; transition detection escapes the trap at every cadence, but does not recover human intervention timing.

A protocol driven framework is presented that binds SBOM and AIBOM artefacts to deterministic environment capture and structured runtime telemetry. Exploitability is computed from declared artefacts, observed activation conditions, and enforced execution policies. CSAF VEX advisories are generated from combined static and runtime evidence, cryptographically signed, and validated through deterministic replay. Evaluation uses approximately 10000 component entries across synthetic Agentic AI workloads 50 to 5000 components, incorporating OSV, GitHub Advisory, KEV, and EPSS datasets.

The transition to Post Quantum Cryptography (PQC) introduces considerable implementation complexity, requiring strict adherence to constant-time execution, side channel resistance, and precise parametrisation. Simultaneously, large language models (LLMs) are heavily embedded in software development workflows, including cryptographic engineering. While LLMs improve productivity, evidence shows that they frequently generate insecure or suboptimal code, particularly in security critical domains. This paper introduces Secure Coding Drift in PQC, a novel socio technical vulnerability model capturing the gradual degradation of secure coding practices due to sustained reliance on LLM-generated code. Unlike prior work that focuses on static vulnerabilities, we conceptualise security risk as a longitudinal behavioural phenomenon rising from human AI interaction. To mitigate this, we propose a gamified, LLM augmented secure coding framework that embeds adversarial evaluation, behavioural feedback, and security scoring into development workflows. Our approach reframes LLMs from passive assistants into active security co-pilots, contributing toward safer PQC implementation in AI mediated environments.

Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safety methods and speculative decoding. We propose SafeSpec, a safety-aware speculative inference framework that integrates risk estimation directly into the verification process. SafeSpec attaches a lightweight latent safety head to the target model to jointly evaluate semantic validity and safety in a single forward pass. When unsafe generations are detected, SafeSpec applies rollback and safety-guided reflective multi-sampling to recover safe continuations rather than terminating generation. We model jailbreak attacks as distributional shifts over generative trajectories, where adversarial prompts increase the probability of harmful continuations without eliminating safe ones. Under this model, SafeSpec performs risk-aware trajectory recovery within the speculative decoding process. Across multiple models and adversarial benchmarks, SafeSpec achieves a substantially improved safety-efficiency trade-off. On Qwen3-32B, SafeSpec reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, demonstrating that speculative acceleration and inference-time safety can be jointly optimized.

Vector databases are increasingly used in security sensitive contexts with Retrieval Augmented Generation and organizational AI pipelines; however, their security capabilities remain limited. Specifically, Fine-grained Access Control (FGAC) which is required to ensure that data access adheres to user-specific policies is not fully supported in modern vector databases. Unlike relational databases, vector databases combine structured and unstructured attributes to provide semantic, approximate query results, which complicates FGAC implementation. This creates an inherent tension between enforcing FGAC policies correctly, achieving high ANN search recall and maintaining low query latency. In this paper, we present a vision for Policy-aware Vector Search by formalizing the FGAC policy model in vector databases as well as the enforcement problem. We compare various enforcement strategies, present preliminary findings, and identify key open challenges for future research in policy-aware vector search.

Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamental challenges: (1) reward models cannot signal when their predictions are unreliable, since they usually act as deterministic point estimators; and (2) modern group-based policy optimization can amplify unreliable reward signals, as exemplified by GRPO's uniform treatment of rewards during advantage computation. As policies explore increasingly diverse responses, these two limitations create a critical vulnerability: unreliable reward estimates may be granted disproportionate influence, triggering severe reward hacking. We propose Uncertainty-Aware Reward Modeling (UARM), which equips reward models with calibrated uncertainty via quantile-based conformal prediction and reweights GRPO advantages through heteroscedastic variance decomposition. Experiments across HelpSteer, UltraFeedback, and PKU-SafeRLHF demonstrate that UARM significantly improves reward model calibration, reduces reward hacking, and enhances downstream alignment quality compared to standard GRPO and uncertainty-agnostic baselines.

This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations -- drawing from our own evaluations -- that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces the Expected Calibration Error (ECE) by an average of 40\% across three Medical VQA datasets, significantly enhancing MLLMs' reliability. The findings highlight the importance of domain-specific calibration for MLLMs in healthcare, offering a more trustworthy solution for AI-assisted diagnosis.

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures. Across eight domains and five recurring risk patterns, we find that over-privileged tool selection is common among mainstream LLM agents and is further amplified by transient failures. We further find that general safety alignment does not reliably transfer to least-privilege tool choice, while prompt-level controls provide only limited mitigation under transient failures. We therefore introduce a privilege-aware post-training defense that teaches agents to prefer sufficient lower-privilege tools and escalate only when necessary. Our mitigation experiments show that this defense substantially reduces unnecessary high-privilege tool use while preserving general capabilities.

The emergence of LLM-driven information services is reshaping the conditions under which public knowledge institutions operate, threatening to absorb the editorial function these institutions exist to exercise. While LLMs offer powerful new affordances for knowledge dissemination, editorial authority is challenged by pretrained LLMs that arrive already aligned with the values and dissemination strategies of their commercial developers. This paper investigates editor participation in re-aligning LLM interfaces to editorial standards through design workshops, in a case study where we design and implement an LLM-enabled encyclopedia interface with a Nordic public knowledge institution. We introduce editorial alignment as a design practice within Participatory AI, framing AI alignment as a design process and positioning the editorial standard as a design artefact that translates editorial practice and values into alignment objectives for technical implementation. Last, we discuss how editorial alignment can create space for ongoing participation and give editors agency in LLM-mediated knowledge dissemination.

Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents. These capabilities make prompt-injection and jailbreak attacks more consequential, especially as attackers adopt model-guided automation to scale probing, prompt refinement, and response evaluation. This work analyzes the resulting attack-defense setting through a probabilistic model of a target system, its defense mechanism, and the attacker's automated judge. Our analysis shows that conventional detect-and-block defenses can allow attacker success rate (ASR) to approach one as the query budget grows, since predictable refusals provide useful feedback to automated search. We then examine detect-and-misdirect, where detected malicious interactions receive controlled, non-operational responses designed to induce false-positive errors in the attacker's judge. This strategy reduces the positive predictive value of attacker-selected candidates and yields a bounded asymptotic ASR. We evaluate a proof-of-concept realization of this strategy through Contextual Misdirection via Progressive Engagement (CMPE), a lightweight conversational misdirection method designed to replace predictable refusal text with safe but strategically misleading responses in automated jailbreak settings. On jailbreak benchmarks, CMPE reduces estimated ASR upper bounds by up to two orders of magnitude and nearly eliminates verified attack success in end-to-end PAIR and GPTFuzz attack runs.

Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring approaches that formulate and enforce policies expressed in a formal language like Datalog offer a promising solution. However, existing approaches are restricted to deterministic policies. In many practical applications of AI agents, there is a need to enforce security policies in the face of ambiguity, leading to probabilistic predicates or state transitions (for example, a declassifier or Personally Identifiable Information (PII) detector that has some failure probability on each invocation). Furthermore, in many such applications, one cannot easily make the independence assumptions necessary to invoke prior work on probabilistic inference in Datalog. We address this by introducing a sound and efficient framework for such verification based on distributionally robust optimization, computing sound upper bounds on the probability of policy violation regardless of possible correlations between predicates. On standard benchmarks for terminal and tool calling agents, we demonstrate that our approach outperforms prior art and improves the security-utility trade-off while ensuring rigorous bounds on the probability of policy violation.

Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutation authority should not reside inside non-deterministic reasoning processes. Existing access-control mechanisms authorize identities, while assurance layers certify proposed actions; neither alone provides a mandatory enforcement point for certified authority at the moment of mutation. This paper introduces the Sovereign Execution Broker (SEB), a runtime enforcement boundary for certificate-bound agentic infrastructure. SEB consumes certificates issued by the Sovereign Assurance Boundary (SAB), verifies that the requested mutation matches the certified execution contract, checks validity windows, policy epochs, revocation epochs, and live-state drift, mints scoped execution identity, invokes infrastructure APIs, and records signed decision and outcome records. By separating proposal, admission, and execution, SEB turns certified authority into a short-lived, revocable, auditable runtime capability, provided that production mutation APIs reject non-broker identities. We present the SEB execution model, certificate and replay-verification predicates, scoped identity semantics, bypass-prevention deployment patterns, failure behavior, and a concrete prototype implementation. We evaluate the prototype on AWS and Kubernetes clusters, measuring latency overheads, revocation propagation, drift detection, and security under fault injection.

Sign languages are expressive visual languages used by Deaf and Hard-of-Hearing (DHH) communities. Despite substantial progress in sign-language recognition, translation, and production, advances remain constrained by fragmented datasets, inconsistent annotations, and limited linguistic coverage. Existing benchmarks often fail to reflect real-world communication needs, and systematic analyses of these limitations remain limited. In this survey, we present a comprehensive index of sign-language datasets, covering 120 resources across 35 sign languages. We analyze key challenges such as modality imbalance, annotation granularity, and signer bias, and outline considerations for future dataset design. We also introduce a 24-field Sign-Language Datasheet and release a public GitHub repository (https://github.com/Ginqwerty/Open-Sign-Language) to support standardized documentation and reproducible evaluation. Overall, our work provides a unified and practical foundation for developing inclusive, robust, and scalable sign-language technologies in real-world applications.

Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interruption: does the agent resume the workflow at the correct step? Does it address the user's interjection? Does it avoid re-delivering content the user already heard? We introduce IHBench (Interruption Handling Benchmark), a benchmark that evaluates post-interruption recovery in voice agents executing state-machine-driven workflows across 10 enterprise domains. Six interruption types are injected at controlled points mid-utterance, with per-interruption evaluation rubrics generated alongside the data. Each interruption is scored on two axes: task fulfillment and recovery quality. We evaluate 27 audio-language model configurations from OpenAI, Google, and the open-weight community. Models vary widely, and recovery quality depends strongly on the interruption type. Across our experiments, closed-weight models are consistently more robust to interruptions than open-weight ones: they win far more often on task fulfillment, degrade roughly 3.3x more slowly as conversations grow longer, and show no audio-versus-text modality gap, whereas the open-weight models lose ground on all three. A human study validates the LLM judge against human annotators, and a cross-benchmark analysis against AudioMultiChallenge indicates that recovery quality is a largely distinct capability axis.

Mean opinion scores (MOS) are widely used for speech quality assessment, yet scalar labels are sensitive to rater variability and listening test differences. This introduces labeling noise, which limits the reliability of MOS prediction. Preference prediction reduces this variability as listeners compare signals directly, producing cleaner labels. We study MOS-free preference prediction and propose PrefSQA, which incorporates uncertainty-aware logits, an impairment attention head, and a module based on non-matching-reference comparisons. We use and refine five datasets, including MOS-derived and low-noise simulated sets with matching and non-matching content, experiment with human preference sets, and test on unseen data. Experiments show small improvements on MOS-derived data, while other sets reveal clear improvement over the baselines, highlighting the value of high-quality preference data and demonstrating the effectiveness of the proposed method.

We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with verifiable rewards, math data curation, synthetic curricula, and verifier training. We show this proxy has a persistent blind spot on its hardest stratum: on the eight free-form math cells we test (GSM8K and MATH across four open-weight models), 10.3-22.9% of the examples that no sampling seed solves in six tries are instead solved at matched compute by a six-chain deterministic regime. These are greedy decoding plus five cheap residual-stream perturbations applied via activation grafting, while greedy alone solves at most 6% on these math cells. Recovery scales with the additional budget, across perturbations whose mechanistic distinctness we verify across all twelve cells (cross-kind fix-set Jaccard <= 0.47 in every setup). Activation grafting is used as an intervention on internal representations, not a decoding method; we use it purely as a diagnostic and diversification tool, and our recovered items show that the pass@k= 0 % stratum is structurally identifiable in the residual stream rather than that the unmodified model reaches them under ordinary inference.

Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media. We argue that this framing obscures how EHR-based suicidality datasets encode a particular operationalization of suicidality, shaped by who authors the data, how episodes are bounded, and how ambiguity is resolved. We ground this argument in a case study of the ScAN dataset, built over MIMIC-III clinical notes. We show how governance constraints, ICD-based cohort selection, single-annotator labeling, and hospital-stay-level aggregation produce labels that reflect clinician-documented judgments, treat suicidality as a bounded episode, and assume that intent can be reliably inferred from documentation. A linguistic analysis demonstrates that identical labels subsume heterogeneous clinical framings differing in temporality, negation, and uncertainty. We argue that clinical NLP should examine the assumptions embedded in suicidality datasets before interpreting their labels as ground truth.

AI and large language models (LLMs) have emerged as promising tools to address global mental health challenges. Despite the global nature of these challenges, there remains a critical shortage of high-quality datasets for training and evaluating such systems. To mitigate this gap, researchers increasingly generate synthetic clinical personas to simulate user data and test digital mental health support systems. However, most validated personas rely on English-centric contexts. This paper investigates whether similar persona-based methods can be used to generate multilingual mental health datasets. We modified nationality and language parameters in personas to generate clinical dialogues in Mandarin, Bengali, and Hindi. We then examined how different LLMs perform when evaluating the depression severity of these generated multilingual datasets against the baseline in English. Our findings indicate that just adding nationality and language parameters in personas might not be adequate, as it can introduce clinical inconsistency across languages. LLM judge models often exhibit inaccuracies in assessing depression severity in non-English texts, with performance varying across different models. This exposes the systemic limitations of applying English-centric personas to multilingual contexts. Ultimately, our work highlights the urgent need for culturally responsive data generation to ensure equitable mental health systems globally.

Large language models (LLMs) are increasingly used as judges for open-ended generation, as large-scale human evaluation is often expensive and difficult to scale, yet their preferences remain imperfect proxies for human judgment. Existing auditing pipelines often assume that a reliable subset of examples or clean supervision signals are available beforehand, for example from human annotation, heuristic filtering, or the outputs of strong judges. In LLM evaluation, this assumption is fragile: the initial split may inherit judge bias, while human verification is typically too scarce to define stable groups at scale. We propose AURA, an adaptive uncertainty--aware refinement framework for auditing pairwise LLM--as--a--judge decisions under selected human verification. AURA iteratively learns a human-consistency signal, propagates reliable evidence, and prioritizes uncertain comparisons for human review. The key idea is to treat trust in a judge as a latent quantity that is progressively refined as evidence accumulates. We provide a compact formulation, a stable refinement procedure, and a comprehensive evaluation on both synthetic and real pairwise LLM-answer data.

Language models have become essential tools in shaping modern workflows. However, their global effectiveness hinges on a nuanced understanding of local socio-cultural contexts. To address this gap, we present NRITYAM, a comprehensive benchmark for evaluating the cultural comprehension capabilities of language models in the context of global dance traditions. NRITYAM comprises 9,260 carefully curated question-answer pairs spanning 12 languages, making it the largest dataset dedicated to evaluating cultural knowledge in dance. The dataset has been developed from the ground up through close collaboration with native dance artists and native speakers of the languages, who authored and validated culturally relevant questions specific to their regions. We evaluate a broad set of models, including large language models, small language models, multimodal large language models, and small multimodal language models. As a multilingual and multicultural benchmark, NRITYAM sets a new standard for evaluating the ability of AI systems to understand and reason about traditional performing arts. Detailed dataset samples are available at~\url{https://github.com/niladrighosh03/NRITYAM}.

The scalability of humanoid robots will depend not only on models and hardware, but also on whether physical experience can accumulate across robots, tasks, organizations, and time. Drawing on the authors' work in developing ISO/WD 26264-1, Humanoid robot datasets -- Part 1: General requirements, within ISO/TC 299/WG 16, this article argues that data standards are becoming foundational infrastructure for Physical AI. We develop three insights. First, humanoid robot data is embodied interaction data, not a collection of isolated digital samples; a useful dataset must preserve the relationship among robot body, action, task, scene, execution trace, and outcome. Second, its value depends on physical coherence: multimodal streams are reusable only when timing, coordinate frames, calibration, kinematics, units, and synchronization assumptions remain inspectable. Third, the main bottleneck is not only data scarcity, but non-cumulative data caused by high collection costs, data silos, and inconsistent evaluation. We argue that humanoid robot data standards address these bottlenecks by making embodied experience interpretable, shareable, traceable, and reusable. A general standard should provide horizontal infrastructure for lifecycle management, metadata, provenance, quality, versioning, and traceability, while capability-specific parts should define domain grammar for manipulation, locomotion, human-robot interaction, cognition, and future humanoid capabilities. As AI moves from screens into bodies, data standards must evolve from organizing digital information to structuring physical interaction.

Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking. Prior work has relied on token-overlap (Jaccard) metrics that systematically underestimate decomposition quality for paraphrastic claims, and has lacked formal termination analysis for the repair loop. We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings. Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence theorems: we formally characterise four properties of the repair pipeline, establishing that rule-based repair is monotone and finitely terminating under an oracle parser assumption; LLM-based self-repair is provably non-monotone and requires an early-exit guard; (3) Three evaluation benchmarks spanning social-media, encyclopaedic, and news domains for cross-domain generalisation measurement; (4) Multi-model benchmarking across four decomposer models (3.8B-12B) and a closed API model. Experiments on SocialClaimSplit, WikiSplitBench, and ClaimDecompBench show that Semantic-F1 outperforms Jaccard-F1 by +15-32pp. EPR ranges from 0.94 to 1.00 on SocialClaimSplit and WikiSplitBench, while ClaimDecompBench includes lower base EPR cases (down to 0.824) due to harder news-domain constructions, and rule-repair reduces the Atomicity Violation Rate (AVR) by 47-100% relative to the base model without degrading fidelity.

Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the dataset, generation pipeline, prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/datasets/datumo/FinRED.

Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts. How reliably can a model turn the same visual evidence into the action required by the current context? To answer this question, we introduce \textsc{ROSE} (\textbf{R}eference-conditioned \textbf{O}ddity and \textbf{S}ymbolic \textbf{E}xecution), a controlled benchmark that holds the visual scene fixed while varying region constraints and required symbolic outputs. Through coupled counting and coordinate-action tasks, \textsc{ROSE} tests whether models can infer an implicit majority reference and act on the resulting fine-grained visual evidence under changing contexts. Across nine recent MLLMs, performance drops by as much as 44.5 percentage points from counting-oriented tasks to region-conditioned action, despite 98.8\% human performance. The gap persists on paired scenes and regions for which the same model returns the correct count, while global-click and matched local controls show that coordinate grounding explains only part of the loss, revealing a distinct, model-dependent bottleneck in turning shared visual evidence into context-specific actions.

Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks. We present IHUBERT, a monolingual Persian PLM trained from scratch with the RoBERTa-base encoder (125M parameters) on a 45 GB curated subset of the Sepahr-Danesh collection (about 7-8B tokens). To improve corpus quality and reduce redundancy, we employ a multi-stage preprocessing pipeline that includes normalization, exact and near-duplicate removal, anonymization, and vector-database-based semantic deduplication for distribution balancing control across domains and registers. We additionally train a 139k-vocabulary BPE tokenizer on the full pretraining corpus to better capture Persian morphology and orthographic variation. IHUBERT is evaluated on seven Persian NLU benchmarks covering NER, sentiment analysis, topic classification, NLI, extractive question answering, and relation extraction, using task-standard metrics (entity-level F1, Macro-F1, EM/F1). IHUBERT achieves its strongest gains on extractive QA, ranking first on both PQuAD (F1 88.3542) and ParsiNLU-RC (F1 49.0987), and attains the best result on FarsTail (Macro-F1 0.8350). On NER and topic classification, it remains competitive (e.g., 0.8308 F1 on ParsTwiNER; 0.7953 Macro-F1 on DigiMag), while relation extraction remains the main remaining gap (0.6684 Macro-F1 on PERLEX). A controlled tokenizer ablation on the IHUBERT pretraining corpus shows that BPE yields slightly lower subword fragmentation than WordPiece at matched vocabulary size, supporting our tokenization design. Overall, IHUBERT advances Persian language modeling through semantically curated large-scale pretraining and broad evaluation across both classification and comprehension-oriented tasks.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to comprehend negation remains underexplored, limiting deployment in real-world applications where models must explicitly identify what is false or absent, e.g., emergency responders need to locate non-flooded routes for evacuation. To comprehensively study this limitation, we introduce RS-Neg, the first benchmark to evaluate negation understanding across region-level to scene-level tasks. Specifically, we design an automated data generation pipeline for RS imagery, using LLMs to synthesize diverse negation queries, and introduce a dynamic visual focus module for verification. Our evaluation reveals that advanced RS MLLMs struggle with negation, exhibiting hallucinations and substantial performance degradation. To close this gap, we propose NeFo, a novel test-time learning method that explicitly incorporates the logical role of negation into the model optimization. Remarkably, using about 5\% unlabeled test samples, NeFo significantly improves the negation understanding of models and shows strong generalization to unseen tasks. Code and data will be released upon acceptance.

Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration. However, existing benchmarks are insufficient for systematically evaluating agentic academic search under realistic open literature environments. We propose ScholarQuest, a large-scale, taxonomy-guided benchmark for agentic academic paper search. ScholarQuest is constructed from over 1,000 computer science topics and four representative research intents, including method-oriented, setting-anchored, comparison-based, and scope-controlled queries. It further provides scalable answer construction and a shared retrieval backend ScholarBase for reproducible evaluation. Benchmarking results show that agentic methods outperform single-shot retrieval baselines, yet the best-performing agent only achieves 0.314 Recall@100 and 0.355 Recall@All, indicating substantial room for improvement. In addition, analyses of search efficiency, intent-level robustness, and failure cases further highlight the benchmark's ability to provide multi-dimensional evaluation signals for academic paper search agents.

Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR). However, previous works have ignored the grain blindness when adapting the contrastive paradigm into retrieval tasks. Grain blindness refers to the tendency of the model to overlook grain-level information contained in the query, which is crucial for effectively handling complex queries. This stems from contrastive learning treating samples as a binary classification (positive/negative), while ignoring the different information carried by each negative sample. To address this, we argue that negatives should be treated differently according to their similarity to the positive sample, enabling the model to learn distinct grain information from each negative. In this paper, we introduce a simple but effective framework, called ELVA, a novel rule-based RL framework that mitigates grain blindness through ranking-driven MLLMs. 1) Instead of relying on reward models, we extend Reinforcement Learning with Verifiable Rewards (RLVR) to retrieval tasks, allowing the model to explore new ranking behaviors without explicit ranking labels. 2) By utilizing rule-based rewards, our approach jointly optimizes the ranking of negative samples while enlarging the similarity gap between positive and negative. To more precisely measure grain blindness, we further introduce MRBench, a new benchmark specifically designed for multi-grain query scenarios. ELVA achieves state-of-the-art results across standard retrieval benchmarks, and its notable 13.1% improvement on MRBench further demonstrates its effectiveness in alleviating grain blindness.

Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing safety benchmarks with high-fidelity 3D physics remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine with realistic 3D dynamics, CRAX leverages vectorized operations and hardware acceleration, yielding up to ~100x speedups over comparable CPU-based safety benchmarks. The benchmark features six environment suites and three agent-specific tasks, each spanning three difficulty levels. Evaluating six popular safe RL methods shows that no single approach dominates across all tasks, and reveals the trade-offs between performance and safety. We find that curriculum learning across difficulty levels and safety transfer can improve performance over direct training in harder settings.

Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety-critical system, instantiated in a simulated nuclear power plant control room. A five-role operator team, each backed by a configurable LLM, runs a plant governed by six critical safety functions (CSFs), while adversaries inject messages over four channels in bounded multi-turn sessions with per-turn feedback. Harm is an objective signal rather than LLM-judged text: a run terminates the moment any CSF is lost, attributed to the causing message. Evaluating four frontier operator models under a fixed-attack paired-replay protocol, we find that adaptive multi-turn attacks reliably push the operator team past a safety limit: across the four models, between 8.7% and 12.1% of attack sessions end with the plant losing a critical safety function. Although the four models look almost equally robust by this aggregate rate, their failures barely overlap: of $149$ sessions, none defeat all four models while a third defeat at least one, so vulnerabilities are nearly disjoint across models rather than nested. The effect of added defences is strongly model-dependent: the same guardrail stack or safety-advisor agent that lowers attack success for one model can raise it for another. We release the simulation venue, attack dataset, and replay tooling for reproducible safety evaluation of LLM agents.

Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enforces a strict temporal split (pre-2025 historical set / post-cutoff leakage-free set), preserves context-aware vulnerable--patched pairs, and introduces two diagnostic metrics: the Directional Failure Index (DFI) and Hierarchical Distance and Direction (HDD). We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification. Our analysis yields two key results. First, data contamination provides no measurable advantage. Function-level analysis shows that 84% of nominally contaminated samples carry no usable memorization signal: vulnerable functions are absent or cross-mapped across datasets, and ~31% of contaminated samples carry CWE misclassification. Second, backbone directional priors dominate fine-tuning. Models exhibit stable, systematic failure modes (DFI ranging from -85.5 to +94.8 pp) that persist from historical to post-cutoff data and resist correction. Fine-tuning shifts the output threshold without changing the decision policy. This is calibration without comprehension: output distributions adapt to training data while the underlying security reasoning remains absent. The weakest backbone at binary detection (DeepSeek-R1) gains the most in coarse CWE classification, revealing that detection and understanding are decoupled capabilities. The best detection score reaches only 52.1% (+2.1 pp above chance); exact CWE ranking remains below 1.3% Top-1 accuracy, confirming that current LLMs lack reliable security reasoning for systems software, regardless of fine-tuning strategy.

Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR--optical datasets largely rely on low-resolution, intensity-only Ground Range Detected~(GRD) products and do not preserve complex-valued SAR measurements or native acquisition geometry, which restricts physically grounded multimodal learning. In particular, large-scale public datasets combining very-high-resolution (VHR) SAR SLC, aligned optical imagery, and natural-language descriptions are still lacking. We present a VHR SAR--optical--text dataset built from open-access Umbra spotlight acquisitions distributed as Sensor Independent Complex Data (SICD). From around 2,500 worldwide scenes (VV/HH, 20cm--2m native resolution), we standardize all SAR data to an 80cm slant-range grid via band-limited FFT resampling and tile the imagery into 1024 by 1024 patches. For each SAR patch, we retrieve a high-resolution optical tile and warp it into the SAR grid using local coordinate correspondences for local pixel-level alignment. We further generate three caption variants (SHORT/MID/LONG) per sample to support vision--language training and evaluation. Our dataset contains 119,566 triplets (complex and amplitude slant-range SAR patch, aligned optical patch, natural-language description) covering 257 locations across 72 countries and a broad range of land types and infrastructures. We release fixed train/validation/test splits and the full preprocessing and baseline code to enable reproducible benchmarks for multimodal alignment on cross-modal retrieval and conditional generation in native SAR geometry. The dataset is publicly available on the Hugging Face Hub at https://huggingface.co/datasets/ONERA/SARLO-80.

The rapid increase in scientific publications leads to the fact that manual study screening in systematic literature reviews (SLRs) is increasingly resource consuming, inefficient, and inconsistent. Classifying studies that clearly report health-related quality-of-life results, such as EQ-5D data, requires a high level of clinical interpretation and poses challenges for human reviewers. This study investigates the use of Google's Gemini and Gemma large language models (LLMs) in automating EQ-5D detection in the PubMed biomedical database based only on published abstracts. A multi-phase framework is proposed that integrates few-shot prompting, weight ensembling aggregation, and a soft stacking meta-classifier. Nine LLMs are evaluated on a dataset of PubMed studies manually labeled by two experts regarding EQ-5D reporting. The weighted ensemble of gemini-2.5-pro, gemma-3-12b, and gemma-3-27b obtained a 0.74 weighted F1-score and 0.74 accuracy, exceeding individually attained results. The ensembling of top-performing models improved the balance between precision and recall compared to individual models, while the soft stacking approach provided greater reliability and interpretability. Feature analysis shows that the probability results from the models are important in guiding the final predictions. The findings suggest that an ensemble-based LLM setup is a reliable and scalable approach for automating screening in biomedical research.

Alzheimer's disease (AD) is a fatal disorder that destroys memory and cognitive skills in the elderly population. Most treatments for AD are effective in the early stage, leading to an increasing demand for early AD diagnosis. AD diagnosis increasingly relies on multimodal data such as clinical assessments, structural Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) imaging. However, MRI and PET acquisition remain costly and not universally accessible, making full-modality inference impractical in real-world clinical workflows. We propose ProMUSE, a Progressive Multi-modal Uncertainty Guided Staged Evidential Network that adaptively determines when additional modalities are necessary, helping reduce the overall cost of data acquisition while maintaining accuracy. ProMUSE first performs evidential classification using low-cost clinical data and quantifies uncertainty via a Dirichlet-based subjective logic model. When uncertainty exceeds a learned threshold, ProMUSE progressively incorporates MRI or PET features, fusing modality-wise belief and uncertainty through Dempster-Shafer theory to obtain a calibrated multimodal prediction. This staged acquisition strategy enables accurate diagnosis while minimizing reliance on expensive imaging. Experiments on ADNI, AIBL, and OASIS across CN-AD, CN-MCI, and MCI-AD tasks demonstrate that ProMUSE achieves competitive or superior accuracy compared to full-modality baselines while reducing MRI/PET usage by 50-90%, yielding substantial cost savings. These results highlight ProMUSE as a practical, uncertainty-aware, and resource-efficient solution for real-world AD screening.

Ventricular tachycardia is a life-threatening rhythm disorder and a major cause of sudden cardiac death. Pace-mapping is a clinical procedure for identifying the intervention target during catheter ablation of VT. It requires clinicians to pace different sites in the ventricles and rapidly interpret the resulting electrocardiograms to determine where to pace next or whether a target site has been identified. Active learning AI models have been proposed to guide clinicians to the next pacing site, showing promise in reducing the number of pacing sites and improving the efficiency of pace-mapping. Existing methods require retraining each target without the ability to transfer knowledge across multiple VTs within the same patient or across patients. We introduce cAPM for continuous AI-assisted pace-mapping to capture and transfer knowledge accumulated from past pace-mapping data to reduce the number of pace-mapping data needed for future target VTs. This is made possible by a task-agnostic surrogate neural network that learns the mapping from pacing sites to 12-lead ECG morphology, an active-learning strategy that refines this surrogate model by selecting the most informative pacing site for each target, and a continual learning strategy to do so sequentially while retaining knowledge from prior targets. Evaluated on an in-silico testbed consisting of sequentially-presented localization tasks across different physiological conditions and ventricular geometries, cAPM with and without replay of past data samples achieved an 81% probability of localizing within clinical tolerance (5 mm accuracy) using 4.5 pace-mapping sites, compared to the state-of-the-art active-learning method achieving 38% probability using 13.7 pacing sites. These results provide a strong basis for preparing cAPM towards in-vivo preclinical and clinical studies where it can be used to guide pace-mapping.

Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the underlying generative model. Current all-atom generators inherit expensive architectures from structure prediction, leading to high training costs and limited sample diversity. We argue that much of this complexity is unnecessary for generators, which condition on sparse geometric constraints rather than rich co-evolutionary signals. Emyx is a 140M-parameter conditional flow matching model that concentrates capacity within standard transformer blocks, replacing heavy embedding stacks with lightweight conditional representations and sparse connectivity. We additionally derive an exact reparametrisation of the flow matching interpolant into the EDM noise-level framework, bridging flow matching training efficiency with state-of-the-art sampling methods designed for diffusion models without retraining. Despite being the smallest model, Emyx outperforms both Proteína-Complexa and RFdiffusion3 against the AME enzyme design benchmark across success rate under strict evaluation requiring both global fold recovery and catalytic geometry accuracy, structural novelty, scaffold diversity, and geometric validity, while training in just $682$ GPU-hours, roughly $4\times$ less than RFdiffusion3.

While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment-ready engine using a Plan-then-Execute architecture to generate verifiable workflow graphs. DynAMO supports both SequentialWorkflow (topological execution) and ParallelWorkflow (dependency-aware concurrency). By dynamically identifying independent tasks, DynAMO preserves structural correctness and safety while significantly improving efficiency through controlled reasoning overlap. Across six controlled experiments on the AssetOpsBench industrial benchmark, DynAMO demonstrates substantial performance and robustness gains. Parallel execution reduces end-to-end latency by a median of 1.6x over sequential orchestration, rising to 1.8x on highly parallelizable workflows. After instrumenting external tool calls with realistic latencies, a latency decomposition shows that LLM reasoning and orchestration still account for more than 90% of execution time, identifying model inference as the primary system bottleneck. Structured context pruning reduces inference latency by approximately 30%, and DynAMO maintains correct functional behaviour (task completion, agent sequencing, and output quality) while exhibiting graceful degradation under controlled fault injection. Reproducibility analysis further confirms stable execution under repeated runs, with parallel scheduling reducing latency variance. These findings establish DynAMO as a practical blueprint for scalable, safe, and latency-aware agent deployment in Industry 4.0 automation pipelines. Code is available at: https://github.com/kushwaha001/DynAMO

Large language models (LLMs) have achieved remarkable success in software development. However, they are susceptible to hallucinations, meaning that they can introduce subtle semantic and logical errors. Due to the high stakes in chip design and manufacturing, hardware engineers are still reluctant to rely on LLMs for register-transfer level (RTL) generation. In this paper, we propose a hardware generation framework that combines the creativity and broad knowledge of LLMs with the explainability and mathematical rigor of formal methods. Specifically, we devise a set of transformation rules that cover various design decisions and hardware features. By iteratively applying these rules, an LLM agent can convert a design specification into an RTL program with guaranteed correctness. Experimental results demonstrate the effectiveness and efficiency of the framework.

Large language models can produce fluent root cause analyses, but fluent final answers alone are insufficient evidence for accountability in high-stakes operations. In real incident response, engineers need to know what evidence supported a diagnosis, which alternatives were considered, where contradictions remained, and whether the system resolved the case or preserved uncertainty. We address this gap with JustDiag, a diagnostic justification engine for RCA that maintains an explicit process state over evidence, findings, competing hypotheses, conflicts, and next checks. We evaluated the system on 66 real-world incidents using a two-layer protocol that separately scores final-answer quality and process quality. Relative to a matched control without diagnostic justification, JustDiag achieved stronger outcome and process scores, while accepting slightly lower terminal completion due to more calibrated non-closure. These results suggest that accountable RCA requires explicit diagnostic justification artifacts and process-aware evaluation, not only fluent final answers.

We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer from poor generalisation across patient subpopulations, institutions, and acquisition settings, resulting in limited real-world clinical utility. Controlled, high-fidelity synthesis of chest radiographs is a promising path toward diversifying clinical datasets and evaluating the robustness of diagnostic models. Therefore, we present the largest specialist generative foundation model for chest radiographs to date, with over 1.3B parameters, trained for 1.6T tokens on a curated, heterogeneous dataset comprising 1.2M radiographs and clinical expert-guided metadata. Our model supports controllable radiograph generation and editing across multiple demographic subgroups, acquisition views, and a dozen pathologies. Moreover, we significantly advance the state of the art in radiograph synthesis fidelity, producing images that are indistinguishable from real radiographs to clinical experts.

Solar energetic particle (SEP) events have attracted increasing attention due to their significant radiation hazards for aviation, spacecraft electronics, and human missions beyond Earth's magnetosphere. From a scientific perspective, SEP events are intriguing because they arise from a set of physical processes extending from the solar surface and corona through the heliosphere, offering insight into particle acceleration and transport mechanisms that are widely applicable across astrophysics. Therefore, advancing our ability to understand and predict SEP events is essential both for deepening our knowledge of such mechanisms and for safeguarding space technologies and exploration. Traditionally, researchers have modeled SEPs using physics-based simulations and empirical methods. More recently, machine learning (ML) has emerged as a new tool for understanding and predicting SEP events. The purpose of this manuscript is to review the currently available ML models for SEP prediction, identify the datasets used for training, compare their architectures, inputs, and outputs, and, based on these insights, outline good practices and recommendations for future research.

Electric vehicle charging stations (EVCSs) can expose distribution feeders to cyberattacks. While machine learning methods, including graph neural networks, can localize which bus is compromised, significant challenges remain in data sharing and model training. For example, privacy regulations grant EVCS owners the right to delete their training data from a deployed model, yet retraining from scratch on every request is computationally prohibitive. To address this, we study graph unlearning (GU) for EVCS cyberattack localization, formulated as a feature-level unlearning problem on a graph-level multi-label classification task. Specifically, we propose gradient difference-based graph unlearning (GDGU), which removes the influence of the requested deletion data through a first-order parameter correction. The correction is computed from the gradient difference between the original training data and a modified dataset in which only the charging power features at the requested EVCS buses are unlearned. Then, a batch-normalization recalibration and a brief recovery fine-tuning step are applied to restore localization utility. We benchmark GDGU against two second-order GU baselines on the IEEE 34-bus, 123-bus, and 8500-node distribution networks across three graph neural network backbones and cumulative unlearning scenarios. GDGU matches the strongest baseline on localization utility and reaches forgetting fidelity close to full-retraining, while unlearning 10 to 12 times faster than retraining from scratch and using far less memory than the second-order GU baselines.

Acoustic gunshot detection is a problem with applications across civilian public safety, military operations, and wildlife conservation, yet the field lacks a rigorous exploration of feature extraction techniques with a focus on generalization to realistic data. The mixed effectiveness of commercial gunshot detection and classification systems indicates an open problem that is not adequately addressed by the current literature. In this paper, we present a systematic investigation of common feature extraction techniques using a dataset of 23,000 gunshot recordings across 85 firearms and 21 calibers. We benchmark three feature extraction techniques with 12 total unique parameter sets using ResNet-18. Our results demonstrate that using the correct feature extraction technique can improve top-1 accuracy by up to 20%, and utilizing the correct parameters for a given feature extraction technique can improve that value by up to 4.7%.

Audio deepfakes generated by neural text-to-speech and voice-cloning systems threaten speaker verification and public discourse at scale. The core challenge is cross-dataset generalization: detectors trained on one synthesis pipeline collapse on unseen forgeries. We argue that this failure is primarily because of structural synthetic speech artifacts which are multi-timescale trajectory anomalies. Though every existing detector aggregates a fixed-window frame statistics, this misaligns the architecture with the signal. We propose FlowFake, a Liquid Time-Constant (LTC) architecture whose hidden state evolves via a learned ODE, with per-neuron adaptive time constants simultaneously resolving spectral (10ms) and prosodic (2s) cues. At only 34K parameters FlowFake achieves formal BIBO stability and O(dt^4) integration error. On a four-dataset cross domain benchmark (ASVspoof2019-LA, FakeOrReal, InTheWild, MLAAD), FlowFake reaches 75.29% on ASVspoof2019 trained only on FakeOrReal and 79.97% trained only on MLAAD. It outperforms RawGAT-ST and Whisper-DF on every evaluated pair and matching SSL Wav2vec2 (300x larger) at 0.01% of its parameter count. The source code is available on : https://github.com/GhostRider2023/FlowFake

Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We present FAPO (Fully Autonomous Prompt Optimization), a framework that lets Claude Code optimize an LLM pipeline inside a standardized codebase. FAPO evaluates a pipeline, inspects intermediate steps, diagnoses failures, proposes scoped changes, and validates variants repeatedly to optimize against a score function. It first tries prompt edits and, only when prompt optimization appears insufficient, changes chain structure within the permitted scope when attribution identifies a structural bottleneck. Across six benchmarks and three task models, FAPO beats the baseline GEPA in 15 of 18 model-benchmark comparisons. In 11 model-benchmark comparisons, FAPO wins with non-overlapping mean $\pm$ trial-standard-deviation ranges, and the mean FAPO-GEPA gain is +14.1 pp. In the six HoVer and IFBench comparisons where prompt-first search escalated to structural changes, FAPO wins all six with a mean gain of +33.8 pp. FAPO also improves performance on security tasks: on CTIBench-RCM, a security CVE-to-CWE task, prompt-only FAPO lifts test accuracy by +4.0 pp on GPT-5, +7.1 pp on Foundation-Sec-8B-Instruct, and +2.0 pp on Foundation-Sec-8B-Reasoning. These results position FAPO as a state-of-the-art pipeline optimization technique for both general-purpose and security-focused tasks.

The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds. This transition introduces an ``extreme cold-start'' problem: unlike traditional items, new short-form videos lack the dense interaction history required for collaborative filtering. Furthermore, immersive feeds introduce strong position and duration biases that distort standard engagement signals. In this paper, we demonstrate the Video Candidate Generation (VCG) system, a scalable multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment. By leveraging a domain-adapted vision-language model (based on CLIP), we map users and videos into a shared semantic space, enabling zero-shot retrieval based on visual content rather than behavioral history. We detail the system's architecture and present a rigorous evaluation comparing generative (LLM) vs. discriminative (CLIP) embeddings. Our results show that while generative models excel at attribute prediction, they suffer from embedding space collapse in retrieval tasks. Online A/B testing demonstrates that VCG effectively mitigates engagement biases, yielding a 50\% uplift in deep video completion. To showcase the system's capabilities, we present an interactive demonstration featuring three bi-directional retrieval scenarios: Product-to-Video, Video-to-Product, and Zero-Shot Semantic Search.

Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that "textualize" these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose "Token Factory", a framework designed to transform traditional signals into "soft tokens" that can be directly processed by LRMs. This approach enables efficient integration and compression of heterogeneous input features, preventing prompt length explosion while enhancing model performance. We detail the architecture of Token Factory and present experimental results validating its effectiveness in a production-scale recommendation environment.

Court proceedings contain valuable evidence about human smuggling networks, but this information is often buried within unstructured, jargon-heavy legal documents. While large language models (LLMs) can support knowledge graph construction through automated information extraction, existing approaches rely on general-purpose models that are not tailored to the entity and relationship definitions required in this domain. We introduce FineREX, a streamlined knowledge graph construction pipeline built around a fine-tuned LLM for named entity recognition and relationship extraction (NER-RE). Using a manually annotated dataset of $512$ text chunks, FineREX achieves absolute improvements of 15.50% and 31.46% in entity and relationship F1-score, respectively, compared to a larger general-purpose baseline. These gains translate into higher-quality knowledge graphs, reducing legal noise by nearly half and lowering node duplication on long documents from 17.78% to 11.17%. By eliminating document rewriting and redundant extraction stages, FineREX also reduces end-to-end processing time by 50.0%. Our results demonstrate that domain-specific fine-tuning can substantially outperform larger general-purpose models while improving both the quality and efficiency of knowledge graph construction for illicit network analysis.

Validating changes in low-level C firmware is expensive because unit tests (UTs) are fragile under strict build constraints, where missing headers, unresolved symbols, and dependency mismatches frequently prevent compilation and linking. This study introduces an automated UT authoring workflow for the Open-Source Silicon Initialization Library (openSIL) firmware codebase maintained by Advanced Micro Devices (AMD) that reduces manual effort through a large language model (LLM) guided multi-agent pipeline. The workflow combines automated generation of test scaffolds, library-aware creation or reuse of stubs, mocks, and fakes, and an iterative compile-dispatch repair loop driven by build logs and line-coverage feedback. We evaluate the approach using compilation success, repair iterations, dispatch success, and line coverage, with time, cost, and token usage as secondary measures. Across 76 functions under test, the workflow generated compilable UTs for 73 functions. In a configuration without line coverage guidance or retrieval augmentation, mean line coverage reached 73.9%. On a 48-function subset evaluated under both configurations, mean line coverage reached 98.8% with line-coverage guidance alone and reached 94.7% when combined with vector-database retrieval. Results show that automated generation-and-repair pipelines can substantially improve UT creation efficiency and coverage for constrained firmware environments while reducing manual debugging effort.

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65\% relative improvement in isolated word recognition and a 4.63\% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65\% relative improvement in isolated word recognition and a 4.63\% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

Electronic design automation (EDA) is inherently multi-stage and handoff-heavy. Design artifacts, flow scripts, and engineering decisions cross tool, session, and organizational boundaries before final implementation, signoff, or release. Each transfer carries explicit and implicit requirements that may not be fully captured by stage-local checks. LLM-based agents now invoke EDA tools directly, embed retrieved knowledge in executable scripts, and hand off state across sessions and stages. Once their outputs condition downstream engineering decisions, the transferred object must satisfy a handoff contract and meet the assumptions of its next consumer. This survey introduces handoff validity as its organizing principle. A handoff is valid when the transferred object satisfies the consumer's acceptance conditions and carries sufficient context, evidence, and provenance for downstream use. We review 82 systems and classify them into three boundary classes. Stage-Bound systems establish validity within a single EDA stage or bounded verification task. Flow-Bound systems preserve coherent workflow state across tools, invocations, and sessions. Organization-Bound systems maintain source grounding, provenance, scope, and admissibility across knowledge and authority boundaries. For each class, we analyze handoff contracts, handoff objects, coordination mechanisms, and open questions. These analyses motivate a five-layer EDA agent communication protocol (EACP), covering the agent discovery, agent message, tool invocation, workflow orchestration, and security and IP protocols. We aim to provide a common vocabulary and research agenda for trustworthy agentic EDA.

Dysarthric speech recognition is crucial for facilitating effective communication among individuals with dysarthria. However, accurately recognizing dysarthric speech poses significant challenges due to varying severity levels and limited data availability. In this paper, we explore data augmentation techniques for dysarthric automatic speech recognition (ASR) systems by fine-tuning the End-to-End pre-trained Wav2Vec2 model, with a specific focus on severity levels. To address the challenges of data scarcity and the need for extensive data in fine-tuning pre-trained ASR systems for dysarthric speech, we investigate four prominent data augmentation methods: Speaking-Rate Modification (SRM), Pitch Modification (PM), Formant Modification (FM), and vocal tract Length Perturbation (VTLP), tailored to different aspects of dysarthria. The study uses individually fine-tuned Wav2Vec2 models for each severity class as baseline systems. Additionally, we conducted severity-specific fine-tuning of the ASR model using augmented data. Results demonstrate distinct efficacy patterns for each augmentation technique across severity levels. The best WERs were achieved with SRM ($s$=0.8) for \textit{low} (9.02\%) and \textit{medium} (38.11\%) severities, and with PM ($τ$=0.8) for \textit{high} severity (55.15\%), reflecting relative improvements of 30.02\%, 16.64\%, and 15.47\%, respectively. These results confirm the effectiveness of the augmentation methods in improving dysarthric ASR performance.

Accurate segmentation of thin, tortuous anatomical structures, such as retinal vessels, cerebral vasculature, and facial wrinkles, remains challenging due to low contrast, frequent discontinuities, and severe class imbalance. Although recent convolutional and Transformer-based models have improved performance, they often yield fragmented predictions and fail to recover fine branches. We propose CSWinUNETR, a general-purpose backbone for 2D and 3D thin-structure segmentation. It employs cross-shaped stripe self-attention to model long-range principal-axis context and incorporates cyclic shifts to enhance information exchange across stripes. To better preserve fine-grained details, we further introduce a detail-enhanced multi-scale self-attention module that aggregates contextual features from multi-resolution representations. In addition, we propose sparse-control dynamic snake convolution, which reconstructs reliable dense curvilinear kernels from sparsely predicted control points to better follow tortuous geometry. Extensive experiments on four benchmarks across ophthalmology, neurovascular imaging, and dermatology demonstrate that CSWinUNETR consistently outperforms state-of-the-art methods without task-specific post-processing or topology-aware losses. The code is available at https://github.com/labhai/CSWinUNETR.

Computed Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused datasets.

Current machine learning models commonly require large and well-annotated datasets. However, the annotation process often becomes a bottleneck, with increased complexity leading to higher chances of human errors. Within this context, our goal in this paper is to leverage unsupervised algorithms to improve data annotation efficiency for complex semantic segmentation problems in industrial materials science. Previous research has quantified labeling time and others explored unsupervised methods. However, to the best of our knowledge, this is the first study to quantify how much unsupervised algorithms accelerate the labeling process. We aim to validate the extent to which this laborious process can be accelerated, focusing on semantic segmentation tasks that involve annotating each pixel of high-resolution images, such as the microstructure characterization challenge in materials science. Specifically, we demonstrate that by using unsupervised computer vision algorithms, the time required for the labeling process can be reduced from 170 hours to 37 hours, achieving an approximate reduction of 78\%. The dataset we work with includes large images of dimensions 1280x959 and 960x703, which further increases the complexity of the annotation task. Despite these challenges, we create and share the largest public steel microstructure segmentation dataset to date, available under MIT License with permanent DOI, contributing a fully annotated, high-resolution dataset to the field. Additionally, this is the first work to compare the labeling time from scratch (a common approach in previous studies) to the labeling time when using these unsupervised algorithms as a pre-annotation step. Furthermore, we provide a Deep Learning model trained on this dataset, validated by field experts, and deployed in an industrial setting, serving as an initial benchmark for this public dataset.

Hyperspectral infrared observations are an important data source for numerical weather prediction (NWP) because they provide rich information on the vertical structure of atmospheric temperature and humidity. However, most existing deep learning methods mainly focus on one-way retrieval from radiances to atmospheric profiles, while the reverse radiance simulation process and the consistency between atmospheric state space and radiance observation space are insufficiently considered. In this study, we propose SIMBA, a unified bidirectional retrieval-forward simulation framework for FY-4A GIIRS hyperspectral infrared radiance modeling toward NWP applications. The framework jointly performs atmospheric profile retrieval and radiance reconstruction, introduces a cycle-consistency constraint to strengthen the coupling between the two processes, and employs a bidirectional Mamba state-space module to capture long-range dependencies along pressure levels. Using collocated FY-4A GIIRS observations and ERA5 reanalysis data, the proposed method is evaluated for temperature retrieval, specific humidity retrieval, long-wave radiance reconstruction, and medium-wave radiance reconstruction. Experimental results show that SIMBA outperforms several representative deep learning baselines across both retrieval and reconstruction tasks, while ablation experiments confirm the contribution of the bidirectional design and cycle-consistency mechanism. These results demonstrate that the proposed framework is effective for joint atmospheric profile retrieval and hyperspectral infrared radiance modeling, and suggest potential for future Jacobian-related analysis and NWP-oriented extensions.

This paper examines the impact of artificial intelligence and digital technologies on the blue-collar gig economy in India, focusing on algorithmic management. This paper examines the impact of artificial intelligence and digital technologies on the blue collar gig economy in India, focusing on algorithmic management he use of automated systems to allocate, monitor, and evaluate work in location-based services such as ride sharing and delivery. Using a social justice framework and a mixed-methods approach comprising interviews with 16 gig workers and 21 key stakeholders, the study uncovers a dual reality: while AI-powered systems expand access to work and generate operational efficiencies, they simultaneously introduce significant challenges related to fairness, transparency, and worker dignity. Key findings reveal that algorithmic systems are opaque by design, produce inequitable outcomes, and are not structured to reward additional labour with proportionate pay. The study advocates for a pragmatic hybrid governance model an Algorithmic Human Manager framework in which technological efficiency and human accountability operate together rather than in opposition. The findings carry implications for policymakers, platform companies, and civil society organizations working to design equitable AI governance frameworks for the gig economy in India and across the Global South.

We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability.

Burst suppression (BS) is a clinically relevant electroencephalographic (EEG) pattern used to monitor sedation depth and brain activity in critically ill patients, particularly during induced coma in Intensive Care Units (ICUs). Automatic burst detection remains challenging because BS patterns vary substantially between patients and annotated datasets are scarce. Recently, EEG Foundation Models (FMs) have shown promise across several downstream EEG applications, but their usefulness for BS detection remains unexplored. We present the first study to evaluate EEG FMs for burst detection in reduced-montage ICU EEG without patient-specific calibration. We compare REVE-base, LUNA-large and LuMamba-Tiny with an adaptive thresholding baseline and a task-specific EEGNet baseline. Additionally, we complement conventional EEG window-based classification with event-based burst detection evaluation. This helps assessing clinically whether burst episodes are correctly detected, reducing the impact of expected annotation variability. The best model, REVE-base, achieved the highest event-based F1-score ($0.868 \pm 0.167$) and reduced burst-per-minute error by 52.1% and 36.2% compared to EEGNet and adaptive thresholding respectively, supporting FMs for scalable EEG monitoring in ICU. Ablation experiments showed that full fine-tuning was the most effective adaptation strategy with respect to frozen-backbone training, two-step fine-tuning, and LoRA-based adaptation, improving event-based F1-score over frozen-backbone training by up to $+0.102$ for LUNA-large. With reduced labeled datasets, pretrained REVE-base outperformed random initialization by $+0.723$ event-based F1 points at 25% of the cohort, demonstrating the benefit of pretraining FM representations when adapted to burst detection with limited labeled data.

Makeup transfer models enable fun augmented reality (AR) experiences as well as virtual try-on (VTO) for online makeup shopping. While recent state-of-the-art diffusion based solutions such as Stable-Makeup dramatically improve the accuracy and realism of makeup transfer, they still face limitations in identity and skin color preservation, making production-level VTO for makeup shopping unrealistic. In this work, we propose MakeupMirror, a diffusion-based approach to makeup transfer that makes significant progress towards preserving facial features and skin tone. We introduce several technical innovations over Stable-Makeup: (1) integration of facial geometry conditioning with ControlNets to maintain facial fidelity; (2) region-specific makeup transfer control to enable precise makeup application across facial regions such as skin, eyes and lips; (3) skin tone-based makeup transfer modulation that prevent skin tone alteration in cross-subject transfer scenarios; and (4) integration of a Levenberg-Marquardt Langevin sampler to speed up inference while maintaining generation quality. Our experiments on CPM-Real, Makeup Wild, and (herein newly collected, more diverse) MakeupSelfies datasets show that MakeupMirror improves relative facial recognition similarity by +60%, reduces relative skin tone difference by -50% over Stable-Makeup, with a latency of 0.7s, while achieving expert acceptance rate of 94% across core facial identity preservation criteria.

Real-world clinical decision support requires reasoning over heterogeneous and longitudinal patient information rather than answering isolated medical questions. However, current medical large language models and retrieval-augmented generation systems often rely on single-step prompting or retrieval, which can be fragile when clinical evidence is distributed across long electronic health records, medical images, sensor streams, guidelines, and referral constraints. This paper proposes MedRLM, a Recursive Multimodal Health Intelligence framework for long-context clinical reasoning, sensor-guided screening, and community-to-tertiary referral support. Instead of compressing all patient information into one prompt, MedRLM treats the patient case as an external clinical environment that can be recursively inspected, decomposed, retrieved, verified, and synthesized. The framework coordinates specialized agents for clinical text, longitudinal EHR, medical imaging, physiological sensor signals, guideline retrieval, uncertainty auditing, and referral planning. It further introduces a Clinical Evidence Graph Memory to connect patient-specific observations with retrieved evidence, standardized definitions, sensor-derived biomarkers, and referral criteria. A sensor-guided recursive triggering mechanism activates deeper reasoning when abnormal physiological or behavioral patterns are detected, while uncertainty-gated refinement supports clinician review for high-risk or low-confidence cases. We also outline a real-data evaluation design using public and credentialed clinical datasets spanning EHR, radiology, ECG, ICU time series, and referral-proxy outcomes. MedRLM aims to move medical AI from static question answering toward auditable, multimodal, and workflow-aware clinical decision support.

Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improving data consumption efficiency in the data management lifecycle. However, producing high-quality data videos requires expertise spanning data analysis, narrative design, and video production. Existing approaches fall short: static visualization tools (e.g., BI dashboards) lack narrative logic and animation; authoring tools require users to pre-prepare visualizations rather than working from raw data; pixel-level video generation models cannot guarantee data fidelity or provenance. We demonstrate DataMagic, an end-to-end interactive system that transforms raw tabular data and natural language queries into narrative data-insight videos. To ensure data fidelity, DataMagic introduces the declarative specification DVSpec, which binds visual and animation elements to underlying data fields through data-driven semantic references. To address the combinatorial explosion of the design space, DataMagic adopts a Generate-then-Orchestrate multi-agent architecture that generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. Leveraging DVSpec's decoupling of logic and rendering, the system further supports three interaction modes and structured provenance-based data Q&A, transforming one-way videos into explorable interactive data interfaces. Evaluation on 109 real-world samples validates the effectiveness of the DataMagic. Homepage: https://datamagic-home.github.io/

Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist this process by classifying decompiled code as benign or malicious, but existing pipelines typically rely on a single decompiler view. We argue that this assumption is fragile: decompilers are lossy heuristic tools, and different decompilers can expose different artefacts of the same binary. We curate a benchmark of benign utilities and malicious programs spanning a range of threat behaviors. Each sample is compiled and decompiled with both Ghidra and RetDec, yielding matched pseudo-C views. Across a range of LLMs from major model families, we find that providing both decompiler views improves malicious-class F1, mainly by increasing recall on malicious samples. Agreement analyses further show that Ghidra and RetDec make partially different errors, supporting the view that decompiler outputs provide complementary evidence. Our results suggest that multi-decompiler prompting is a simple, training-free way to improve LLM-based malware triage in practical settings.

Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized. We study 4-bit KV-cache compression for this setting, using TurboQuant-style rotation and codebook quantization as a quality anchor and vLLM FP8 KV caching as the deployment anchor. We report three contributions. First, we frame 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly. Second, we describe the practical design choices needed to make the 4-bit path robust, including asymmetric K/V treatment, Walsh-Hadamard rotation, QJL removal, and block-scale variants. Third, we present serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant, an FP4 approximation path that uses FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on CDNA4. On a long-context, multi-turn agentic workload, UltraQuant cuts P50 time-to-first-token by 3.47x in the cache-pressured late rounds (2.3x across all rounds) and raises output throughput by 1.63x over the FP8 KV baseline.

As AI agents are increasingly integrated into core business processes, understanding and designing effective interaction patterns between humans and AI agents becomes crucial for value creation. This study identifies and evaluates principles and criteria for a positive User Experience (UX) with AI agents, along with methods for its measurement. We identify user expectations and needs to facilitate adoption, build trust, and support user-centered decision-making by development teams. Using a mixed-methods approach that combines qualitative and quantitative techniques, we explore interaction patterns between humans and AI agents. The findings from this exploratory research serve as the basis to develop a survey experiment which evaluates the effectiveness of specific design elements on a larger scale. This foundational research contributes to the development of more intuitive and effective human-AI agent interactions in business settings.

Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available. In causal identification, this information is often expressed in the form of a causal graph, and data are observed or collected for some subset of variables in the graph. Target queries may be for a single effect alone or for a class of effects in a given model. The derivation of an identification algorithm then defines mathematically the process by which the desired causal effect(s) can be uniquely determined, theoretically, in expectation. Identifiability in expectation, or 'theoretical identifiability,' generally assumes asymptotic properties, infinite data, or other mathematically idealized conditions. In this paper, we explore a fundamental distinction between this theoretical, idealized notion of identifiability and a proposed alternative that is computation-bound. The framework we propose - 'computational identifiability' - is to instead define a finite computational search procedure for an empirical estimator. If this process finds an estimator empirically, within a desired error tolerance, then identifiability is satisfied, conditional on the specified assumptions of the search (i.e., a prior distribution over the parameters) and conditional on the search procedure itself. Through several experiments, we demonstrate how this framework allows us to answer fine-grained, practical identification questions, such as identification with small finite samples, with ambiguous graphical criteria, with mixed observational-interventional data, and across counterfactual data and estimands. Code is available at https://github.com/lbynum/metadentify.