Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear truth probes, applying them to LLMs role-playing historical personas whose likely beliefs differ from modern consensus. For each persona, we compare false claims the persona would likely have endorsed (*era-believed*) with topic-matched false claims they would not have endorsed (*era-false*). Across prompting, in-context learning, and supervised fine-tuning, persona induction suppresses era-believed statements less than equally false alternatives, yet they remain classified as false overall. Role-play therefore shifts what these models say more than what they internally represent as true. We contrast this with models trained on harmful advice that exhibit Emergent Misalignment (EM). Across three model families (Qwen 2.5 14B, Qwen 3 8B, and Llama 3.3 70B), their false claims move substantially toward the true region of probe space, are defended under challenge roughly half the time versus about a sixth for role-play, and are used in downstream reasoning. Role-play and Emergent Misalignment thus are points on a spectrum of belief internalization, where role-play changes what a model says with little representational change, while Emergent Misalignment shifts the internal representation of false claims without fully marking them as true.

The performance of modern language models depends critically on pretraining data composition. Yet existing data selection methods rely on auxiliary classifiers for document scoring or mixture optimization, adding computational overhead and dependence on labeled data. We propose WebGraphMix, a lightweight data selection framework that computes structural centrality scores over the Common Crawl host-level web graph and uses them to vary the proportion of central versus peripheral documents in the pretraining mixture. We hypothesize that central hosts expose models to reusable abstractions, while peripheral hosts encode specialized, long-tail knowledge. WebGraphMix computes centrality scores efficiently at web scale, requiring no model training, labeled data, or downstream supervision. We integrate WebGraphMix into the DataComp-LM pipeline and train models at 400M and 1B parameter scales with 8B and 28B tokens respectively, evaluating on 23 tasks ranging from factual knowledge to symbolic reasoning. Our experiments show that central and peripheral web regions encode complementary capabilities. Mixture combining both at a ratio of 1:1 achieves 41.4% on average, compared to 39.8% for uniform sampling. Combining structural scores with document-level quality classifier scores further improves performance to 43.8%. These findings demonstrate that web graph topology is a meaningful axis for pretraining data curation, capturing information that is largely orthogonal to existing content-based approaches.

Real-world robots need to adapt their behavior beyond the envelope of their pre-trained policy. Policy finetuning or retraining are options, but they risk catastrophic forgetting, degrading the pretrained policy's base performance. To combat this, we introduce CLAE: Closed-Loop Affine Activation Editing, an inference-time framework for steering the behavior of a frozen policy by editing intermediate activations while keeping the base policy weights and downstream action head untouched. CLAE approaches behavior steering as a closed-loop problem whose outputs edit policy activations that adapt online to the robot state, environment, target behavior, and multi-robot context. It trains a sparse autoencoder over frozen-policy activations, selects behavior-relevant latent features via post-hoc probing, and learns a lightweight RL-based steering policy that applies state-dependent affine edits to selected latents during inference. We validate CLAE on a frozen multi-quadrotor navigation policy trained to perform a single task: navigating robots to a set of goal locations while avoiding obstacles. Through extensive simulations and physical tests, we show that while navigating to their goal positions, CLAE can 1. steer individual robot behavior by controlling each robot's velocity profile; 2. coordinate multirobot behavior by preserving a desired formation; and 3. produce entirely new behavior wherein robots are required to reduce their exposure to surveillance cameras in the environment.

Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability. Existing FCL methods often rely on repeated local optimization, replay, and full supervision. Analytic alternatives avoid iterative training and replay, but using high-dimensional random features to improve accuracy requires a second-order feature statistic, the Gram matrix, which has a quadratic communication cost in the random feature size $M$. We propose FedRAN, a resource-aware analytic FCL framework that replaces gradient-based updates with compact random feature statistics. Each client transmits a truncated-SVD summary of its Gram matrix, reducing the dominant second-order upload from quadratic to linear in $M$ for fixed rank. The server performs a two-level QR-SVD subspace merge, spatially across clients and temporally across tasks, and solves a ridge classifier in closed form. FedRAN further supports label scarcity through prototype-based pseudo-labeling. Across CIFAR-100, ImageNet-R, and VTAB datasets, FedRAN improves average accuracy by up to 4.8 percentage points over the strongest baseline, uses 30.6-121.8$\times$ less per-client communication than optimization-based FCL, and is 190.3$\times$ faster on average than gradient-based baselines; with only 20% labels, pseudo-labeling improves average accuracy by up to 6.61 points. These results show that FedRAN enables accurate and resource-efficient FCL under communication, computation, and label constraints. The source code is available at this https URL.

Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats. A practical middle ground keeps paper-based, problem-oriented tasks but records the assessment-relevant answers as single capital letters in a table that a machine can read. The open question is whether this reading can be made accurate and, above all, fair enough for unsupervised grading. Earlier automated approaches reached only about 88%--91% recognition -- too low -- and failed on the cases that matter most: answers placed outside the cell, crossed out, or written in cursive. We show that general-purpose vision-language foundation models (VLMs), which interpret the page rather than match pixel templates, close this gap. On a benchmark of 61 anonymised exams (3141 answer positions) the best model reaches 98.4% accuracy, well above the previous baseline. Crucially, we centre the evaluation on fairness: we distinguish false negatives (a correct answer marked wrong, which disadvantages the student) from false positives, and a lightweight prompt that supplies the reference solution as context lowers the false-negative rate to 0.58%. Under an exemplary grading scheme only three of the 61 exams would be graded worse, all caught by a student self-review step. Fully automated, fairness-aware exam grading at scale is therefore defensible; we release the anonymised benchmark to support reproducibility.

Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset for each cluster by greedily minimising the maximum mean discrepancy (MMD), and (iii) runs exact PFN inference on each reduced-context batch. CRUMB is architecture-agnostic and requires no retraining. On the 51-dataset TabArena benchmark, evaluated across three PFN architectures (TabPFNv2, TabICLv1, TabICLv2), we show that CRUMB outperforms similar state-of-the-art context selection strategies. We also show that CRUMB is resilient to covariate drift, as the MMD-minimisation step naturally helps align the training context distribution to match the current test batch distributions.

Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to examine how reasoning capabilities emerge in LLMs and where they fail. We make three main contributions. First, we introduce a structured taxonomy of LLM reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning. Second, we analyze methodological trends across these paradigms, including prompting methods, model architectures, training objectives, reward modeling, and evaluation benchmarks. Third, we synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross-domain generalization. By organizing a rapidly expanding literature, this survey offers a unified view of the current capabilities and limitations of reasoning in LLMs. We also identify emerging research directions, including meta-reasoning, self-evolving reasoning frameworks, multimodal reasoning, and socially grounded reasoning. Overall, this work aims to serve as a reference for developing more robust, interpretable, and generalizable reasoning systems in future language models.

Point cloud semantic segmentation requires architectures that capture both fine-grained local geometry and broad global scene structure. Transformer-based networks have demonstrated strong performance by focusing on detailed local feature aggregation; however, global context is conveyed primarily through skip connections across encoder-decoder stages, which we argue is insufficient for full scene understanding. We hypothesize that augmenting skip connections with a learnable global feature extraction module allows the network to acquire scene-level knowledge before descending into local detail, leading to richer and more contextually grounded representations. To this end, we propose Point Transformer with Wavelet Neural Operato (PT-WNO), which integrates a shared Wavelet Neural Operator (WNO) branch alongside the skip connections of a point cloud transformer backbone. At each encoder-decoder transition, point features are projected onto a dense 3D volumetric grid where the WNO captures multi-scale global spectral context through learnable wavelet decomposition and reconstruction. These global features are fused back into the network via lightweight adapters, complementing rather than replacing the existing skip connections. Experiments on four large-scale 3D point cloud benchmarks demonstrate the effectiveness of PT-WNO. On S3DIS (Area 5), PT-WNO achieves 71.59% mIoU, outperforming the Point Transformer v3 (PTv3) baseline by +1.03 points. On DALES it achieves 81.05% mIoU (+1.47 over the baseline). On ScanNet~v2, PT-WNO obtains 76.19% mIoU, remaining competitive with the baseline (76.36%).

Robotic table tennis is a representative benchmark for high-speed, closed-loop robotic control in dynamic environments, where accurate and fast prediction of ball states is critical for reliable planning and control. Physics-based approaches rely heavily on accurate parameter identification and precise initial state, while learning-based methods often struggle to capture long-range temporal dependencies and are typically trained on limited or simulated data. We propose a transformer-based framework for table tennis ball state prediction that leverages attention mechanisms to model long-range temporal correlations directly from historical observations, without relying on explicit flight or bounce models. To support robust learning and generalization, we collected a large-scale real-world dataset from players of varying skill levels and diverse ball cannon configurations. The combination of a high-capacity transformer architecture and extensive real-world data enables accurate long-horizon forecasting. Building on this capability, we introduce a plug-and-play sim-to-real transfer strategy, Swap Predictor at Deployment (SPAD), which replaces the physics-based simulator used during training with the proposed real-world-trained predictor at deployment, improving the sim-to-real transferability of the policy without requiring retraining. We demonstrate that this simple substitution effectively narrows the sim-to-real gap while preserving the efficiency and scalability of simulation-based training.

Accurate loss reserving is foundational to insurer solvency, yet accelerating climate driven catastrophes systematically violate the stability assumptions on which traditional actuarial methods depend. This white paper presents a research program testing whether Long Short Term Memory (LSTM) neural networks can detect and adapt to these structural breaks faster and more accurately than Chain Ladder, Bornhuetter Ferguson, and Cape Cod methods. Using 15 plus years of regulatory development triangle data from Florida and Louisiana, enriched with NOAA hurricane intensity indices and sea surface temperatures, we hypothesize a targeted improvement of 15, 20% in reserve accuracy for catastrophe exposed years, a threshold grounded both in the prior neural network reserving literature and in the formal convergence results developed here. Beyond empirical validation, we develop a theoretical framework grounding LSTM structural break detection in probabilistic terms, providing formal performance guarantees that compensate for the limited number of catastrophe events in the test period. We document the research design, methodology, expected contributions, and a candid assessment of limitations.

Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have emerged as the dominant paradigm, they suffer from a critical bottleneck: data efficiency. Current methods treat the development dataset as a static benchmark, wasting significant compute budget on uninformative data. In this work, we introduce APEX (Automatic Prompt Engineering eXpert), a novel framework that optimizes the data usage alongside the prompt search. APEX dynamically stratifies the dataset into Easy, Hard, and Mixed tiers based on the optimization lineage. By prioritizing the Mixed tier, which identifies the data where the LLM has mixed performance, we identify two high-leverage subsets: the addressable frontier for generating informative mutations and the rank-sensitive frontier for distinguishing candidate quality. We evaluate APEX across three diverse benchmarks: IFBench, SimpleQA Verified, and FACTS Grounding. Under a fixed budget of 5,000 evaluation calls, due to its data efficiency, APEX outperforms the initial prompt by an average of 11.2% on Gemini 2.5 Flash and 6.8% on Gemma 3 27B, demonstrating that a data-centric approach is key to efficient and effective prompt optimization.

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recognition. However, existing state-of-the-art methods must predict an exceedingly large number of spatiotemporal patches, significantly prolonging training time. Besides, by treating all spatiotemporal regions equally during reconstruction, these models are distracted from learning the critical motion patterns that underlie action semantics. To address these challenges, we propose Adaptive Masked Reconstruction (AMR), a faster and stronger pre-training framework. We first decouple the decoder from the encoder, enabling flexible prediction of larger spatiotemporal patches and dramatically reducing reconstruction complexity. Given that larger patches contain more complex information, which is challenging to predict and consequently degrades performance, we accordingly introduce an adaptive guidance module. This module identifies regions of high motion informativeness, guiding the model to focus on the most discriminative parts of each patch and alleviating reconstruction difficulty. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that AMR not only accelerates pre-training substantially but also improves downstream recognition accuracy, surpassing current state-of-the-art approaches.

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semantic gap' in deep geometric learning. As deep models become central to 3D content creation, explainability shifts from a peripheral feature to a fundamental requirement for trust and accountability in safety-critical domains such as healthcare and manufacturing. CBMs provide an intrinsic interpretability solution by constraining latent representations to align with human-defined concepts, yet their application to unstructured 3D data remains largely unexplored. We design, implement, and validate a formal 3D-CBM architecture that maps raw geometric inputs, including point clouds and meshes, into a multi-tiered taxonomy of interpretable primitives and functional attributes. The framework further identifies strategic datasets, such as PartNet and ShapeNet, specialized for concept-based supervision. Experimental results from a 3D part-manipulation proof-of-concept experiment demonstrate the framework's efficacy, achieving a concept prediction accuracy of 88.8\% and a Chamfer Distance of 0.0115. Critically, the model enables precise test-time intervention, allowing for the interactive correction of structural errors. This work establishes a foundation for semantically-steerable 3D generation and invites further exploration into collaborative human-in-the-loop design systems.

Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning models (LRMs), this conventional route is particularly difficult to follow: explanation methods for single token generations do not naturally generalize to long trajectories, and the trajectories themselves are often not faithful when read as natural language. We propose an alternative that bypasses the explanation step: treat behavior forecasting as a learnable task and train Behavior Forecasters that operates on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation. The forecaster's training data is obtained by querying the LRM with no human annotation, and its inference is done in a single forward pass. We instantiate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer. We evaluate this approach on both tasks across three diverse reasoning datasets and find that trained Behavior Forecasters are more accurate than GPT-5.4 and Claude Opus-4.6 reading the same trajectories as naive readers, at a small fraction of their inference cost. We find that fine-tuning the backbone end-to-end and initializing it from the target LRM are each necessary for strong performance. These results show that the reasoning trajectory carries information about the LRM's future behavior that goes beyond what naive reading conveys.

Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features. However, these methods do not consider the runtime state of the serving infrastructure. On shared GPU clusters under concurrent load, this infrastructure blindness causes systematic resource underutilization: preferred models accumulate deep request queues while equally capable alternatives sit idle. In multi-agent pipelines, where each query triggers multiple sequential model calls, these delays then compound across every downstream step. Closing this gap is challenging because the relevant infrastructure signals (queue depths, KV-cache pressure, latencies) are dynamic and noisy, and they must drive three different decisions: planning, per-step routing, and scheduling. We introduce INFRAMIND, a framework that makes the entire multi-agent stack infrastructure-aware. An infra-aware planner conditions topology and role selection on real-time system load and remaining budget, biasing toward simpler graphs under congestion and richer ones at low load. An infra-aware executor then observes per-model queue depths, cache utilization, and response latencies at each agent step to decide which model to call and how deeply to reason; a budget-aware scheduler further reorders each model's queue so that urgent requests are served first. Cast as a hierarchical constrained MDP and solved end-to-end via reinforcement learning, the system learns to balance quality against latency automatically. Across five benchmarks, INFRAMIND delivers up to +7.6 pp accuracy over the prior baseline at low load with up to 7x lower latency, and sustains up to 99.9% SLO compliance under high load where every baseline drops below 50%.

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is this https URL

Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initialization, often itself a pretrained or previously aligned model. Quadratic-regularized MD, including GD and Mahalanobis geometries, is well-known to be stable for convex smooth objectives. We show a sharp contrast: once the regularizer is non-quadratic, MD can be exponentially more sensitive to initialization than GD, even with a well-conditioned regularizer in Euclidean norm. We give a three-dimensional construction with a convex, smooth objective and a strongly convex, smooth, well-conditioned regularizer where an initial $\varepsilon$ perturbation is quickly amplified to $\min\{\text{polylog}^{-1}(1/\varepsilon), \varepsilon e^{\Omega(\eta T)}\}$ after $T$ iterations of MD with step size $\eta$. For canonical KL-regularized MD on the simplex, we show that even linear objectives can amplify an initial $\varepsilon$ perturbation exponentially fast in high-dimensional or near-boundary regimes. Finally, we show that adding a Bregman regularization term toward an anchor point can stabilize the dynamics while largely preserving the optimization guarantees, and that the choice of anchor is crucial: anchoring at the initialization only partially mitigates the instability, whereas anchoring at a fixed point yields a more stable mechanism.

Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schemas are large and ambiguous. Ambiguity across user questions, database schemas, and model interpretations are central failure modes in NL2SQL, leading to misaligned intent, incorrect schema grounding, and erroneous SQL generation. Existing approaches rely on human clarification or treat ambiguity as a schema representation problem, but these do not scale nor resolve ambiguity autonomously. We propose SOMA-SQL to automatically resolve ambiguity via targeted synthetic query log and ambiguity-driven probing. SOMA-SQL constructs synthetic query log to ground schema interpretation and guide candidate SQL generation; it then executes targeted probing queries, driven by a structured ambiguity taxonomy and candidate disagreements, to produce disambiguation evidence for final SQL selection and repair. This active approach to ambiguity discovery and resolution generalizes across unseen schemas and query distributions without human-in-the-loop. Experiments on six public benchmarks demonstrate that SOMA-SQL improves execution accuracy by 13.0% on average over state-of-the-art baselines, with gains of up to 16.7% on ambiguous questions.

Every day, millions absorb claims from podcasts and streams that no fact-checker ever sees. Spoken misinformation is built through conversation, where credibility comes not from facts alone but from how claims are framed, reinforced, or left unchallenged across turns. Yet fact-checking has focused on isolated text, leaving dialogue audio under-studied. We introduce MAD2, a new Multi-turn Audio Dialogues benchmark for spoken claim verification, containing 1,000 two-speaker dialogues with 3,368 check-worthy claims and approximately 10 hours of audio, and propose calibrated multimodal fusion of a context-aware audio encoder and a dialogue-aware text model. Across settings, adding dialogue context improves verification, but the gains depend on scenario type. Using only preceding context often matches offline performance, supporting live-moderation settings, and audio contributes most when transcript-based models are destabilized by additional context. Overall, conversational structure matters more for verification than misinformation framing.

Most existing drone-based inspection systems require the drone to fly dangerously close to the target or follow complex flight paths to capture small details. In addition, drone flight is affected by disturbances and localization inaccuracies, which can cause the drone to lose sight of its supposed target when it has a narrow view. Furthermore, trajectory planning often requires prior information about the target's geometry, position, and orientation, which is not always available for non-structural targets such as trees, vehicles, or people. To address these challenges, this paper presents aerial_micro_inspection, a generic pipeline for aerial micro-inspection across different use cases. The pipeline assumes a PX4-powered drone equipped with two cameras: (i) a zoomed, gimbal-mounted inspection camera that captures fine details without requiring the drone to fly very close to the target, and (ii) a wide-field-of-view stereo navigation camera that acquires the target surface on site, estimates its range, and partitions it into smaller inspection regions. In addition, a vision-based feedback loop compensates for drone motion while the inspection camera visits small partitions of a larger surface. We evaluate the pipeline in simulation and real-world experiments, mainly in two use-case scenarios: tree inspection for detecting oak processionary caterpillars and their eggs, and greenhouse inspection of sticky traps for detecting whiteflies. The results show improved coverage robustness under drone disturbances in simulation, as well as effective detection of caterpillars and eggs and high-detail imaging of insects in real-world experiments. The pipeline is open-source, developed in ROS 2, and can be adapted to new applications by replacing the surface-segmentation and micro-target detection checkpoints. The code is available at: this https URL

Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack strategies can vary by orders of magnitude. Consequently, ASR at a fixed budget can obscure the true effort required to jailbreak a model, thereby making it hard to determine whether an attack's cost justifies its payoff to the attacker. We propose a compute-aware evaluation framework based on computational pressure, measured in cumulative floating-point operations (FLOPs), as a proxy for adversarial effort. We introduce risk-compute curves, which map compute budgets to attack risk, and derive two metrics that summarize the average pressure required for a given attack to succeed. Across ten models spanning three families and four different stages in language model training and alignment, evaluated with three attack strategies (gradient-based, iterative refinement, and template-based) on two jailbreak robustness benchmarks, we find: (1) alignment training has non-monotonic effects on compute-space robustness; (2) scaling model size reduces gradient-based attack effectiveness but has limited impact on cheaper template-based attacks; (3) gradient-based attacks optimized on a surrogate model can transfer to a separate target model, providing a way to reduce attacker costs; (4) compute cost varies by up to ${\approx}5{\times}$ across harm categories within a single model; and (5) safety-aligned RL increases aggregate cost while leaving some categories disproportionately accessible. We release our framework to enable compute-aware risk assessment and evaluation.

Action chunking has become a standard design in modern robot policies, from diffusion/flow policies to vision-language-action models, where the policy predicts a sequence of actions and executes a fixed number of them instead of acting one step at a time. However, this paradigm relies on a key assumption: a fixed execution horizon. During chunk execution, the policy operates open-loop, which is particularly problematic for fine-grained manipulation tasks that require frequent replanning. In practice, the execution horizon is typically chosen through empirical tuning and is highly task-dependent. To this end, we propose Dynamic Execution Horizon Prediction (DEHP), an effective method that trains a lightweight execution-horizon prediction branch using online reinforcement learning while keeping the pretrained chunk policy completely frozen. This makes the method compatible with black-box chunk policies and isolates the effect of adapting the execution horizon from changes to the underlying action generator. Across our evaluations, DEHP improves the success rate of different high-precision and long-horizon manipulation tasks by a large margin. Our qualitative analysis further shows that DEHP predicts shorter execution horizons during fine-grained stages of the task and longer horizons during free-space motion. In this way, DEHP balances the efficiency of open-loop chunk execution with the reactivity of closed-loop single-step control. Project page: this https URL

Dexterous manipulation with multi-finger hands can be sensitive to physical parameters such as object shape, pose, and friction coefficients. While simulation enables large-scale data collection with known parameter values, simulation-trained policies must still handle uncertainty at deployment, where the true parameters and therefore the true dynamics are unknown. Standard domain randomization strategies may be insufficient for precise tasks like screwdriver turning, as manipulation strategies may need to change depending on specific parameter values. To address this, we propose Probabilistic Latent Unified world Modeling and parameter Estimation (PLUME), a world model that jointly learns to evolve a belief over parameter values as well as the system dynamics conditioned on those parameters. We learn a latent space to jointly represent multiple qualitatively different physical parameters along with rewards, themselves functions of partially-observable variables, to inform planning. Our novel learning framework leads to efficient alignment of the world model to true dynamics through online parameter inference as opposed to re-training or fine-tuning. We evaluate our method on simulated screwdriver turning, valve turning, bucket lifting, and disk flicking tasks, as well as a hardware screwdriver turning task, where we achieve successful zero-shot transfer of our simulation-trained policy and outperform state-of-the-art offline reinforcement learning and world-model-augmented behavior cloning baselines. Please see our website at this https URL for videos.

Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recursive structures. Conversely, Vector Symbolic Architectures maintain constant dimensionality but sacrifice capacity and fidelity due to noisy compression via superposition. In this work, we propose Orthogonal Subspace Carving (OSC), a memory architecture that binds fillers to roles by projecting onto the null space of the role basis before aggregating into a fixed order-p tensor. OSC uses projections to enforce geometric orthogonality between bound structures within a static memory trace. We show that this mechanism decouples the tensor order from the structural depth, enabling deep recursive binding within a constant memory footprint. By performing retrieval via recognition, this construction allows for component vectors that are orders of magnitude smaller than the memory tensor, giving superior memory efficiency in settings involving high superposition. We also show that TPR is a special case of binding in Clifford algebra, and give a Clifford formulation of OSC.

Gaussian splatting methods have become increasingly popular for neural reconstruction of the real world. However, they are often limited in scale and resolution due to compute and memory constraints. We present a multi-GPU Gaussian splatting approach that scales reconstruction to higher resolutions and larger scenes while abstracting away the code complexity typically associated with distributing a model. To accomplish this, we propose a PyTorch backend that distributes the Gaussian parameters and splatting operators across GPUs via CUDA unified memory and NVLink. Because distribution occurs at the operator level, the model code requires no explicit cross-device communication. More broadly, the backend exposes multiple GPUs as an aggregate PyTorch device and supports other PyTorch operators. We demonstrate city-scale reconstructions with street-level detail consisting of over 1 billion Gaussian splats, more than 25 times as many as the current state of the art.

Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets. We study an auditable staged-promotion protocol for a fixed micro-pretraining runner on two heterogeneous host blocks: Windows A100 and Linux L40S. Starting from twelve prior-screened configurations, we use staged budgets of 2 minutes, 5 minutes, 10 minutes, 60 minutes, and 12 hours, with frozen promotion rules before expensive continuations. The early screens are intentionally treated as unstable: the 5- and 10-minute rankings are host-sensitive, and the eventual 12-hour top-ranked condition is not the mean-best condition at the replicated 10-minute gate. Because seed ranges differ across stages, these changes are operational promotion evidence, not within-seed curves. A replicated 60-minute gate keeps the Staged Factorial Screening bridge reference in the promoted set, where it ranks first in all four 60-minute host-seed cells. In the final 12-hour confirmation package, the bridge condition ranks first in all four host-seed cells across two seeds; the greedy comparator does not meet the frozen 0.010 val_bpb near-equivalence rule; and the cheaper d8/ar48 (depth-8, aspect-48) sentinel does not meet the frozen 0.020 mean-gap rule. The executed 12-hour branch spends 144 GPU-hours, and the full staged protocol records 169.2 training GPU-hours including screening stages. Continuing all four 60-minute candidates would spend 192 GPU-hours, while continuing all nine replicated 10-minute candidates would spend 432 GPU-hours. The latter numbers are accounting counterfactuals for unrun continuations, not evidence that skipped candidates could not have overtaken the reference. The result is a bounded cost-allocation finding, not a claim of global optimality, capacity-normalized superiority, or superiority over adaptive hyperparameter optimization methods.

Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored. We analyze the predictive behavior encoded in FD-SLM hidden representations and find that they exhibit stream-specific predictive patterns: during listening, they preferentially predict the incoming user stream, whereas during speaking, they preferentially predict the model output stream. Building on this observation, we show that FD-SLMs dynamically modulate their internal predictive focus between two states: a generative state aligned with model output generation and a perceptive state aligned with incoming user input. However, this modulation can lag behind abrupt changes in conversational context. During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it to miss the beginning of the incoming input. We term this delayed internal transition state inertia. To quantify its downstream impact, we introduce the Zero-Buffer Benchmark (ZBB), a diagnostic benchmark for evaluating immediate interruption comprehension when user speech begins abruptly. We evaluate this setting using response correctness and initial-word occurrence rate (IWOR). Finally, we mitigate state inertia through activation steering with a perception vector, a training-free intervention with little additional computational overhead. Across multiple state-of-the-art FD-SLMs, activation steering substantially improves interruption handling; for example, on PersonaPlex, it improves correctness from 28% to 45% and IWOR from 40% to 72% without any fine-tuning.

Deception detection is a critical and highly challenging task within affective computing and behavioral analysis. Existing deep learning methods typically treat this task as a straightforward classification problem; however, this black-box approach lacks interpretability and fails to capture the complex logical deduction processes utilized by human experts when identifying lies. While Multimodal Large Language Models (MLLMs) have shown potential, applying them effectively requires a bridge between low-level audiovisual cues and high-level logical reasoning. In this paper, we propose DeceptionX, a novel MLLM framework that shifts the paradigm of deception detection from black-box classification to an interpretable Observe-Think-Summarize reasoning process. To address the scarcity of high-quality reasoning data, we first constructed DeceptChain, a high-quality dataset developed through a human-in-the-loop process. This dataset synthesizes fine-grained visual and auditory evidence (such as micro-expressions and vocal tremors) into structured chain-of-thought reasoning data. Furthermore, we propose a three-stage training pipeline and a Discrepancy-Aware Redundancy Elimination~(DARE) strategy for DeceptionX to further enhance the model's generalization capabilities. Extensive experiments demonstrate that DeceptionX not only outperforms existing MLLM baselines and state-of-the-art methods on standard real-world benchmarks but also provides transparent, expert-level reasoning paths, bridging the critical gap between accuracy and interpretability in multimodal deception detection.