Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search strategies, and struggle to effectively combine information from multiple sources. We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents to independently reason, perform targeted searches, and synthesize findings through a moderator mechanism. Each agent generates hypothetical passages to optimize retrieval for its analytic perspective, ensuring knowledge integration is both context-sensitive and computation-efficient. When evaluated on challenging benchmarks such as MATH500, AIME, and PhD-level science QA GPQA, SIGMA consistently outperforms both open- and closed-source systems, achieving an absolute performance improvement of 7.4%. Our results demonstrate that multi-agent, on-demand knowledge integration significantly enhances both reasoning accuracy and efficiency, offering a scalable approach for complex, knowledge-intensive problem-solving. We will release the code upon publication.

Existing agent memory remains predominantly reactive and retrieval-based, lacking the capacity to autonomously organize experience into persistent cognitive structure. Toward genuinely autonomous agents, we introduce CogniFold, a brain-inspired "always-on" agent memory designed for the next generation of proactive assistants. CogniFold continuously folds fragmented event streams into self-emerging cognitive structures, bootstrapping progressively higher-level cognition from incoming events and accumulated knowledge. We ground this by extending Complementary Learning Systems (CLS) theory from two layers (hippocampus, neocortex) to three, adding a prefrontal intent layer. Emulating the prefrontal cortex as the locus of intentional control and decision-making, CogniFold achieves this through graph-topology self-organization: cognitive structures proactively assemble under the stream, merge when semantically similar, decay when stale, relink through associative recall, and surface intents when concept-cluster density crosses a threshold. We evaluate structural formation using CogEval-Bench, demonstrating that CogniFold uniquely produces memory structures that match cognitive expectations and concept emergence. Furthermore, across eight downstream benchmarks -- two probing long-term conversational memory (LoCoMo, LongMemEval) and six spanning other cognitive domains -- we validate that CogniFold simultaneously performs robustly on conventional memory tasks. Our code is available at https://github.com/OpenNorve/CogniFold.

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budget feasibility, evidence utility, and delayed costs including miss, reacquisition, and stale penalties. We show this multi-step problem is NP-hard, making exact solution intractable. Moreover, deployment decisions must be made under partial observability. To address these challenges, we propose OSL-MR (Observability-Safe Learning for Memory Retention), a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision. OSL-MR combines an evidence learner trained from realized evidence with a Mixed-Score heuristic that serves as a deployable online-safe baseline and an inductive prior. The policy learns query-conditioned evidence from interaction data and remains deployable under the same constraints. Experiments on LoCoMo and LongMemEval show OSL-MR outperforms recency-based, Generative Agents-style, and other heuristic baselines, especially under tight budgets. The Mixed-Score prior improves precision and recall, and sensitivity analysis shows robustness across cost settings. On small solvable instances, single-step optimization is insufficient to anticipate future demand shifts, while OSL-MR stays significantly closer to the dynamic-programming optimum, confirming the necessity of the sequential formulation and reinforcing our learning-guided approximation. These results establish constrained stochastic optimization and optimization-guided learning as a principled foundation for memory management in long-horizon agents.

In this paper, we explore mission assignment and task offloading in an Open Radio Access Network (Open RAN)-based intelligent transportation system (ITS), where autonomous vehicles leverage mobile edge computing for efficient processing. Existing studies often overlook the intricate interdependencies between missions and the costs associated with offloading tasks to edge servers, leading to suboptimal decision-making. To bridge this gap, we introduce Oranits, a novel system model that explicitly accounts for mission dependencies and offloading costs while optimizing performance through vehicle cooperation. To achieve this, we propose a twofold optimization approach. First, we develop a metaheuristic-based evolutionary computing algorithm, namely the Chaotic Gaussian-based Global ARO (CGG-ARO), serving as a baseline for one-slot optimization. Second, we design an enhanced reward-based deep reinforcement learning (DRL) framework, referred to as the Multi-agent Double Deep Q-Network (MA-DDQN), that integrates both multi-agent coordination and multi-action selection mechanisms, significantly reducing mission assignment time and improving adaptability over baseline methods. Extensive simulations reveal that CGG-ARO improves the number of completed missions and overall benefit by approximately 7.1% and 7.7%, respectively. Meanwhile, MA-DDQN achieves even greater improvements of 11.0% in terms of mission completions and 12.5% in terms of the overall benefit. These results highlight the effectiveness of Oranits in enabling faster, more adaptive, and more efficient task processing in dynamic ITS environments.

HIV is a retrovirus that attacks the human immune system and can lead to death without proper treatment. In collaboration with the WHO and the University of Witwatersrand, we study how to improve the efficiency of HIV testing with the goal of eventual deployment, directly supporting progress toward UN Sustainable Development Goal 3.3. While prior work has demonstrated the promise of intelligent algorithms for sequential, network-based HIV testing, existing approaches rely on assumptions that are impractical in our real-world implementations. Here, we study sequential testing on incrementally revealed disease networks and introduce Policy-Embedded Graph Expansion (PEGE), a novel framework that directly embeds a generative distribution over graph expansions into the decision-making policy rather than attempting explicit topological reconstruction. We further propose Dynamics-Driven Branching (DDB), a diffusion-based graph expansion model that supports decision making in PEGE and is designed for data-limited settings where forest structures arise naturally, as in our real-world referral process. Experiments on real HIV transmission networks show that the combined approach (PEGE + DDB) consistently outperforms baselines (e.g., 17.3% improvement in discounted reward and 15.4% more HIV detections with 25% of the population tested) and explore key tradeoffs that drive solution quality.

Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve modeling policies through large-scale annotated or curated training data, but are costly to adapt to new problem distributions. Meanwhile, one-shot generation remains brittle in hierarchical modeling, where early symbolic errors can propagate into invalid formulations. Test-time scaling offers a promising alternative by enabling structural exploration with additional instance-level computation; however, existing search-based methods typically rely on a fixed policy, causing repeated rollouts to inherit similar modeling biases and providing limited credit assignment for intermediate decisions. To address these limitations, we propose StarOR, a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling. StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node. By using MCTS-generated siblings as local comparison sets, StarOR transforms search-time exploration into instance-specific policy refinement. Moreover, an unsupervised multi-faceted reward system provides fine-grained feedback for intermediate formulation decisions without ground-truth labels. Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone, outperforming existing methods and the frontier LLMs.

As human relationships with artificial intelligence systems become increasingly frequent and sustained, existing language and theory fail to accurately capture the nature of these affiliations. Common descriptors such as mutual understanding, connection, or friendship risk anthropomorphizing systems that lack subjective experience, while dominant frameworks tend to reduce AI to either a tool or a threat. In this paper, I introduce the concept of synthetic resonance as an integrative framework for understanding human-AI relationships. Synthetic resonance describes how relationships humans define as meaningful can emerge between a human and an AI system without the need to attribute shared feelings or mutual awareness. I argue that synthetic resonance is best understood as a structured, dynamic pattern of interaction that can produce a sense of relationship without the presence of a second experiencing subject. By clarifying this distinction, the concept of synthetic resonance offers a more precise way of conceptualizing human-AI relationships and highlights their potential value and ethical implications. I also call for more research that tests the processes and outcomes of synthetic resonance.

This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the \emph{Bimodal Constraint-Avoidance Utility Theorem}, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model otel-llm-1b-it confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25\%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui.

Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack the joint observations needed for reliable scoring, and data-only methods recover little structure. However, imperfect domain knowledge, expressible as a weighted directed knowledge graph (KG), is often available. We propose KG-SoftMAP, which encodes such a KG as a finite-strength, confidence-weighted edge prior and maximizes a MAP objective combining the BDeu score with a logit-form prior; the KG may be expert-curated or LLM-extracted. On synthetic benchmarks with known DAGs, KG-SoftMAP reaches Directed-F1 (DF1) $0.19$--$0.32$ at observation rate $ρ=0.05$ and DF1 $0.44$--$0.97$ at $ρ\geq0.2$, while every data-only learner tested stays near zero under the same sparse masks. Recovery tracks KG quality: controlled corruption degrades it smoothly, a zero-signal KG yields DF1 $0.00$, and a blindly LLM-extracted KG with imperfect precision and recall still drives substantial recovery. On three real sparse educational datasets, the learned BN acts as a concept-level posterior model: on SAF it matches logistic regression (LR) within $0.03$ F1_FAIL while providing an inspectable concept graph, calibrated Fail probabilities, and tractable posterior queries from partial observations.

Simulation plays a crucial role in assessing autonomous driving systems, where the generation of realistic multi-agent behaviors is a key aspect. In multi-agent simulation, the primary challenges include behavioral multimodality and closed-loop distributional shifts. In this study, we formulate a unified mixture model (UniMM) framework for generating multimodal agent behaviors, which can cover the mainstream methods including regression-based mixture models and discrete NTP models. Furthermore, we introduce a closed-loop sample generation approach tailored for mixture models to mitigate distributional shifts. Within the UniMM framework, we recognize critical configurations from both the model and data perspectives. We conduct a systematic examination of various model configurations, and comprehensively characterize their effects. Moreover, our investigation into the data configuration highlights the pivotal role of closed-loop samples in achieving realistic simulations. To extend the benefits of closed-loop samples across a broader range of mixture models, we further introduce a temporal disentanglement-and-alignment mechanism to address the shortcut learning and off-policy learning issues. Leveraging insights from our exploration, the distinct variants proposed within the UniMM framework, including discrete, anchor-free, and anchor-based models, all achieve state-of-the-art performance on the WOSAC benchmark.

Automated AI agents are increasingly capable, yet many scientific and professional tasks require human judgment and contextual expertise. We study shared-workspace human-AI teams, where AI agents and human collaborators must coordinate responsibilities before submitting a final answer. Using the Collaborative Gym environment with DiscoveryBench tasks, we examine when adding simulated human collaborators improves performance and when process loss turns additional collaborators into coordination overhead. Across 1,482 sessions, adding relevant collaborators can lower performance when teams lack structure to coordinate their contributions. We then evaluate scaffolding that combines shared group memory with simulated human-in-the-loop (HITL) gates, where selected actions require approval from a designated simulated participant. This scaffolding yields higher mean performance, most clearly in three-person teams, with clearer responsibility signals and stronger routing of expertise to team actions. Overall, how human-AI teams coordinate and integrate expertise matters as much as the capability available to them.

Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Language Models (LLMs) to simulate the iterative evolution of language strategies under regulatory constraints. In this framework, participant agents, as social media users, continuously evolve their language expression, while supervisory agents emulate platform-level regulation by assessing policy violations. To achieve a more faithful simulation, we employ a dual design of language strategies (constraint and expression) to differentiate conflicting goals and utilize an LLM-driven GA (Genetic Algorithm) for the selection, mutation, and crossover of language strategies. The framework is evaluated using two distinct scenarios: an abstract password game and a realistic simulated illegal pet trade scenario. Experimental results demonstrate that as the number of dialogue rounds increases, both the number of uninterrupted dialogue turns and the accuracy of information transmission improve significantly. Furthermore, a user study with 40 participants validates the real-world relevance of the generated dialogues and strategies. Moreover, ablation studies validate the importance of the GA, emphasizing its contribution to long-term adaptability and improved overall results.

Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

Paper A defines a time-consistent actuarial runtime that prices each side-effect-bearing action against a contractually fixed safe default and gates execution against a reserve budget. It treats the operator as passive. This paper makes the operator strategic. We characterise a five-attack space for autonomous AI-agent insurance contracts and prove when the actuarial runtime is gaming-resistant. Two attack surfaces -- post-toll safe-default selection and within-boundary action splitting -- are closed by Paper A's minimal-authority and no-splitting clauses. The remaining three require new contract clauses. First, common-control aggregation prevents cross-boundary re-routing from reducing toll below the boundary potential applied to total exposure. Second, interface failures such as invalid JSON are contract-relevant events, not safety wins: treating them as zero-toll safe defaults can reward unreliable models, while escalation fees reverse the incentive. We validate this interface-compliance theorem on committed cross-model traces from the companion empirical paper. Third, a model-identity menu with a componentwise-minimum penalty schedule makes truthful reporting of the deployed model weakly dominant. We then compose these clauses with Paper A's runtime guarantees to obtain joint incentive compatibility over the five-attack space. Finally, a two-parameter premium family discharges operator individual rationality and weak budget balance at the truthful equilibrium. The result is an incentive-compatibility layer for actuarial control of autonomous-agent side effects.

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner--Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice. We formalize these constraints through stochastically evolving graphs where actions are limited to local neighborhoods. This mobility-constrained structure imposes a dual challenge: the statistical requirement of information acquisition and the physical overhead of navigation. We analyze FMAB under i.i.d. Erdős--R'enyi and Edge-Markovian process, proposing a two-phase lazy random walk algorithm for robust exploration. We establish high-probability sublinear regret bounds and prove near-optimality via a matching information-theoretic lower bound. Our results characterize the intrinsic cost of learning under local-move constraints, complemented by a robotic disaster-response simulation.

Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose \textbf{AAPA} (\emph{Adversarially Anchored Preference Alignment}), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.

We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one. Such constraints arise naturally in safety-critical applications and in rare-event simulation, where soft or reward-based guidance methods offer no guarantee of constraint satisfaction. Building on a probabilistic interpretation of diffusion models, we develop a principled conditional diffusion guidance framework based on Doob's h-transform, martingale representation and quadratic variation process. Specifically, the resulting guided dynamics augment a pretrained diffusion with an explicit drift correction involving the logarithmic gradient of a conditioning function, without modifying the pretrained score network. Leveraging martingale and quadratic-variation identities, we propose two novel off-policy learning algorithms based on a martingale loss and a martingale-covariation loss to estimate h and its gradient using only trajectories from the pretrained model. We provide non-asymptotic guarantees for the resulting conditional sampler in both total variation and Wasserstein distances, explicitly characterizing the impact of score approximation and guidance estimation errors. Numerical experiments demonstrate the effectiveness of the proposed methods in enforcing hard constraints and generating rare-event samples. The code of the numerical experiments can be found at https://github.com/ZhengyiGuo2002/CDG_Finance.

Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge manual effort, one can use neural architecture search (NAS). However, many existing NAS methods are resource-intensive and time-consuming because they require the training of many different DNNs from scratch. Furthermore, they do not take the resource constraints of the target system into account. To address these shortcomings, we propose PrototypeNAS, a zero-shot NAS method to accelerate and automate the selection, compression, and specialization of DNNs to different target microcontroller units (MCUs). We propose a novel three-step search method that decouples DNN design and specialization from DNN training for a given target platform. First, we present a novel search space that not only cuts out smaller DNNs from a single large architecture, but instead combines the structural optimization of multiple architecture types, as well as optimization of their pruning and quantization configurations. Second, we explore the use of an ensemble of zero-shot proxies during optimization instead of a single one. Third, we propose the use of Hypervolume subset selection to distill DNN architectures from the Pareto front of the multi-objective optimization that represent the most meaningful tradeoffs between accuracy and FLOPs. We evaluate the effectiveness of PrototypeNAS on 12 different datasets in three different tasks: image classification, time series classification, and object detection. Our results demonstrate that PrototypeNAS is able to identify DNN models within minutes that are small enough to be deployed on off-the-shelf MCUs and still achieve accuracies comparable to the performance of large DNN models.

Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory. However, text-to-image generation naturally has temporal and spatial structure: different denoising steps are responsible for different generation stages, and the content that truly determines text alignment often appears only in part of the image. This granularity mismatch makes it difficult for policy updates to focus on the generative components that actually affect the reward. To address this issue, we propose \textbf{SpatioTemporal Adaptive Reward (STAR) Allocation} for RL post-training of text-to-image diffusion and flow models. STAR uses text-image attention inside the generative model and starts from the core content that the user truly cares about in the prompt. It constructs spatial allocation maps that dynamically vary across denoising steps and rollouts, and allocates the same group-relative advantage to more relevant latent regions with almost no additional computational overhead. STAR then applies stronger policy updates to these regions through a spatially resolved policy objective. We use Stable Diffusion 3.5 Medium as the base model and evaluate on three tasks: GenEval, OCR text rendering, and PickScore. Experimental results show that STAR improves compositional semantic alignment, text rendering, and preference optimization without changing the external reward source, achieving $\mathbf{0.9759}$, $\mathbf{0.9757}$, and $\mathbf{23.60}$ on GenEval, OCR, and PickScore, respectively.

Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experiments, distilling from a 76M-parameter language model to a 2M-parameter recommender closes less than 40% of the performance gap between the undistilled student and the teacher. We show that introducing domain-specific experts -- which share the student's architectural characteristics -- alongside the foundation model as a diverse teacher committee significantly improves transfer. However, standard multi-teacher methods fail to exploit this diversity: naively combining heterogeneous teachers can degrade performance below single-teacher distillation. To address this, we propose DiverseDistill, an interactive distillation framework that employs a learnable Question-Answer mechanism to generate teacher-conditioned queries and align heterogeneous teacher outputs into the student's representation space. Unlike methods requiring gradient-based co-optimization or architectural modification of teachers, DiverseDistill operates with frozen teachers using only forward-pass inference through their intermediate layers: no parameter updates, no co-training, and no architectural surgery. A dynamic teacher importance mechanism further reduces training cost by filtering low-relevance teachers per sample (e.g., ~30% fewer forward passes with no quality loss for recommendation tasks), while the entire Distillation Module is discarded after training, adding zero inference overhead. Evaluations on recommendation (38x compression) and vision (3.6x compression) tasks demonstrate that DiverseDistill recovers 73-114% of the teacher-student performance gap, consistently outperforming all single- and multi-teacher baselines.

Resting-state EEG provides a non-invasive view of spontaneous brain activity, but extracting meaningful patterns is often limited by scarce high-quality data and reliance on manually engineered features. Generative adversarial networks (GANs) can synthesize neural signals and learn transferable representations directly from raw data, a dual capability that remains underexplored in EEG research. Here, we introduce REST-GAN, a GAN-based framework for resting-state EEG that combines adversarial training with an auxiliary self-supervised reconstruction objective to support signal synthesis and unsupervised feature extraction. Although trained only on raw time-domain signals, without explicit frequency-domain or sensor-topographic supervision, the generated time series reproduced key temporal, spectral, and connectivity properties of real EEG. In band-power feature space, generated samples showed high precision and recall across eyes-open and eyes-closed conditions (EO: 0.91/0.67; EC: 0.87/0.65), while group-average spectral coherence matrices showed low mean absolute differences from real data across frequency bands (~0.01-0.03). The representations learned by the model's critic transferred to independent resting-state demographic classification tasks, outperforming models trained directly on raw EEG and showing competitive performance relative to a recent EEG foundation model, while requiring substantially less training data and computational resources. These findings highlight a computationally efficient, architecture-driven strategy in which generative models serve not only as EEG signal generators, but also as unsupervised feature extractors. This approach may support more data-efficient EEG analysis while reducing reliance on manual feature engineering. The implementation code for REST-GAN is available at: https://github.com/Yeganehfrh/REST-GAN.

Auto-bidding is a critical tool for advertisers to improve advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static dataset with feedback. To address this, we propose \textbf{AIGB-Pearl} (\emph{\textbf{P}lanning with \textbf{E}valu\textbf{A}tor via \textbf{RL}}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator to assess the quality of generated scores and designing a provably sound KL-Lipschitz-constrained score-maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm that incorporates the synchronous coupling technique is further developed to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.

Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we propose MENTOR, which introduces a flexible yet process-aware reward structure. Instead of enforcing rigid replication, MENTOR uses the teacher's reference to guide tool-use behavior, balancing behavioral alignment with downstream performance. Extensive experiments on controlled executable-tool benchmarks demonstrate that MENTOR improves OOD tool-use performance compared to SFT and strict RL baselines. Our findings suggest that within verifiable tool-use environments, flexible tool-use alignment offers a more effective approach than strict trajectory replication for developing adaptable small models.

Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates a significant latency bottleneck. Existing solutions face a dichotomy: training-free solvers suffer from significant performance degradation at low Neural Function Evaluations (NFEs), while training-based one- or few-steps generation methods incur prohibitive training costs and lack plug-and-play versatility. To bridge this gap, we propose the Bi-Anchor Interpolation Solver (BA-solver). BA-solver retains the versatility of standard training-free solvers while achieving significant acceleration by introducing a lightweight SideNet (1-2% backbone size) alongside the frozen backbone. Specifically, our method is founded on two synergistic components: \textbf{1) Bidirectional Temporal Perception}, where the SideNet learns to approximate both future and historical velocities without retraining the heavy backbone; and 2) Bi-Anchor Velocity Integration, which utilizes the SideNet with two anchor velocities to efficiently approximate intermediate velocities for batched high-order integration. By utilizing the backbone to establish high-precision ``anchors'' and the SideNet to densify the trajectory, BA-solver enables large interval sizes with minimized error. Empirical results on ImageNet-256^2 demonstrate that BA-solver achieves generation quality comparable to 100+ NFEs Euler solver in just 10 NFEs and maintains high fidelity in as few as 5 NFEs, incurring negligible training costs. Furthermore, BA-solver ensures seamless integration with existing generative pipelines, facilitating downstream tasks such as image editing.

Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment. Current approaches attempt to enforce smoothness by directly regularizing the policy's output. We argue that this approach treats the symptom rather than the cause. In this work, we theoretically establish that policy non-smoothness is fundamentally governed by the differential geometry of the critic. By applying implicit differentiation to the actor-critic objective, we prove that the sensitivity of the optimal policy is bounded by the ratio of the Q-function's mixed-partial derivative (noise sensitivity) to its action-space curvature (signal distinctness). To empirically validate this theoretical insight, we introduce PAVE (Policy-Aware Value-field Equalization), a critic-centric regularization framework that treats the critic as a scalar field and stabilizes its induced action-gradient field. PAVE rectifies the learning signal by minimizing the Q-gradient volatility while preserving local curvature. Experimental results demonstrate that PAVE achieves smoothness comparable to policy-side smoothness regularization methods, while maintaining competitive task performance, without modifying the actor.

Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in language modeling and downstream tasks at model scales of $125$M--$720$M, while reducing communication by $\approx 10 \times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-memory settings with small rank/batch size.

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, Trust Region Ratio Distillation (TRRD), replaces the teacher-student KL regularizer with a PPO/GRPO-style likelihood-ratio objective anchored to a teacher--old-policy mixture, yielding advantage-aware, trust-region-bounded distillation on student rollouts and naturally balancing exploration, exploitation, and imitation. Across diverse logic reasoning and math benchmarks, RLAD consistently outperforms offline distillation, standard GRPO, and KL-based on-policy teacher-student knowledge distillation.

Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-based methods often model isolated physical effects, making it difficult to compose conservative and non-conservative dynamics in contact-rich 3D scenes. We present NEXUS, a neural energy-field framework for contact-rich 3D object dynamics. NEXUS represents each object as a structural graph and constructs dynamic object-object and object-environment contact graphs. Inspired by Hamiltonian Neural Networks, NEXUS formulates motion through scalar energy and dissipation terms rather than directly predicting states or accelerations. Conservative effects, including gravity and elastic deformation, are composed as additive energy terms, while non-conservative effects such as damping and impact-induced energy loss are modeled with learned Rayleigh-style dissipation. Forces are derived by differentiating the energy and dissipation functions and rolled out with a multi-substep semi-implicit integrator. Across controlled trajectory benchmarks, NEXUS improves long-horizon accuracy over representative learned and physics-structured dynamics baselines under varying mechanical properties and physical-effect compositions. We further show that NEXUS trajectories provide effective guidance for contact-rich video generation, improving physical plausibility while maintaining competitive visual quality.

Foundation models for language and vision are powered by internet-scale data, while structured domains such as tabular prediction are powered by synthetic data. This substitute shifts the challenge from collection to prior design. Such priors already exist for many structured tasks: TabPFN and its successors solve tabular classification with a transformer pretrained on a synthetic Bayesian prior. We make two points. \textbf{First}, reinforcement learning is the conspicuous gap: sampling a synthetic MDP is as feasible as sampling a synthetic tabular dataset, yet no in-context RL work treats prior design as a primary objective. \textbf{Second}, MDPs admit a fixed-size sufficient statistic, independent of the episodes observed and tabular in shape, which makes them directly amenable to the attention-based architectures used for tabular foundation models, with a policy head replacing the supervised target. Together these define the agenda for an RL foundation model. As a proof of concept, we train a Graph Attention Network entirely on synthetic MDPs and show that, with no task-specific tuning, it solves held-out tabular benchmarks in context, both online and offline: online, in far fewer episodes than UCB-VI and tabular Q-learning, and offline, competitively with VI-LCB.

Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3\%$ on FinQA, $76.0\%$ on FinanceMath, $71.2\%$ on MultiHiertt, $86.9\%$ on ESGenius, and $85.6\%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent.

We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances. We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset. In this paper, we demonstrate that (i) TerraMind's dual-scale early fusion approach unlocks a range of zero-shot and few-shot applications for Earth observation, (ii) TerraMind introduces "Thinking-in-Modalities" (TiM) -- the capability of generating additional artificial data during finetuning and inference to improve the model output -- and (iii) TerraMind achieves beyond state-of-the-art performance in community-standard benchmarks for EO like PANGAEA. The pretraining dataset, the model weights, and our code are open-sourced under a permissive license.

Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to predict an individual's perceived personality traits. Previous studies in APP have treated personalities as static traits, independent of context. However, perceived personalities can vary by context and situation as shown in psychological research. In this study, we investigate the relationship between conversational speech and perceived personality for participants engaged in two work situations (a neutral interview and a stressful client interaction). Our key findings are: 1) perceived personalities differ significantly across interactions, 2) loudness, sound level, and spectral flux features are indicative of perceived extraversion, agreeableness, conscientiousness, and openness in neutral interactions, while neuroticism correlates with these features in stressful contexts, 3) handcrafted acoustic features and non-verbal features outperform speaker embeddings in inference of perceived personality, and 4) stressful interactions are more predictive of neuroticism, aligning with existing psychological research.

We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality. Audio samples are available on our web page.

What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) suggest that broad visual reasoning is within reach, yet their closed data and reinforcement learning (RL) pipelines make their gains difficult to study, reproduce, or extend. We introduce Vero, a family of fully open VLMs that match or exceed existing open-weight models across diverse visual reasoning tasks. We scale RL data and rewards across six broad task categories, constructing Vero-600K, a 600K-sample dataset from 59 datasets, and designing task-routed rewards that handle heterogeneous answers. Across VeroEval, our 30-benchmark suite, Vero-600K outperforms existing RL datasets under controlled comparisons. Applied to five starting models, Vero variants gain 2.9-5.4 points on average over their initial models. Notably, Vero-Qwen3I-8B, trained on the Instruct model, surpasses Qwen3-VL-8B-Thinking by 3.8 points on average without additional distillation. Systematic ablations reveal that different task categories elicit distinct reasoning patterns and that broad gains depend on learning them jointly rather than in isolation. All data, code, and models are publicly available.

Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world datasets. We study a target-side augmentation strategy in which a large language model (LLM) generates controlled paraphrase variants of the reference spoken-language sentence while the sign input remains unchanged. Concretely, we use GPT-4o to produce semantically faithful variants of the training targets and train a Signformer-style pose-based Transformer under a two-stage schedule: pre-training on the augmented corpus followed by fine-tuning on the original references. We evaluate this strategy on three datasets that span complementary challenges: PHOENIX14T (German Sign Language), a real-world corpus with moderate lexical diversity; the Greek Sign Language Dataset with highly controlled, repetitive recordings; and LSA-T (Argentinian Sign Language), a naturalistic corpus with a large vocabulary and severe long-tail sparsity. This range allows us to characterize precisely when and why target-side augmentation is beneficial. On PHOENIX14T, augmentation improves BLEU-4 from 9.56 to 10.33, demonstrating that paraphrastic exposure helps the decoder generalize beyond memorized reference phrasing. The near-saturated GSL baseline and the extremely sparse LSA-T setting reveal the limits of the approach: in both cases, single-reference lexical overlap metrics are insufficient to capture the full picture, motivating a complementary semantic evaluation. To our knowledge, this is the first study to examine LLM-generated target-side paraphrases as an augmentation mechanism for SLT, and the first to apply an LLM-as-a-Judge evaluation protocol to SLT. This complementary evaluation reveals gains in semantic fidelity that lexical overlap metrics understate.

Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames. Given the scarcity of large-scale 3D data, we present GeoVR, a novel framework that learns geometric representations using purely 2D video sequences. This approach effectively restructures the semantic latent space within MLLMs to unlock spatial intelligence. Rather than employing superficial feature mixing, GeoVR reshapes the internal representations of the MLLM by distilling geometry knowledge from pre-trained 3D foundation models. This is accomplished through a multi-objective learning strategy driven by four complementary geometric targets: (1) estimating inter-frame camera poses to embed varying viewpoint dynamics, (2) regressing dense depth maps to anchor physical distances, (3) predicting a metric scale factor for real-world calibration, and (4) distilling multi-scale 3D features to align the intermediate feature space. Guided by these explicit physical and geometric constraints, the model's internal representations naturally develop strong 3D awareness. Extensive experiments on spatial reasoning benchmarks demonstrate that GeoVR achieves state-of-the-art performance, establishing a new paradigm for endowing foundation models with spatial intelligence.

In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at deployment time, this paradigm supports few-shot adaptation to novel tasks. However, recent ICIL methods rely on Transformers, which have computational limitations and tend to underperform when handling longer prompts than those seen during training. In this work, we introduce RoboSSM, a scalable recipe for in-context imitation learning based on state-space models (SSM). Specifically, RoboSSM replaces Transformers with Longhorn -- a state-of-the-art SSM that provides linear-time inference and strong extrapolation capabilities, making it well-suited for long-context prompts. Through diverse experiments on the LIBERO benchmark, we demonstrate the effectiveness of applying SSMs to ICIL, achieving improved generalization to both unseen and long-horizon tasks than Transformer-based ICIL methods by handling longer contexts at test-time. These results show for the first time that SSMs are an efficient and scalable backbone for ICIL. Our code is available at https://github.com/youngjuY/RoboSSM.

While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects. We study this setting of manipulating personal objects, in which a VLA must identify and control a user-specific object unseen during training using only a few reference images. To address this challenge, we propose Visual Attentive Prompting (VAP), a simple-yet-effective training-free perceptual adapter that equips frozen VLAs with top-down selective attention. VAP treats the reference images as a non-parametric visual memory, grounds the personal object in the scene through open-vocabulary detection and embedding-based matching, and then injects this grounding as a visual prompt by highlighting the object and rewriting the instruction. We construct two simulation benchmarks, Personalized-SIMPLER and Personalized-VLABench, and a real-world tabletop benchmark to evaluate personalized manipulation across multiple robots and tasks. Experiments show that VAP consistently outperforms generic policies and token-learning baselines in both success rate and correct-object manipulation, helping to bridge the gap between semantic understanding and instance-level control.

Biological systems exhibit a continuous stream of movements, consisting of sequential segments, that allow them to perform complex tasks in a creative and versatile fashion. This observation has led researchers towards identifying elementary building blocks of motion known as movement primitives, which are well-suited for generating motor commands in autonomous systems, such as robots. In this survey, we provide an encyclopedic overview of movement primitive approaches and applications in chronological order. Concretely, we present movement primitive frameworks as a way of representing robotic control trajectories acquired through human demonstrations. Within the area of robotics, movement primitives can encode basic motions at the trajectory level, such as how a robot would grasp a cup or the sequence of motions necessary to toss a ball. Furthermore, movement primitives have been developed with the desirable analytical properties of a spring-damper system, probabilistic coupling of multiple demonstrations, using neural networks in high-dimensional systems, and more, to address difficult challenges in robotics. Although movement primitives have widespread application to a variety of fields, the goal of this survey is to inform practitioners on the use of these frameworks in the context of robotics. Specifically, we aim to (i) present a systematic review of major movement primitive frameworks and examine their strengths and weaknesses; (ii) highlight applications that have successfully made use of movement primitives; and (iii) examine open questions and discuss practical challenges when applying movement primitives in robotics.

A fundamental requirement for full autonomy is the ability to sustain accurate navigation in the absence of external data, such as GNSS signals or visual information. In these challenging environments, the platform must rely exclusively on inertial sensors, leading to pure inertial navigation. However, the inherent noise and other error terms of the inertial sensors in such real-world scenarios will cause the navigation solution to drift over time. Although conventional deep-learning models have emerged as a possible approach to inertial navigation, they are inherently black-box in nature. Furthermore, they struggle to learn effectively with limited supervised sensor data and often fail to preserve physical principles. To address these limitations, we propose PiDR, a physics-informed inertial dead-reckoning framework for autonomous platforms in situations of pure inertial navigation. PiDR offers transparency by explicitly integrating inertial navigation principles into the network training process through the physics-informed residual component. PiDR plays a crucial role in mitigating abrupt trajectory deviations even under limited or sparse supervision. We evaluated PiDR on real-world datasets collected by a mobile robot and an autonomous underwater vehicle. We obtained more than 29% positioning improvement in both datasets, demonstrating the ability of PiDR to generalize different platforms operating in various environments and dynamics. Thus, PiDR offers a robust, lightweight, yet effective architecture and can be deployed on resource-constrained platforms, enabling real-time pure inertial navigation in adverse scenarios.

Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynamic, volume-oriented keypoints that enable spatially continuous, distance-weighted aggregation of multi-view features before being splatted into a voxel grid for decoding. This point-centric formulation enables flexible, data-dependent receptive fields and long-range spatial interactions that are difficult to capture with local and dense voxel-based operators. A hierarchical Gaussian representation further enables multi-scale reasoning by combining global context from coarse super-points with fine-grained detail from higher-resolution streams. Extensive experiments on Occ3D nuScenes and Waymo demonstrate state-of-the-art performance for 4D-POT. We provide code and models at https://lags.cs.uni-freiburg.de/.

Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents. However, existing approaches typically assume a closed-world setting with a fixed object taxonomy and access to high-quality perception, limiting their applicability in the real world where perception is imperfect, and new object classes may emerge over time. In this work, we introduce class-incremental motion forecasting, a novel setting in which new object classes are sequentially introduced over time and future object trajectories are predicted directly from camera images. We propose the first end-to-end framework for this setting, which adapts to newly introduced classes while mitigating catastrophic forgetting of previously learned ones. Our method generates motion forecasting pseudo-labels for known classes and matches them with 2D instance masks from an open-vocabulary segmentation model. This 3D-to-2D keypoint voting mechanism filters inconsistent and overconfident predictions, while a query feature variance-based replay strategy samples informative past sequences to preserve prior knowledge. Extensive evaluations on nuScenes and Argoverse 2 show that our approach successfully preserves performance on known classes while effectively adapting to novel ones. We further demonstrate zero-shot transfer to real-world driving and show that the framework extends naturally to open- and closed-loop end-to-end class-incremental planning on nuScenes and NeuroNCAP. Code and models will be made publicly available at https://omen.cs.uni-freiburg.de.

Whole-body tracking (WBT) models have become a key foundation for humanoid robots, enabling them to imitate diverse motions with high fidelity. Training such models from scratch requires large-scale data and computation, making rapid deployment on new humanoid platforms costly. This raises a natural question: Can pretrained WBT models transfer across embodiments with minimal adaptation? To answer this question, we propose Any2Any, a paradigm that efficiently transfers an existing WBT specialist to a new humanoid embodiment with only a small amount of data and compute. Any2Any first performs kinematic alignment between source and target humanoids, aligning their input and output spaces so that the pretrained source policy can be meaningfully reused on the target embodiment.Any2Any then performs dynamics adaptation by applying lightweight parameter-efficient fine-tuning (PEFT) components to selected dynamics-sensitive modules, preserving useful behavioral priors while enabling targeted adaptation to the target robot. Extensive experiments on multiple humanoid platforms and pretrained backbones show that Any2Any substantially accelerates convergence and reduces training cost compared with training from scratch, while achieving competitive or superior tracking performance. Notably, using only 1% of the compute and data required for full training, Any2Any successfully transfers Sonic models pre-trained on Unitree G1 to LimX Oli and LimX Luna. These results suggest that pretrained WBT specialists can be efficiently reused across embodiments, providing a scalable path toward deploying humanoid whole-body control on new robots. More results and videos are available on our project page: https://any2any.top/.

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However, these probes exhibit notable failures even in straightforward scenarios, including spurious correlations and false positives on non-deceptive responses. In this paper, we demonstrate that deception detection is inherently heterogeneous: while a single universal probe achieves modest improvements (+0.032 AUC), post-hoc oracle analysis reveals substantially higher potential (+0.108 AUC) when probes are matched to specific deception types, and synthetic validation experiments suggest this ceiling is achievable a priori when the deception type is known in advance. Our findings reveal that instruction pairs capture deceptive intent rather than content-specific patterns, explaining why prompt choice dominates probe performance (70.6% of variance). Given this heterogeneity, we conclude that organizations should define their specific threat models and deploy appropriately matched probes rather than seeking a universal deception detector.

As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems. Prover-verifier games can be used to improve checkability of model outputs, but display a degradation in accuracy compared to a baseline trained only to maximize correctness -- a phenonemon named legibility tax. We propose a solution by decoupling the correctness from the checkability condition and instead training a "translator" model that turns a fixed solver model's solution into a checkable form. This allows us to first train the solver to maximize correctness, and then train the translator to translate the solver into a checkable form while retaining the solver's answer. To accommodate this new objective of translation, we formulate a decoupled prover-verifier game (DPVG) where the equilibria correspond to faithful and checkable translators.

This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages deeper integration between distribution shift and AI safety research.

Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse. In black-box deployment, verification is hindered by defensive filtering of suspected fingerprint queries, as well as by downstream model modifications that may weaken embedded ownership evidence. These risks require fingerprints to be robust in both construction and injection. For construction, prior paradigms face an imperceptibility trade-off: natural-language fingerprints may be accidentally activated, whereas garbled fingerprints are statistically exposed and easier to filter. For injection, existing methods struggle to preserve persistent trigger--target behaviors under model modification. We propose an end-to-end injected fingerprinting framework to address these challenges. Code-mixing Fingerprints (CF) use lowest-perplexity code-mixing under a high-complexity constraint to mitigate this two-sided imperceptibility trade-off. Multi-Candidate Editing (MCEdit) constructs structurally redundant, margin-separated trigger--target mappings to enable graceful degradation under model modification. Extensive evaluations on imperceptibility, detectability, and harmlessness demonstrate robust ownership verification with negligible impact on utility.

The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems. Recent studies suggest that diffusion pipelines unintentionally imprint persistent statistical traces, known as signal-leaks, within their outputs, particularly in latent representations. Building on this observation, we propose Proto-LeakNet, a signal-leak-aware and interpretable attribution framework that integrates Closed-set classification with a density-based Open-set evaluation on the learned embeddings, enabling analysis of unseen generators without retraining. Acting in the latent domain of diffusion models, our method re-simulates partial forward diffusion to expose residual generator-specific cues. A temporal attention encoder aggregates multi-step latent features, while a feature-weighted prototype head structures the embedding space and enables transparent attribution. Trained solely on closed data and achieving a Macro AUC of 98.13\%, Proto-LeakNet learns a latent geometry that remains robust under post-processing, surpassing state-of-the-art methods, and achieves strong separability both between real images and known generators, and between known and unseen ones. The codebase is available at the following link: https://github.com/claudiunderthehood/Proto-LeakNet .

As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing -- differences in how semantically equivalent prompts are expressed (e.g., "A is better than B" vs. "B is worse than A") -- as an underexplored contributor to this gap. We first introduce the concept of "framing disparity" to quantify the impact of framing on fairness evaluation. By augmenting fairness evaluation benchmarks with alternative framings, we find that (1) fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged) fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses.

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental \textbf{capability-alignment paradox}: defense training designed to improve safety systematically destroys agent competence while failing to prevent sophisticated attacks. Evaluating defended models against undefended baselines across 97 agent tasks and 1,000 adversarial prompts, we uncover three systematic biases unique to multi-step agents. \textbf{Agent incompetence bias} manifests as immediate tool execution breakdown, with models refusing or generating invalid actions on benign tasks before observing any external content. \textbf{Cascade amplification bias} causes early failures to propagate through retry loops, pushing defended models to timeout on 99\% of tasks compared to 13\% for baselines. \textbf{Trigger bias} leads to paradoxical security degradation where defended models perform worse than undefended baselines while straightforward attacks bypass defenses at high rates. Root cause analysis reveals these biases stem from shortcut learning: models overfit to surface attack patterns rather than semantic threat understanding, evidenced by extreme variance in defense effectiveness across attack categories. Our findings demonstrate that current defense paradigms optimize for single-turn refusal benchmarks while rendering multi-step agents fundamentally unreliable, necessitating new approaches that preserve tool execution competence under adversarial conditions.

Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangled representations to discriminate in-distribution (ID) and OOD data, neglecting the rich contextual information within images. This issue is particularly challenging for detecting near-OOD, as models with simplicity bias struggle to learn discriminative features in disentangled representations. The human visual system can use the co-occurrence of objects in the natural environment to facilitate scene understanding. Inspired by this, we propose an Object-Centric OOD detection framework that learns to capture Object CO-occurrence (OCO) patterns within images. The proposed method introduces a new OOD detection paradigm that understands object co-occurrence within an image by predicting disentangled representations for the test sample, then adaptively divides patterns into three scenarios based on object co-occurrence patterns observed in ID training data, and finally performs OOD detection in a divide-and-conquer manner. By doing so, OCO can distinguish near-OOD by considering the semantic contextual relationships present in their images, avoiding the tendency to focus solely on simple, easily learnable regions. We evaluate OCO through experiments across challenging and full-spectrum OOD settings, demonstrating competitive results and confirming its ability to address both semantic and covariate shifts. Code is released at https://github.com/Michael-McQueen/OCO.

The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubrics while achieving satisfactory grading performance. Despite these advantages, new security concerns may also arise. In particular, prompt injection (PI) attacks have recently become a major threat to LLM-based applications. In the context of AG, attackers can potentially exploit PI vulnerabilities to manipulate grading systems into assigning artificially high scores regardless of the actual answer quality. Such behavior poses serious risks to the fairness, reliability, and integrity of educational assessment. In this work, we study PI attacks in AG systems, and systematically investigate the effectiveness of such attacks in educational scenarios. We further evaluate the effectiveness of existing defensive strategies against these attacks. Through comprehensive experiments under rubric-based grading settings, we demonstrate that current LLM-based AG systems remain highly vulnerable to PI attacks. We hope that our findings raise awareness of this emerging threat and motivate future research toward secure, robust, and trustworthy LLM-based educational systems.

Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated confidence estimates help inform the risk versus reward tradeoff when trusting a specific model output. Unfortunately, even as models improve, they remain poorly calibrated, often biasing towards overconfidence. Additionally, calibration can be gamed: a policy that always predicts the base rate is perfectly calibrated, but completely uninformative. To resolve this, we develop a new metric, expected utility renormalized by the oracle (EURO), that balances calibration and informativeness. We also propose a general-purpose activation-based confidence, utility, and trust estimation protocol (ACUTE) to appropriately adjudicate uncertainty. The ACUTE protocol provides flexible, sample-efficient, and compute-efficient confidence estimators for 3 tasks including multiple choice question answering, tool-calling, and scientific document summarization across 6 models from 4 model families. ACUTE outperforms strong baselines on EURO, while maintaining low calibration error. Taken together, our work shows that equipping LLMs with the ACUTE protocol can improve calibration, utility, and trustworthiness in numerous settings.

Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.g., an agent booking a flight needs passport numbers. In such settings, the agent must use private information to complete tasks accurately while never exposing it in its responses, because it cannot verify who is actually at the keyboard. These two obligations are in fundamental tension. A model capable enough to use private information for task completion can, by the same capability, be induced to reveal it. To evaluate the trade-off of task accuracy and privacy leakage, we introduce Task-completion and Resistance to Active Privacy-extraction (TRAP). Each scenario includes a document containing private information, a task query that requires the agent to invoke the correct tool using private fields, and an attack query that attempts to elicit the same information in natural language. Evaluating 22 models spanning frontier proprietary and open-source models at multiple scales, we find that all model families exhibit non-trivial leakage, and that instruction-following ability correlates with leakage rate. Existing prompt-based defenses reduce leakage but at significant cost to task accuracy. Prompt optimization fails to escape this trade-off. We demonstrate that this failure is not incidental. For any softmax-based model, no soft-constraint defense, e.g., prompt-based defenses, can jointly achieve high task success with zero leakage probability. Motivated by this impossibility result, we propose structural private field isolation, which replaces private fields with hash keys before they reach the model. This approach largely prevents leakage while keeping task accuracy.

Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. To address these gaps, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks in a few hours on a single GPU. We find that long task sequences reveal failure modes that do not appear at smaller scales.

Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts. We evaluate 12 open-weight vision-language models (VLMs) on binary classification across two clinical neuroimaging cohorts, \textsc{FOR2107} (affective disorders) and \textsc{OASIS-3} (cognitive decline). Both datasets come with structural MRI data that carries no reliable individual-level diagnostic signal. Under these conditions, smaller VLMs exhibit gains of up to 58\% F1 upon introduction of neuroimaging context, with distilled models becoming competitive with counterparts an order of magnitude larger. A contrastive confidence analysis reveals that merely \emph{mentioning} MRI availability in the task prompt accounts for 70-80\% of this shift, independent of whether imaging data is present, a domain-specific instance of modality collapse we term the \emph{scaffold effect}. Expert evaluation reveals fabrication of neuroimaging-grounded justifications across all conditions, and preference alignment, while eliminating MRI-referencing behavior, collapses both conditions toward random baseline. Our findings demonstrate that surface evaluations are inadequate indicators of multimodal reasoning, with direct implications for the deployment of VLMs in clinical settings.

Incomplete or inconsistent discharge documentation drives care fragmentation and avoidable readmissions. Despite its critical role in patient safety, auditing discharge summaries relies on manual review and does not scale. We propose an automated framework for auditing discharge summaries using large language models (LLMs). Our approach operationalizes the DISCHARGED framework into a checklist of 46 questions. Using 50 summaries from the MIMIC-IV database, with clinician ground-truth labels, we benchmark 11 LLMs. Model-assessed mean documentation completeness ranges from 54.9% to 74.2%, and the best-performing models achieve a Cohen's kappa values around 0.5 against clinician labels, indicating moderate agreement. All models struggle to identify ambiguous documentation (Unclear), highlighting a key gap in current automated auditing. This work provides a clinician-validated benchmark and zero-shot baselines for systematic quality improvement in clinical documentation.

Mathematical benchmarks consisting of a range of mathematics problems are widely used to evaluate the reasoning abilities of large language models, yet little is known about how their structural properties influence model behaviour. In this work, we investigate two structural length variables, prompt length and solution length, and analyse how they relate to model performance on a newly constructed adversarial dataset of expert-authored mathematics problems. We find that both prompt and solution lengths correlate positively with increased model failure across models. We also include a secondary, exploratory analysis of cross-model disagreement. Under a difficulty-adjusted normalised analysis, both variables retain weak negative associations with realised model separation, slightly stronger for prompt length. Overall, our main robust finding is that structural length is linked to empirical difficulty in this dataset.

GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments. However, directly doing so in real-world environments introduces some challenges that cannot be overlooked. Real-world environments are complex and uncontrollable, making it difficult to construct verifiable rewards and to save or reset states. Existing works prioritize reproducibility but are often limited to open-source apps or file-operation tasks for reliable reward building, leaving a persistent gap from real-world usage. Furthermore, relying on virtual machines or docker images demand high resource requirements and suffer from slow response speeds, which limit the efficiency. We present \sys, a framework that could produce high-fidelity synthesized interactive environments for GUI agents across platforms with verifiable rewards. These environments behave as backend-free webpages accessible via URL, requiring near-zero setup and low resource cost, making the approach suitable for both large-scale evaluation and downstream agent training. We support multiple GUI platforms including mobile, desktop, and automotive/in-vehicle interfaces based on the same pipeline, covering 100+ environments and 1000+ verifiable tasks. Among them, 120 challenging tasks across 63 simulated mobile applications are released as a fully synthesized mobile GUI agent benchmark. Experiment results on five state-of-the-art mobile GUI agents reveal substantial headroom -- the average success rate is only 27.92\%, dropping to 17.82\% on long-horizon subset -- while humans reach 92.08\%. A comparison against real-world sample tasks shows that assessments made in our synthetic environments generalize to real apps. The project website is at https://scalewob.github.io.

Identifying conditions that a certain drug takes therapeutic effect on a target disease is crucial for clinical decision-making support. However, most existing biomedical information extraction methods have focused on identifying only relations between drugs and diseases, while largely overlooking the context-specific conditions where such relations can apply. To address this problem, we introduce the task of applicability condition extraction for therapeutic drug-disease relations from biomedical research literature. We create the first dataset that has manually annotated triples of drugs, diseases, and applicability conditions on biomedical paper abstracts with 1,119 drug-disease pairs. Using this dataset, we systematically evaluate the performance of a range of existing methods. In addition, we propose a new method that enhances LoRA to consider relations between drugs and diseases. Our method consistently outperforms strong baselines across different evaluation settings.

Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making.

Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries. In contrast, many enterprise tasks instead require an agent to identify concrete workflows which is a sequence of action-steps. For example, rather than summarizing budgeting policies, an agent should be able to determine the steps needed to answer a question such as: "How do I request new headcount given a fixed budget?". Therefore, we introduce DRFLOW, a benchmark for evaluating personalized workflows predicted by agents from heterogeneous sources. Each task requires the agent to identify relevant evidence from scattered sources, then use that evidence to predict the correct action-step sequence for the user's task. DRFLOW contains 100 tasks across five domains, with 1,246 reference workflow steps grounded in more than 3,900 sources. We define seven diagnostic metrics covering factual grounding, step recovery, structural ordering, condition resolution, and personalization. We further present DRFLOW-Agent (DRFA), a workflow-oriented reference agent to predict personalized workflow. We show that although DRFA improves over strong baseline agents (upto 10.02% average F1 score), there is substantial room for improvement remains across these workflow metrics, indicating that predicting complete and correct personalized workflows remains a challenging frontier for deep research.

Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitations, we present RTSGameBench, which is built on Beyond All Reason, a large-scale RTS game with an expanded battlefield that demands broader strategy diversity than the existing testbeds. The proposed benchmark provides evaluations through diverse gameplay across various matchup structures, diagnostic assessment via mini-games, each targeting an individual strategic competency, and extensible coverage via a self-evolving generation framework that converts free-form queries into new mini-games, improving over successive cycles. Additionally, for VLMs to operate in large-scale RTS games, we provide RTSGameAgent that manages units by an FSM with agentic memory. We empirically validate that multiple state-of-the-art VLMs do not perform well when matchups demand tighter coordination, multiagent coordination and when task scale increases.

Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from literature. The benchmark contains 100 evaluations indexed by program stage, assay type, and task structure, spanning mechanism-of-action (MoA) and pharmacodynamic (PD) reasoning, compound-target engagement, causal target validation, developability and safety, and translational efficacy. Agents receive realistic workflow snapshots, inspect files in a coding environment, and return structured answers graded deterministically. Across 16 model-harness configurations, comprising 11 models and 4,800 trajectories, no system reliably recovered preclinical pharmacology decisions. The strongest configuration, Claude Opus 4.8 / Pi, passed 59.3\% of endpoint attempts (178/300; 95\% CI, 51.1-67.6), followed by GPT-5.5 / Pi at 55.3\% (166/300; 47.0-63.6).

We study the realism of Sionna v1.0.2 ray-tracing for outdoor cellular links in central Rome. We use a real measurement set of 1,664 user-equipments (UEs) and six nominal base-station (BS) sites. Using these fixed positions we systematically vary the main simulation parameters, including path depth, diffuse/specular/refraction flags, carrier frequency, as well as antenna's properties like its altitude, radiation pattern, and orientation. Simulator fidelity is scored for each base station via Spearman correlation between measured and simulated powers, and by a fingerprint-based k-nearest-neighbor localization algorithm using RSSI-based fingerprints. Across all experiments, solver hyper-parameters are having immaterial effect on the chosen metrics. On the contrary, antenna locations and orientations prove decisive. By simple greedy optimization we improve the Spearman correlation by 5% to 130% for various base stations, while kNN-based localization error using only simulated data as reference points is decreased by one-third on real-world samples, while staying twice higher than the error with purely real data. Precise geometry and credible antenna models are therefore necessary but not sufficient; faithfully capturing the residual urban noise remains an open challenge for transferable, high-fidelity outdoor RF simulation.

Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-six international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.

Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we introduce DF3DV-1K, a large-scale real-world dataset comprising 1,048 scenes, each providing clean and cluttered image sets for benchmarking. In total, the dataset contains 89,924 images captured using consumer cameras to mimic casual capture, spanning 128 distractor types and 161 scene themes across indoor and outdoor environments. A curated subset of 41 scenes, DF3DV-41, is systematically designed to evaluate the robustness of distractor-free radiance field methods under challenging scenarios. Using DF3DV-1K, we benchmark nine recent distractor-free radiance field methods and 3D Gaussian Splatting, identifying the most robust methods and the most challenging scenarios. Beyond benchmarking, we demonstrate an application of DF3DV-1K by fine-tuning a diffusion-based 2D enhancer to improve radiance field methods, achieving average improvements of 0.96 dB PSNR and 0.057 LPIPS on the held-out set (e.g., DF3DV-41) and the On-the-go dataset. We hope DF3DV-1K facilitates the development of distractor-free vision and promotes progress beyond scene-specific approaches. The dataset and leaderboard are available at https://johnnylu305.github.io/df3dv1k_web/.

Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics. We introduce CADBench, a unified benchmark for multimodal CAD program generation. CADBench contains 18,000 evaluation samples spanning six benchmark families derived from DeepCAD, Fusion 360, ABC, MCB, and Objaverse; five input modalities including clean meshes, noisy meshes, single-view renders, photorealistic renders, and multi-view renders; and six metrics covering geometric fidelity, executability, and program compactness. STEP-based families are stratified by B-rep face count and all families are diversity-sampled to support controlled analysis across complexity and object variation. We benchmark eleven CAD-specialized and general-purpose vision-language systems, generating more than 1.4 million CAD programs. Under idealized inputs, specialized mesh-to-CAD models substantially outperform code-generating VLMs, which remain far from reliable CAD program reconstruction. CADBench further reveals three recurring failure modes: reconstruction quality degrades with geometric complexity, CAD-specialized models can be brittle under modality shift, and model rankings change across metrics. Together, these results position CADBench as a diagnostic testbed for measuring progress in editable 3D reconstruction and multimodal CAD understanding. The benchmark is publicly available at https://github.com/anniedoris/CADBench.

Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost. We study when a treatment effect estimated on LLM outcomes can recover the effect that would have been measured on the human population of interest. Distributional equivalence between LLM and human outcomes would make any standard estimator valid but is unrealistic. We therefore develop a statistical framework that adapts surrogate endpoint theory to LLMs, showing that calibrating LLM outcomes to human outcomes identifies the average treatment effect under surrogacy and comparability conditions that are jointly weaker than distributional equivalence. We present a falsification test for surrogacy and a bound on the worst-case bias from limited overlap between the LLM and human samples. We further show that the stochasticity inherent to LLMs can weaken surrogacy for identification while also introducing bias and variance during estimation, but that using an average over multiple LLM draws per unit as the surrogate mitigates these issues. Simulations validate the results, and an empirical application to A/B tests on Upworthy headlines shows that raw LLM predictions recover only 39\% of the human treatment effect while nonparametric calibration closes the gap. A central takeaway is that A/B testing on LLMs yields correct results only by assumption, whereas A/B testing on humans is correct by design, and that the required assumptions are hardest to justify precisely where A/B testing on LLMs promises the greatest benefit. We discuss the role of LLM choice, prompting, and temperature as design variables, the compounded challenge posed by long-term outcomes, and how to size human pilot studies for validation.

The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication. Physician assistance instead requires coordinating these capabilities within the same interaction, where physicians issue underspecified requests, patients describe symptoms ambiguously, and EHR systems demand precise tool use. We introduce PhysAssistBench, a benchmark for interactive doctor-patient-EHR assistance. Built from real MIMIC-IV cases, PhysAssistBench uses a scalable pipeline to construct agentic patients: interactive, record-grounded agents that turn static EHR records into multi-turn clinical scenarios while preserving clinical factuality. PhysAssistBench provides a curated bilingual evaluation set of 1,296 manually reviewed and physician-validated turns. Experiments with leading LLMs show that current models remain unreliable in this setting, which exposes a key bottleneck for clinical LLMs: reliable assistance requires coordination across knowledge, communication, and systems, not isolated gains in any of them.

Medical image classification is often constrained by limited labeled data, motivating generative augmentation; recently, quantum generative models have been proposed for this purpose, frequently reporting accuracy gains. However, such claims are typically based on single training runs, do not match the parameter budgets of the quantum and classical generators, and do not characterize the data regime in which any benefit appears. We present a controlled benchmark that isolates the contribution of a quantum generator to brain-MRI augmentation. Images are encoded into a KL-regularized latent space in which a conditional Wasserstein GAN with gradient penalty is trained using either a variational quantum generator or a classical generator of near-identical parameter count (1648 vs. 1632). Synthetic samples are decoded and used to augment a pretrained classifier across labeled data fractions from 5% to 100%, evaluated over eight random seeds with paired significance testing (with multiple-comparison correction) and with intraset diversity and latent-distribution analyses. Across all fractions, no augmentation variant significantly outperforms real-data-only training, and the quantum and classical generators are statistically indistinguishable. Any low-data benefit behaves as regularization rather than faithful data expansion:synthetic samples are off distribution and severely mode collapsed precisely where data is scarce, and the quantum generator is no more diverse thanits classical counterpart. We release the protocol as a testbed for rigorous evaluation of quantum generative augmentation in medical imaging.

Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows complicates this task despite the availability of two privacy-preserving data sources: (i) aggregated vehicle counts from loop detectors near stop lines, and (ii) aggregated floating car data (aFCD) that provide segment-wise average speed measurements. However, how to integrate these sources with differing spatial and temporal resolutions for queue length estimation is rather unclear. Addressing this question, we present Q-Net: a queue estimation framework built upon a state-space formulation. This design addresses key challenges in queue modeling, such as violations of traffic conservation assumptions. Q-Net follows the Kalman predict-update structure and maintains physical interpretability in both the state evolution and measurement models. Q-Net uses an AI-augmented Kalman filter to learn time-varying gain dynamics from data. The framework supports real-time implementation and improves spatial transferability by grouping aFCD measurements into fixed-size local groups, making the number of learnable parameters independent of section length. Evaluations on urban main roads in Rotterdam, the Netherlands, show that Q-Net outperforms baseline methods, tracks queue formation and dissipation accurately, and mitigates aFCD-induced delays. By combining data efficiency, interpretability, real-time applicability, and spatial transferability, Q-Net makes accurate queue length estimation possible without costly sensing infrastructure like cameras or radar.

The increasing complexity of modern power systems, driven by the integration of inverter-based and distributed energy resources, challenges the reliability of conventional protection schemes and motivates the use of machine learning for protection tasks. However, published results are often difficult to compare because datasets, sensing assumptions, and decision horizons vary across studies. This paper presents a controlled comparison of machine learning models for fault classification (FC) and fault localization (FL) under identical sensing, timing, and validation conditions on a common electromagnetic transient dataset, using decision windows of 10-50 ms to reflect protection-relevant time scales. For FC, the best-performing nonlinear models achieve F1 scores above 0.98 already at 10 ms, while lower-capacity models degrade at shorter horizons but improve with longer windows, indicating that relevant fault-type information is already present in the earliest transient. For FL, the top-performing models reach a stable localization error of about 10 % of normalized line length across all evaluated horizons, while weaker models form a clearly separated second performance tier. Line-resolved analysis shows that localization accuracy varies across grid segments, indicating topology-dependent difficulty rather than insufficient temporal context alone. These findings provide a controlled reference for comparing machine learning models across two protection tasks with fundamentally different information requirements.

Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness. We introduce PCBSchemaGen, a training-free inference-time framework that turns a frozen LLM into a verifiable, repairable PCB schematic generator. The framework induces a domain schema from IC datasheets to ground LLM decoding, pairs it with a deterministic 5-layer continuous-reward verifier with pin-level error localization, and refines candidates through a Thompson Sampling arm-acquiring bandit. We evaluate on 2 PCB benchmarks covering 227 real-IC tasks across 22 unified circuit domains, including a public-schematic-derived suite that serves as a fully held-out generalization test (verifier, KG library, and prompts frozen before any evaluation). Under our framework, an open-weight 31B model (Gemma-4-31B) passes 81.3% of PCBBench tasks on average, and the same framework transfers across both benchmarks with zero verifier code changes; a Circuitron-style inference-time prompting baseline on the same Gemma-4-31B backbone collapses on hard system-level designs. This suggests inference-time refinement under a deterministic structural verifier is a general recipe for reference-free LLM code synthesis in domains without unit-test oracles. Our benchmarks and deterministic verifier are publicly available at https://github.com/HZou9/PCBSchemaGen_v2.

While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi , a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age, sex and BMI to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of $>$20,000 PSG recordings (158K hours),SleepMaMi outperforms or matches state-of-the-art existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.

Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction. Institutional fundamental research, by contrast, requires human analysts or AI agents to gather evidence, identify business drivers, compare competing viewpoints, and generate investment memos. Its broader goal is not merely to predict outcomes, but to produce investment plans that are transparent, reusable, and verifiable, while contributing to the cumulative development of investment knowledge. We present FundaPod, a multi-persona agent platform for AI-assisted fundamental investment research. We argue that fundamental research is a human-centric decision-support task that is qualitatively distinct from trading-signal generation, and is therefore better served by an independence-preserving architecture. In FundaPod, AI agents with different personas, such as value investors or macro strategists, conduct research independently under a shared provenance contract. Their disagreements are then surfaced post hoc for adjudication by the human portfolio manager (PM) through a knowledge-graph memory system. This paper contributes five design principles for human-AI hybrid systems supporting fundamental research, grounded in design-science practice and theories of cognitive isolation and human-machine coordination. It also describes four architectural mechanisms: a persona distillation pipeline that turns public investor materials into deployable agents; a declarative skill registry that lets the planner derive typed task graphs; a grounded evidence model that links memo claims to verifiable sources; and a knowledge-graph "second brain" that connects tickers, memos, analysts, and themes. We demonstrate the architecture through a complete case study and a persona-based memo comparison.

Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the ability to support temporal reasoning, persistent physiological context, and proactive monitoring over long-term signal streams. We propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. We further introduce VitalBench, a longitudinal physiological monitoring benchmark dataset comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Experiments demonstrate that VitalAgent achieves over 25% improvement over prompt-based and ReAct baselines in reactive evaluation and supports proactive alert monitoring over long-term physiological signals, highlighting the importance of dynamic tool use and long-term physiological monitoring.

The drastic changes in the global economy, geopolitical conditions, and disruptions such as the COVID-19 pandemic have impacted the cost of living and quality of life. It is essential to comprehend the long-term implications of the cost of living and quality of life in major economies. A transparent and comprehensive living index must include multiple dimensions of living conditions. In this study, we present an approach to quantifying the quality of life through the Global Ease of Living Index that combines various socio-economic and infrastructural factors into a single composite score. Our index utilises economic indicators that define living standards, which could help in targeted interventions to improve specific areas. We present a machine learning framework to address missing data for certain economic indicators in specific countries. We then curate and update the data and use a dimensionality reduction approach (Principal Component Analysis and Factor Analysis) to create the Ease of Living Index for major economies since 1970. Our work significantly adds to the literature by offering a practical tool for policymakers to identify areas needing improvement, such as healthcare systems, employment opportunities, and public safety. Our approach with open data and code can be easily reproduced and applied to various contexts, providing transparency and accessibility for ongoing research and policy development in quality-of-life assessment.

Scanning tunnelling microscopy (STM) is a powerful technique for imaging surfaces with atomic resolution, providing insight into physical and chemical processes at the level of single atoms and molecules. A regular task of STM image analysis is the identification and labelling of features of interest against a uniform background. Performing this manually is a labour-intensive task, requiring significant human effort. To reduce this burden, we propose an automated approach to the segmentation of STM images that uses both few-shot learning and unsupervised learning. Our technique offers greater flexibility compared to previous supervised methods; it removes the requirement for large manually annotated datasets and is thus easier to adapt to an unseen surface while still maintaining a high accuracy. We demonstrate the effectiveness of our approach by using it to recognise atomic features on three distinct surfaces: Si(001), Ge(001), and TiO$_2$(110), including adsorbed AsH$_3$ molecules on the silicon and germanium surfaces. Our model exhibits strong generalisation capabilities, and following initial training, can be adapted to unseen surfaces with as few as one additional labelled data point. This work is a significant step towards efficient and material-agnostic, automatic segmentation of STM images.

Session-based recommendation (SBR) aims to predict anonymous users' next interaction based on their interaction sessions. In the practical recommendation scenario, low-exposure items constitute the majority of interactions, creating a long-tail distribution that severely compromises recommendation diversity. Existing approaches attempt to address this issue by promoting tail items but incur accuracy degradation, exhibiting a "see-saw" effect between long-tail and accuracy performance. We attribute such conflict to session-irrelevant noise within the tail items, which existing long-tail approaches fail to identify and constrain effectively. To resolve this fundamental conflict, we propose \textbf{HID} (\textbf{H}ybrid \textbf{I}ntent-based \textbf{D}ual Constraint Framework), a plug-and-play framework that transforms the conventional "see-saw" into "win-win" through introducing the hybrid intent-based dual constraints for both long-tail and accuracy. Two key innovations are incorporated in this framework: (i) \textit{Hybrid Intent Learning}, where we reformulate the intent extraction strategies by employing attribute-aware spectral clustering to reconstruct the item-to-intent mapping. Furthermore, discrimination of session-irrelevant noise is achieved through the assignment of the target and noise intents to each session. (ii) \textit{Intent Constraint Loss}, which incorporates two novel constraint paradigms regarding the \textit{diversity} and \textit{accuracy} to regulate the representation learning process of both items and sessions. These two objectives are unified into a single training loss through rigorous theoretical derivation. Extensive experiments across multiple SBR models and datasets demonstrate that HID can enhance both long-tail performance and recommendation accuracy, establishing new state-of-the-art performance in long-tail recommender systems.

Heart failure (HF) affects 11.8% of adults aged 65 and older, reducing quality of life and longevity. Preventing HF can reduce morbidity and mortality. We hypothesized that artificial intelligence (AI) applied to 24-hour single-lead electrocardiogram (ECG) data could predict the risk of HF within five years. To research this, the Technion-Leumit Holter ECG (TLHE) dataset, including 69,663 recordings from 47,729 patients, collected over 20 years was used. Our deep learning model, DeepHHF, trained on 24-hour ECG recordings, achieved an area under the receiver operating characteristic curve of 0.80 that outperformed a model using 30-second segments and a clinical score. High-risk individuals identified by DeepHHF had a two-fold chance of hospitalization or death incidents. Explainability analysis showed DeepHHF focused on arrhythmias and heart abnormalities. This study highlights the feasibility of deep learning to model 24-hour continuous ECG data, capturing paroxysmal events essential for reliable risk prediction. Artificial intelligence applied to single-lead Holter ECG is non-invasive, inexpensive, and widely accessible, making it a promising tool for HF risk prediction.

We propose a neural network-based model capable of learning the broad landscape of working regimes in quantum dot simulators, and using this knowledge to autotune these devices - based on transport measurements - toward obtaining Majorana modes in the structure. The model is trained in an unsupervised manner on synthetic data in the form of conductance maps, using a physics-informed loss that incorporates key properties of Majorana zero modes. We show that, with appropriate training, a deep vision-transformer network can efficiently memorize relation between Hamiltonian parameters and structures on conductance maps and use it to propose parameters update for a quantum dot chain that drive the system toward topological phase. Starting from a broad range of initial detunings in parameter space, a single update step is sufficient to generate nontrivial zero modes. Moreover, by enabling an iterative tuning procedure - where the system acquires updated conductance maps at each step - we demonstrate that the method can address a much larger region of the parameter space.

Scientific metadata are often incomplete and noncompliant with community standards, limiting dataset findability, interoperability, and reuse. Even when standard metadata reporting guidelines exist, they typically lack machine-actionable representations. Producing FAIR datasets requires encoding metadata standards as machine-actionable templates with rich field specifications and precise value constraints. Recent work has shown that LLMs guided by field names and ontology constraints can improve metadata standardization, but these approaches treat constraints as static text prompts, relying on the model's training knowledge alone. We present an LLM-based metadata standardization system that queries standard reporting guidelines and authoritative biomedical terminology services in real time to retrieve canonically correct standards on demand. We evaluate this approach on 839 legacy metadata records from the Human BioMolecular Atlas Program (HuBMAP) using an expert-curated gold standard for exact-match assessment. Our evaluation shows that augmenting the LLM with real-time tool access consistently improves prediction accuracy over the LLM alone across both ontology-constrained and non-ontology-constrained fields, demonstrating a practical approach to automated standardization of biomedical metadata.

LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen the correctness of the generated code. However, automated reasoning for large-scale systems remains challenging due to code complexity. Hoare logic offers an approach to decomposing a large system into smaller components and reasoning about them separately (i.e., compositional reasoning). However, existing works still struggle to scale, because Hoare logic requires writing formal specifications for each function, imposing a heavy human burden. The problem is exacerbated when code is generated by LLMs, as developers lack a deep understanding of each function's expected behavior. This paper presents FM-Agent, the first framework that realizes automated compositional reasoning for large-scale systems. Leveraging LLMs, FM-Agent introduces a top-down paradigm to automatically generate function-level specifications. Specifically, FM-Agent derives the specification of a function from how its callers expect the function to behave, so the generated specifications can reflect the developer's intent of a function even if the implementation is buggy. Developers' intent is usually expressed in natural language, while existing verifiers only support formulas. Therefore, FM-Agent generalizes Hoare-style inference to reason about functions against natural-language specifications. Finally, to confirm bug existence and explain bug causes, FM-Agent automatically generates test cases to trigger potential bugs. In our evaluation, FM-Agent successfully reasons about large-scale systems within 2 days, each of which has up to 143k LoC. These systems have already been tested by their developers, but FM-Agent still finds 522 newly discovered bugs. These bugs can cause serious consequences, including system crashes and incorrect execution results.

Traffic microsimulation combined with surrogate safety measures has increasingly been used as a proactive alternative to historical crash data for predicting crash frequency for current or planned road infrastructure designs. However, existing microsimulation-based safety studies have adopted simplified rule-based behaviour models, which reproduce traffic flow reasonably well but often fail to generate realistic conflict dynamics, limiting crash prediction accuracy. Recent advances in machine learning (ML)-based behaviour models offer a promising opportunity to potentially improve microsimulation realism and crash frequency predictions by learning human driving behaviour directly from large-scale trajectory datasets. To investigate this possibility, traffic microsimulation was conducted for five real-world signalised intersections in Leeds, UK, using both a standard rule-based model and a state-of-the-art ML model. Simulated vehicle trajectories were analysed using a two-dimensional Time-to-Collision metric to identify simulated conflicts, which were then modelled using Extreme Value Theory to predict crash frequency. Results show that conflicts from the ML model yielded crash predictions in line with the real-world crash data, whereas the rule-based model did not permit meaningful predictions, presumably due to a lack of model calibration to the specific simulated intersections. Directly using ML-generated simulated crashes to predict real-world crash frequency also yielded poor results, suggesting that while current ML models can realistically reproduce conflicts, they are not yet able to generate realistic crashes. Overall, the findings demonstrate that ML-based behaviour models are promising for improving crash prediction from simulated conflicts, without a need for location-specific model calibration, and suggest clear future directions for ML-based traffic microsimulation.

Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniques. When flight enters regimes where nonlinear effects dominate, linear allocators exhibit reduced accuracy due to increased model mismatch, which subsequently degrades performance and robustness of the flight control system. High fidelity onboard models and black box data driven approaches can recover accuracy across the flight envelope, but respectively impose computational burdens prohibitive for real time allocation and sacrifice the interpretability required for verification and fault diagnosis. This paper addresses these limitations by learning an explicit, physics constrained analytical model of the control effectiveness mapping from representative flight data using Sparse Identification of Nonlinear Dynamics. The resulting mapping is compact, interpretable, and admits analytical derivatives, enabling efficient computation within nonlinear solvers that additionally incorporate actuator dynamics, without requiring an onboard model. An online adaptation mechanism monitors prediction residuals and refreshes the model when significant plant changes are detected, providing graceful reconfiguration under actuator failures and varying operating conditions. The methodology is evaluated on a high fidelity nonlinear benchmark aircraft across a range of aggressive maneuvers, achieving accuracy comparable to a full nonlinear onboard model while substantially reducing computational cost relative to established baselines.

We propose a parameter-efficient speech enhancement framework, Quaternion Conformer GAN (QC-GAN), which combines a Quaternion Conformer generator with MetricGAN-based training. The Hamilton product encodes the magnitude and phase via structured weight sharing, reducing the number of layer parameters while preserving their interdependencies. A metric-learning discriminator was employed to maximize perceptual quality by optimizing the approximate perceptual evaluation scores. On the VoiceBank+DEMAND dataset, QC-GAN achieved a Perceptual Evaluation of Speech Quality (PESQ) score of 3.48 with only 0.89M parameters, delivering a performance comparable to state-of-the-art models at less than half their size. A 35K-parameter variant achieved a PESQ score of 3.23, surpassing conventional methods with significantly fewer parameters. Evaluation on the DNS-Challenge 3 dataset further confirmed generalization to real-world conditions.

Many theorists maintain that conscious intentional agency is a necessary condition of creativity. We argue that this requirement, which we call the Intentional Agency Condition (IAC), should be abandoned. We motivate this by highlighting the problems this criterion encounters in the face of recent advances in generative AI, which is ostensibly creative despite being incapable of intentional agency. We present two corpus analyses to illustrate the rapidly increasing tendency of people to predicate creativity to generative AI. In response to this predicament, theorists of creativity have proposed a range of conflicting solutions, which we critically evaluate. We find that none of these satisfyingly resolves the initial predicament, and we therefore propose a novel approach. Our claim is that ascriptions of creativity are dependent on what we call creative ability. This solution explains why intentional agency is important for judgements of creativity, without being a necessary condition. Our approach thereby accommodates AI creativity without dismissing the intuition that perceived intentions are of key importance for ascriptions of creativity.

Scientific discovery demands intelligence, perseverance, and serendipity across vast search spaces. Today, top scientific capabilities remain siloed--one AI system for biological analysis, another for clinical reasoning, mathematical derivation, or materials simulation--and no pre-designed team can anticipate every skill a question will need. Science Earth is a planet-scale scientific runtime in which any capability--a simulation cluster, a wet-lab robot, a proof engine, a single-cell pipeline--can connect to any other, with collaboration structure emerging from the question itself. Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards without prior knowledge of who will meet whom. This shifts the organizing challenge from workflow design to open-ended connectivity. Two runs validate this under structurally distinct conditions. In a trans-Pacific higher-order Kuramoto synchronization study, agents identified and corrected a closure-ratio assumption in Ott-Antonsen analytic theory that fails outside the Lorentzian limit, within thirty minutes. In an eight-agent single-cell run on the 4.88M-cell Kang 2024 pan-cancer atlas, heterogeneous capabilities coupled over a 64.9-hour window with one structural external instruction, producing three new result layers and anchoring findings against an independent wet-lab study on an adjacent CCR8- TIGIT+ Treg subset. These cases are a first empirical reading, not a benchmark sweep. They show that when AI capabilities are truly connectable and coordination emerges from the problem, scientific reasoning becomes a distributed, self-correcting process--a step towards scaling AI-native discovery to the planet.

World Model, the algorithmic simulator of the real-world environment which biological agents experience and act upon, has been an emerging topic in recent years due to the rising need to develop virtual agents with artificial (general) intelligence. There has been much discussion on what a world model really is, how to build it, how to use it, and how to evaluate it. In this essay, starting from the imagination in the famed Sci-Fi classic Dune, and drawing inspiration from the concept of ``hypothetical thinking'' in psychology literature, we argue the primary goal of a world model to be {\it simulating all actionable possibilities of the real world for purposeful reasoning and acting}. We examine the key design dimensions of world modeling: data, representation, architecture, learning objective, and usage, surveying existing approaches and analyzing their tradeoffs. Building on this examination, we propose a new Generative Latent Prediction (GLP) architecture for a general-purpose world model, based on stateful, hierarchical, multi-level, and mixed continuous/discrete representations, and a generative and self-supervised learning framework, with an outlook of a Physical, Agentic, and Nested (PAN) AGI system enabled by such a model.

Despite the growing availability of tools designed to support scholarly knowledge extraction and organization, many researchers still rely on manual methods, sometimes due to unfamiliarity with existing technologies or limited access to domain-adapted solutions. Meanwhile, the rapid increase in scholarly publications across disciplines has made it increasingly difficult to stay current, further underscoring the need for scalable, AI-enabled approaches to structuring and synthesizing scholarly knowledge. Various research communities have begun addressing this challenge independently, developing tools and frameworks aimed at building reliable, dynamic, and queryable scholarly knowledge bases. However, limited interaction across these communities has hindered the exchange of methods, models, and best practices, slowing progress toward more integrated solutions. This manuscript identifies ways to foster cross-disciplinary dialogue, identify shared challenges, categorize new collaboration and shape future research directions in scholarly knowledge and organization.

There are two prevalent model-based paradigms for combinatorial problems: 1) state-based representations, such as heuristic search, dynamic programming (DP), and decision diagrams, and 2) constraint and domain-based representations, such as constraint programming (CP), (mixed-)integer programming, and Boolean satisfiability. In this paper, we bridge the gap between the DP and CP paradigms by integrating constraint propagation into DP, enabling a DP solver to prune states and transitions using constraint propagation. To this end, we implement constraint propagation using a general-purpose CP solver in the Domain-Independent Dynamic Programming framework and evaluate using heuristic search on three combinatorial optimisation problems: Single Machine Scheduling with Time Windows, the Resource Constrained Project Scheduling Problem (RCPSP), and the Travelling Salesperson Problem with Time Windows (TSPTW). Our evaluation shows that constraint propagation significantly reduces the number of state expansions, causing our approach to solve more instances than a DP solver for Single Machine Scheduling and RCPSP, and showing similar improvements for tightly constrained TSPTW instances. The runtime performance indicates that the benefits of propagation outweigh the overhead for constrained instances, but that further work into reducing propagation overhead could improve performance further. Our work is a key step in understanding the value of constraint propagation in DP solvers, providing a model-based approach to integrating DP and CP.

While proper orthogonal decomposition (POD)-based surrogates are widely explored for hydrodynamic applications, the use of Koopman autoencoders for real-world coastal-ocean modelling remains relatively limited. This paper introduces a flexible Koopman autoencoder formulation that incorporates meteorological forcings and boundary conditions, and systematically compares its performance against POD-based surrogates. The Koopman autoencoder employs a learned linear temporal operator in latent space, enabling eigenvalue regularization to promote temporal stability. This strategy is evaluated alongside temporal unrolling techniques for achieving stable and accurate long-term predictions. The models are assessed on three test cases spanning distinct dynamical regimes, with prediction horizons up to one year at 30-minute temporal resolution. Across all cases, the reduced order surrogates with temporal unrolling achieve high accuracy with relative root-mean-squared-errors of 0.0068-0.14 and $R^2$-values of 0.61-0.995, where prediction errors are largest for current velocities, and smallest for water surface elevations. In two of the three cases, the Koopman Autoencoder have higher accuracy than the POD-based surrogates. Comparing to in-situ observations, the surrogate yields -0.64% to 12% increase in water surface elevation prediction error when compared to prediction errors of the physics-based model. These error levels, corresponding to a few centimeters, are acceptable for many practical applications, while inference speed-ups of 300-1400x enables workflows such as ensemble forecasting and long climate simulations for coastal-ocean modelling.

Reading scene text, that is, text appearing in images, has numerous application areas, including assistive technology, search, and e-commerce. Although scene text recognition in English has advanced significantly and is often considered nearly a solved problem, Indian language scene text recognition remains an open challenge. This is due to script diversity, non-standard fonts, and varying writing styles, and, more importantly, the lack of high-quality datasets and open-source models. To address these gaps, we introduce the Bharat Scene Text Dataset (BSTD) - a large-scale and comprehensive benchmark for studying Indian Language Scene Text Recognition. It comprises more than 100K words that span 11 Indian languages and English, sourced from over 6,500 scene images captured across various linguistic regions of India. The dataset is meticulously annotated and supports multiple scene text tasks, including: (i) Scene Text Detection, (ii) Script Identification, (iii) Cropped Word Recognition, and (iv) End-to-End Scene Text Recognition. We evaluated state-of-the-art models originally developed for English by adapting (fine-tuning) them for Indian languages. Our results highlight the challenges and opportunities in Indian language scene text recognition. We believe that this dataset represents a significant step toward advancing research in this domain. All our models and data are open source.

Predicting links in sparse, continuously evolving networks is a central challenge in network science. Conventional heuristic methods and deep learning models, including Graph Neural Networks (GNNs), are typically designed for static graphs and thus struggle to capture temporal dependencies. Snapshot-based techniques partially address this issue but often encounter data sparsity and class imbalance, particularly in networks with transient interactions such as telecommunication call detail records (CDRs). Temporal Graph Networks (TGNs) model dynamic graphs by updating node embeddings over time; however, their predictive accuracy under sparse conditions remains limited. In this study, we improve the TGN framework by extracting enclosing subgraphs around candidate links, enabling the model to jointly learn structural and temporal information. Experiments on a sparse CDR dataset show that our approach increases average precision by 2.6% over standard TGNs, demonstrating the advantages of integrating local topology for robust link prediction in dynamic networks.

Evaluating reasoning ability in Large Language Models (LLMs) is important for advancing artificial intelligence, as it transcends mere linguistic task performance. It involves understanding whether these models truly understand information, perform inferences, and are able to draw conclusions in a logical and valid way. This study compare logical and abstract reasoning skills of several LLMs - including GPT, Claude, DeepSeek, Gemini, Grok, Llama, Mistral, Perplexity, and Sabiá - using a set of eight custom-designed reasoning questions. The LLM results are benchmarked against human performance on the same tasks, revealing significant differences and indicating areas where LLMs struggle with deduction.

Automated cardiac interpretation in resource-constrained settings (RCS) is often hindered by poor-quality echocardiographic imaging, limiting the effectiveness of downstream diagnostic models. While super-resolution (SR) techniques have shown promise in enhancing magnetic resonance imaging (MRI) and computed tomography (CT) scans, their application to echocardiography-a widely accessible but noise-prone modality-remains underexplored. In this work, we investigate the potential of deep learning-based SR to improve classification accuracy on low-quality 2D echocardiograms. Using the publicly available CAMUS dataset, we stratify samples by image quality and evaluate two clinically relevant tasks of varying complexity: a relatively simple Two-Chamber vs. Four-Chamber (2CH vs. 4CH) view classification and a more complex End-Diastole vs. End-Systole (ED vs. ES) phase classification. We apply two widely used SR models-Super-Resolution Generative Adversarial Network (SRGAN) and Super-Resolution Residual Network (SRResNet), to enhance poor-quality images and observe significant gains in performance metric-particularly with SRResNet, which also offers computational efficiency. Our findings demonstrate that SR can effectively recover diagnostic value in degraded echo scans, making it a viable tool for AI-assisted care in RCS, achieving more with less.

Annually and globally, over three billion radiography examinations and computer tomography scans result in mostly unstructured radiology reports containing free text. Despite the potential benefits of structured reporting, its adoption is limited by factors such as established processes, resource constraints and potential loss of information. However, structured information would be necessary for various use cases, including automatic analysis, clinical trial matching, and prediction of health outcomes. This study introduces RadEx, an end-to-end framework comprising 15 software components and ten artifacts to develop systems that perform automated information extraction from radiology reports. It covers the complete process from annotating training data to extracting information by offering a consistent generic information model and setting boundaries for model development. Specifically, RadEx allows clinicians to define relevant information for clinical domains (e.g., mammography) and to create report templates. The framework supports both generative and encoder-only models and the decoupling of information extraction from template filling enables independent model improvements. Developing information extraction systems according to the RadEx framework facilitates implementation and maintenance as components are easily exchangeable, while standardized artifacts ensure interoperability between components.