mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 23 Sep 2026

460 papers

  1. PRIME: Frequency-Aware Unified Pruning and Merging for MoE CompressionMixture-of-experts → MoE large language models
  2. Route-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  3. Taming an End-to-End Autonomous Driving Policy for Urban Navigation of Quadruped RobotsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  4. KVFetch: Temporal Prefetching for the Missing Half of KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  5. Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language ModelsRetrieval-augmented generation → Generation and context integration
  6. EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress UnderstandingLLM reasoning → Spatial and embodied reasoning +1
  7. The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  8. VisionPsy-Nano: Improving Accuracy, Efficiency, and Reliability in On-Device Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  9. PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic ModelDiffusion models → Inverse problems and image restoration
  10. When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to GuessLLM agents and tool use → Software engineering coding agents
  11. Guarded Gradient-Based Activation Steering of Shutdown Responses in Qwen3.5-0.8B: A Minimum-Step PolicyMechanistic interpretability → Activation steering methods
  12. MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text SpottingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  13. Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context GroundingLLM agents and tool use → Social simulation and multi-agent debate
  14. Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language ReasoningLLM reasoning → Multimodal reasoning +1
  15. RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?LLM agents and tool use → Web, search, and research agents
  16. LastOPD: Taming Collapse in Latent On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  17. Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity ApplicationsLLM agents and tool use → Agent threats, guardrails and governance
  18. Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action PolicyVision-language-action models → Reinforcement learning and post-training +2
  19. CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  20. Signals of AI Hallucination: Designing Hallucination-Aware Cues for Embodied Conversational Agents in VRLLM agents and tool use → Multimodal and embodied agents
  21. DeltaWAM: Delta World Action Models for Bimanual ManipulationWorld models → Embodied and robot world models
  22. Stream Recursion Model (SRM)Mechanistic interpretability → Knowledge and representations inside LLMs
  23. An Analysis of Streaming Deep Reinforcement Learning for Adaptive Continual Learning in RoboticsDeep reinforcement learning methods → Deep RL algorithms and representations
  24. OCC4M: Object-Centric 4D Memory for Spatiotemporal Reasoning in Long-Horizon ManipulationLLM reasoning → Spatial and embodied reasoning
  25. DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait AnalysisLLM reasoning → Spatial and embodied reasoning
  26. Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language ModelsKnowledge distillation → Speech and audio distillation
  27. Agent Memory with Episodic Retrieval for Financial Decision-MakingLLM agents and tool use → Financial trading and forecasting agents
  28. BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild ChallengeState-space sequence models (S4, Mamba) → Speech and audio SSMs
  29. Small yet Assistive: Spatially-Aware Post-Training for Low VisionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  30. Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  31. Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability DeliveryLLM agents and tool use → Agent skill learning and evolution
  32. Driving Epidemic Models with AI Agents: the Epydemix Agent FrameworkLLM agents and tool use → Medical and scientific domain agents
  33. Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning ModelsLLM reasoning → Causal reasoning in LLMs
  34. Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving TopologiesWorld models → Latent predictive world models
  35. Training Object Permanence in World ModelsWorld models → World models for language agents
  36. The Fellowship of the Query: Learning Retrieval ActionsRetrieval-augmented generation → Agentic RAG, agents and memory
  37. RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theoryLLM reasoning → Reinforcement learning for reasoning
  38. Reward Hacking Challenges Oversight of Autonomous Research AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  39. Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic DecisionsLLM agents and tool use → Agent threats, guardrails and governance +1
  40. Adversarial Closed-Loop Curriculum for Evolving Role-Playing AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  41. OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial RecommenderMixture-of-experts → MoE for recommender systems
  42. Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  43. Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  44. Token Clustering and Semantic Sequence Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  45. Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  46. DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMsLLM reasoning → Hallucination detection and mitigation +1
  47. Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation AgentsLLM agents and tool use → Software engineering coding agents
  48. CARE: Condition-Aware Representation Regularization for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  49. Who Is Behind the Harness? Fingerprinting LLMs through Agentic BehaviorLLM agents and tool use → Agent threats, guardrails and governance
  50. BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data PipelinesLLM agents and tool use → Medical and scientific domain agents
  51. Pistis Technical ReportMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  52. PAWS: Policy-driven Agentic World SimulationLLM agents and tool use → Financial trading and forecasting agents
  53. On the Diffusibility of High-Dimensional LatentsDiffusion models → Diffusion foundations and sampling
  54. The Past Frames the Future: Memory for Autoregressive Video GenerationWorld models → Video-generation world models and simulators
  55. Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic BenchmarkLLM reasoning → Reasoning for agents, planning and code
  56. Order-Invariant Answers, Order-Sensitive Representations in Mathematical ReasoningLLM reasoning → Mathematical reasoning
  57. Agent-Editing World Model: Rethinking World Modeling for LLM AgentsWorld models → World models for language agents +2
  58. Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World ModelWorld models → Latent predictive world models
  59. Tractable Reinforcement Learning for Full Class of Signal Temporal Logic Specifications Using Spatiotemporal Tube RewardDeep reinforcement learning methods → Safe and constrained RL
  60. PointCast: One World Model for Rigid, Articulated, and Deformable Object ManipulationWorld models → Embodied and robot world models
  61. When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit AssignmentLLM reasoning → Reinforcement learning for reasoning +1
  62. ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid ControlLLM safety and security → Machine unlearning +1
  63. Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumerLLM agents and tool use → Financial trading and forecasting agents
  64. Memory-Conditioned Diffusion Model for Generalized Langevin DynamicsDiffusion models → Flow matching, time series and science
  65. AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving ScenariosLLM reasoning → Chain-of-thought reasoning for driving +2
  66. Zero-Shot Object Removal via Attention Masking, Latent Anchoring, and RefinementDiffusion models → Inverse problems and image restoration
  67. Beyond Future Prediction: Denoising as Generative Adaptation for Robot ControlDiffusion models → Diffusion and flow policies for robotics
  68. TANDEM: Task and Motion Planning with As-Needed Demonstrations for Efficient Vision-Language-Action Model Fine-tuningVision-language-action models → Reinforcement learning and post-training
  69. Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3State-space sequence models (S4, Mamba) → Core SSM architectures for language
  70. Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  71. Generalizable Robotic Insertion with World ModelsWorld models → Embodied and robot world models
  72. MemBodied: Recurrent Associative Memory for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  73. Controlling Collectives of AI Agents in Reasoning Space with Spatial TransformersLLM reasoning → Reasoning for agents, planning and code +1
  74. A Unified Framework and Dataset for Oriented Object Visual Grounding in Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  75. From Agent Output to Authorized TransitionLLM agents and tool use → Software engineering coding agents
  76. UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio GenerationDiffusion models → Audio, speech and music
  77. PASTABench: Proactive Assessment of Sequential Trajectories for Agent SafetyLLM agents and tool use → Agent threats, guardrails and governance
  78. Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge CoordinationOffline RL and imitation learning from data → Safe offline RL +1
  79. Dissecting Advantage-Guided Post-Training for Vision-Language-Action PoliciesVision-language-action models → Reinforcement learning and post-training +1
  80. RL Starts before RL: On Policy Distillation for Better Reinforcement LearningKnowledge distillation → On-policy and self-distillation for LLMs +1
  81. Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based RefinementDiffusion models → Medical imaging and segmentation
  82. Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  83. Distillation for Efficient Multitask Manipulation Policies via Conditional Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  84. Curriculum Learning with GNN-based Reinforcement Learning for Job Shop SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
  85. ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth ZoomingDiffusion models → 3D, point cloud and scene generation
  86. SlackDrive: Reclaiming Runtime Slack for Adaptive Driving InferenceWorld models → World models for autonomous driving +1
  87. AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building modelsLLM agents and tool use → Multimodal and embodied agents
  88. Exact Quantile Balancing and Load-Error Injection for Mixture-of-ExpertsMixture-of-experts → Efficient MoE training and inference systems
  89. Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format ComparisonEfficient LLM inference and serving → KV cache optimization
  90. Learning a Speed-adaptive Hip Exoskeleton Control Policy Via Sim-to-real Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  91. Improving Ensemble Filters with Flow MatchingDiffusion models → Flow matching, time series and science
  92. Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using AgentsLLM agents and tool use → Tool learning and function calling
  93. Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated FinanceLLM agents and tool use → Financial trading and forecasting agents
  94. Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk TargetsEfficient LLM inference and serving → KV cache optimization
  95. Less Language, More Latents: Annotation-Efficient VLAs for DrivingVision-language-action models → VLA for autonomous driving +1
  96. The KV Cache Working Set: Online Capacity Planning for LLM Inference SystemsEfficient LLM inference and serving → KV cache optimization
  97. Categorical Internalisation of Environmental Groupoids for Generalisable POMDP SolvingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  98. Limiting-Kernel Q(λ): Bridging Short and Long HorizonsDeep reinforcement learning methods → RL theory and sample complexity
  99. InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot PoliciesVision-language-action models → 3D and spatial-aware VLA
  100. FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational PathologyMultimodal LLMs / vision-language models → Medical vision-language models
All 460
  1. Gender Bias in Vision-Language In-Context LearningMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  2. Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency RegularizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  3. InternW0: A Foundational Physical World Model for Efficient Real-World InteractionsWorld models → Embodied and robot world models
  4. Agent-based Modeling: Equilibrium, Echo Chambers, and Efficiency in Hybrid Coevolutionary Opinion GamesLLM agents and tool use → Social simulation and multi-agent debate
  5. InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image GenerationLLM safety and security → Vision-language and text-to-image safety
  6. State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live StateLLM agents and tool use → Reinforcement learning for LLM agents
  7. EmphTTS: an emphasis-control TTS with reinforcement learningDeep reinforcement learning methods → RL training of language and agent models
  8. Unity Insight: A Production Code--Asset Index for LLM Coding Agents in Unity ProjectsLLM agents and tool use → Software engineering coding agents
  9. DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold AlignmentLLM reasoning → Reinforcement learning for reasoning
  10. FDE-Bench: Evaluating LLM Agents for Deployment Environment ConfigurationLLM agents and tool use → Software engineering coding agents
  11. EBRL: Asynchronous Embodied RL by Multi-Grained Resource ManagementDeep reinforcement learning methods → RL training of language and agent models
  12. Robustness of Diffusion Models under Distribution ShiftDiffusion models → Diffusion foundations and sampling
  13. Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using AgentsLLM agents and tool use → Agent threats, guardrails and governance
  14. ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  15. NV-Reason-CT: 3D Visual Language Model for CT AnalysisLLM reasoning → Clinical and biomedical applications +1
  16. WhatWorkedBench: Benchmarking Experimental Understanding in AI AgentsLLM agents and tool use → Software engineering coding agents
  17. Active Learning for Low-Altitude Radio Map Construction via Plug-and-Play Flow MatchingDiffusion models → Flow matching, time series and science
  18. DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming VideoEfficient LLM inference and serving → Fast autoregressive visual generation
  19. CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action ExecutionVision-language-action models → VLA architectures and generalization
  20. Spiking Neural Network Predicting Sequence of the External Worlds States in Model-Based Reinforcement LearningDeep reinforcement learning methods → Spiking and neuromorphic RL
  21. Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line InspectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  22. Latent evolving World Action ModelWorld models → Embodied and robot world models +1
  23. BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +1
  24. Quantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud OrchestrationDeep reinforcement learning methods → Quantum reinforcement learning
  25. Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction FollowingKnowledge distillation → On-policy and self-distillation for LLMs
  26. What Looks Like a Capability Limit in Vision-Language Models Is a Readout LimitMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  27. Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAGRetrieval-augmented generation → Privacy and security of RAG
  28. Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-SpeechLLM safety and security → Machine unlearning +1
  29. When Parallel Drafter Meets Parallel Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  30. PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  31. EvoAudio: Recursive Self-Improvement for Audio UnderstandingSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  32. MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving CompressionRetrieval-augmented generation → Generation and context integration +1
  33. Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  34. Planned Test-Time Scaling with Coordinated Reasoning PathsLLM reasoning → Test-time compute and efficient thinking
  35. Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language ModelsLLM reasoning → Test-time compute and efficient thinking
  36. Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes InteractionLLM safety and security → Machine unlearning
  37. Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular DesignLLM agents and tool use → Medical and scientific domain agents
  39. Spatial and Semantic Reasoning for LLM-Driven Robot Navigation via MCPLLM reasoning → Spatial and embodied reasoning
  40. CART: Closed-Loop Adaptive Red Teaming for Large Language ModelsLLM safety and security → Prompt injection and agent security
  41. Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  42. Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative WorkflowsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  43. Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved MechanismsLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. CoRe-WAM: Correspondence-Aligned Temporal Residuals for World Action ModelsWorld models → Embodied and robot world models
  45. Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  46. EmbodiedSWE: Coding Agents for Long Horizon Dexterous RoboticsLLM agents and tool use → Multimodal and embodied agents
  47. Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI AgentsLLM agents and tool use → GUI and mobile agents +1
  48. Discrete Diffusion Models via Evolving Variational Autoregressive NetworksDiffusion models → Diffusion foundations and sampling
  49. StateComp: Learning When to Compress History in Long Horizon AgentsLLM agents and tool use → Agent memory systems
  50. Large Knowledge Model: From Papers to a Scientific Reasoning LandscapeLLM reasoning → Knowledge- and tool-augmented reasoning +1
  51. KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM ScalingLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  52. SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud DetectionLLM agents and tool use → Financial trading and forecasting agents
  53. Memory Control Signals Emerge Before Action in Long Horizon AgentsLLM agents and tool use → Agent memory systems
  54. Hunyuan-A13B Technical ReportMixture-of-experts → MoE large language models
  55. DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon AgentsLLM reasoning → Reasoning for agents, planning and code +1
  56. BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving PredictionEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  57. CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned EnvironmentsLLM agents and tool use → Social simulation and multi-agent debate
  58. Specifying and Maintaining Agentic Workflows: An Empirical Study of GitHub Agentic WorkflowsLLM agents and tool use → Software engineering coding agents
  59. From PyTorch to the NPU: LLM-Agent-Driven Model Conversion Across Heterogeneous Inference RuntimesLLM agents and tool use → Software engineering coding agents
  60. Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell ModelsLLM agents and tool use → Medical and scientific domain agents
  61. Data-Assimilation-Assisted Reinforcement Learning for Power Grid Control under Load UncertaintyDeep reinforcement learning methods → RL for energy, networks and operations
  62. Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge LatticesRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  63. LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  64. BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse RetrievalRetrieval-augmented generation → Generation and context integration
  65. Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset
  66. Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes
  67. Sharp Oracle-Regret Tradeoffs for Projection-Free Online Convex Optimization
  68. System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer
  69. The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
  70. Contingent Exposure Routing for Financial AI: Outage Risk and the Cost of Indivisible Decisions
  71. CAVE-Mem: Boundary-Aware Experience Validation for Memory Search
  72. Compositional Embedding Architecture for Physical Field Prediction in Componentized Aerospace Systems
  73. How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds
  74. Conflicting Supervision Moves Commitment, Not Capability: A 12.29σ arrangement effect that is exactly zero under a convention-agnostic score
  75. Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
  76. Constant-Memory Recall: Learned Associations in a Fixed Matrix State
  77. The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models
  78. When Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction
  79. What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery
  80. Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world application
  81. 3dgs-sc: a controlled static screen-content benchmark for 3d gaussian splatting
  82. Gauge-Equivariant Attention for Rotation-Stable 360^circ Scene Understanding
  83. Calibration-Free Surface Normals Estimation in Vision-Based Tactile Sensing using Universal Photometric Stereo
  84. Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detection
  85. Dimension-Specific Imbalance and an Adaptive Hybrid Label Strategy for Multi-Task Affective State Recognition in Classroom Video
  86. Fusion Under Component Failure: Negative Results and Failure Modes in Ensemble AI-Generated Image Detection
  87. ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?
  88. Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers
  89. M2PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease
  90. When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection
  91. COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages
  92. KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization
  93. A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations
  94. Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning
  95. Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes
  96. Script Choice in LLMs: Evidence for Late-Layer Commitment
  97. The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning
  98. Learned Cross-Task Relationships in Multi-Task Models
  99. Physics-Guided Multi-Objective Deep Learning for Ultrasound RF Data Interpolation in Resource-Constrained Imaging
  100. Reinforcement Learning with Verifiable Rewards for Small Search Agents
  101. KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS
  102. Selective Inference for Deep Clustering in Latent Spaces
  103. Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling
  104. Technical Manual for Toolkit for Confidence-Corpus Consistency, Corpus Absorption and Rule Learning via Fine-Tuning on a Fabricated Corpus
  105. GeoNLI - A Natural Language Interpreter for Satellite Imagery
  106. Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
  107. Integrating Local Detail and Global Context: A Dual-Input Multi-Task Learning Framework for Bone Tumor Diagnosis
  108. PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs
  109. Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage
  110. Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities
  111. Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits
  112. Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation
  113. Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?
  114. An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection
  115. LabFactory: Building and Evaluating Executable AI Labs
  116. Federated Learning of AnDE Classifiers
  117. TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation
  118. M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
  119. Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
  120. OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds
  121. PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting
  122. Global Convergence of Third-Order Langevin Dynamics for Non-Convex Optimization via Simulated Annealing
  123. UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound
  124. fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series
  125. UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference
  126. Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters
  127. Learning to Discover Interesting Mathematics
  128. HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Mesh
  129. BRFID: Toward Byzantine-Robust Federated Intrusion Detection
  130. TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation
  131. NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees
  132. SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models
  133. Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning
  134. Time-Series Foundation Models That Understand Data Revisions
  135. TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
  136. Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs
  137. When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages
  138. SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference
  139. Matrix Aggregation Operators
  140. Speculative Evaluation of Stochastic LLMs
  141. CFD Correction of Open Tip Clearance Flow in a Compressor Cascade Using VAE Latent Space Adaptation
  142. SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
  143. An Order-Theoretic Characterization of Consistent Inductive Inference
  144. Contrastive Learning for Authorship Verification
  145. StudentBench: AI and human tutoring yield equivalent GRE learning gains
  146. Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction
  147. Even Sharper Bounds for Transductive Learning and Its Applications
  148. Nonequilibrium Phases of Repulsive Self-Attention: Chaos, Attention Condensation, and Emergent Locality
  149. HaRP: High Dynamic Range Photosequencing through Dual Reversed Shutter Scanning
  150. Minimal-Norm Univariate Two-Layer ReLU Classification: Exact Solutions and Global Optimality with Skip Connections
  151. MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos
  152. Predicting the Progression of Adolescent Idiopathic Scoliosis
  153. Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
  154. Context-Continuous Preference Learning for Exoskeleton Personalization
  155. Repairability of Inexact Solvers in Recursive State Estimation with Machine Learning
  156. The Skin-Restricted Reinhard Transform:Uniqueness under a Lightness-Preserving Constraint
  157. Learning Holographic Reduced Representations with Clifford Variational Autoencoders
  158. Learning Collective Dynamics with Differentiable Gaussian Representations
  159. Memory Attention
  160. Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following
  161. Quantum score matching with applications to learning thermal states
  162. LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials
  163. Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB
  164. MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference
  165. Digital diglossia: Arabic between X and Facebook
  166. Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding
  167. Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler
  168. An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice
  169. BronchoTop: Bronchoscopy Navigation via RGB-Only Topological Localization
  170. LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder
  171. Learning the Cost of Reliable Inference
  172. VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoing
  173. RoomLight: A 2.5D Illumination Prior for Indoor Environments
  174. Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings
  175. PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer
  176. Benchmarking Hyperspectral Foundation Models for Hyperspectral Unmixing
  177. Shutdown Sabotage Propensities in Multi-Agent Systems
  178. Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
  179. Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solving
  180. RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models
  181. Complementary Roles of Activation and Parametric Memory in Few-Shot Learning
  182. hyperbolix: Hyperbolic Deep Learning in JAX
  183. Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat?
  184. ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
  185. EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks
  186. Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning
  187. Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification
  188. From Alignment to Fusion in 3D Vision-Language
  189. Log-Depth Recurrent Language Modeling
  190. Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models
  191. Transferable Evidence Reconstruction for Longitudinal Glucose Representations
  192. Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features
  193. From Change Captions to Change Detection: Semantic-Appearance Agreement Framework for Remote Sensing Change Detection
  194. Two Global Crops Suffice: Locating Semantic Emergence in DINO-Style Self-Supervised Learning
  195. VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation
  196. From ECG Signals to Representative-Morphology Heatmaps for Biometric Recognition
  197. How Sensitive Are LLM Leaderboard Claims to Hidden Model Selection?
  198. Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal Classification
  199. Rank-One Signal Recovery in Sparse Wishart Noise
  200. Depth-Guided Contrastive Learning for 2D Representations with 3D Spatial Awareness
  201. A comparative assessment of global building and settlement datasets across geographic and settlement contexts
  202. Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs
  203. EvEMTBench: An Open Benchmark for Machine Learning in Power System Protection
  204. "We'll Fix It Later": Education, AI, and the Deferral of Privacy in EdTech
  205. NPBoost: Neural Processes with Gradient-Boosted Fixed Effects
  206. Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation
  207. Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
  208. Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingness
  209. Visual Tripwires: Anticipating Failure in Deep Vision Systems
  210. MotionSpec: Spectral Trajectory Supervision for Motion-Consistent Video Generation
  211. Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark
  212. Discovery of fully efficient fault indicators along a data-based diagnosis process
  213. LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations
  214. Recursive Uncertainty-Gated Image Registration for Learning-based Algorithms
  215. Reference-Based Analysis of Coherence and Diversity in Open-Ended Text Generation
  216. LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT
  217. TEEP-RCNN: Texture-Enhanced Edge-aware Perception for Steel Surface Defect Detection via Improved Convolutional Block Attention in Faster R-CNN
  218. A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models
  219. Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings
  220. TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
  221. How Much Were You Told? Measuring External Information in Peer Reviews
  222. Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing
  223. PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
  224. SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials
  225. Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints
  226. Shared Global KV with Layer-Specific Local History
  227. Controlled Attribute-Specific Summarization of Interrogative Dialogues
  228. Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
  229. PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue
  230. Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress
  231. Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices
  232. Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
  233. All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
  234. Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions
  235. MENO: Memory-Efficient Neural Operator
  236. NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers
  237. AI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets
  238. NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objects
  239. SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
  240. DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mapping
  241. SynSeq: End-to-End SYNTAX Score Prediction from Coronary Angiography Videos
  242. Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research
  243. CasCVS-Net: A Staged Multi-Task Cascade for Critical View of Safety Assessment
  244. What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates
  245. Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding
  246. RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction
  247. Track2Art: Articulated Object Model Recovery with Visual-Geometric Track Representations
  248. SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection
  249. The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA
  250. Evolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence
  251. Private Decentralized Optimization with Noise Reduction and Bias Correction
  252. FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
  253. FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints
  254. Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond
  255. Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting
  256. Pheno-GS: Phenoscape-scale Geodesic Sinkhorn
  257. Compliant AI Infrastructure for Regulated Finance: A tiered multi-agent framework with DLT audit trails for financial operations in DACH
  258. SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
  259. BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport
  260. A generalizable structural brain MRI foundation model built through dual-priority federated pretraining
  261. Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality
  262. When Context Misleads: In-context Learning with Jurisdiction in Large Language Models
  263. Efficient Linear Bandits via Cluster-Aware Sketching
  264. Hidden not Deleted: How Networks Suppress Entangled Features
  265. MWE-ECL: Recoverable Long-Range Context Does Not Always Override Local Lexical Priors
  266. The Capability Manifold and ML Scaling Laws
  267. Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters
  268. VCMM: Variance-Calibrated Momentum for Multimodal Learning
  269. TNLearn: An Open Source Python Package for Task-based Neurons
  270. When Visual Quality Misleads: Intent Recognition under Rendered Avatar Distortions
  271. ThaiTrees: Thai Syntactic Dependency Trees Across Domains
  272. PhyMo: A Physical-Field Modality for Multimodal AI4Physics
  273. Behaviora - A Conceptual Architecture for External and Internal Behavior of Robots and Agents
  274. ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather
  275. M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification
  276. Not What You Meant: Can LLMs Follow a Specified Negation Semantics?
  277. Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models
  278. Know-Your-Scene (KYS)-SLAM: Hierarchical Semantic-Motion Priors for Feature Matching in Stereo Visual SLAM
  279. Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality
  280. Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
  281. Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction
  282. Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs
  283. Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement
  284. Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents
  285. Issuer-Sovereign Agentic Payments
  286. SatUnreal: A High-Precision Synthetic Dataset for Satellite Stereo Matching via Unreal Engine
  287. Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces
  288. Overlapping Visual Grouping Without Semantic Priors
  289. EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine
  290. Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
  291. S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detection
  292. When Labels Are Scarce: An Oscillatory State Space Model for Vibration Diagnosis
  293. Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference
  294. Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation
  295. AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
  296. Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools
  297. When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models
  298. Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction
  299. Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
  300. ASAP: Visual Analytics for Identifying and Analyzing Image Patterns in AI-generated Images
  301. Geometry-Conditioned Visual Place Recognition in Natural Environments
  302. Anomaly-Free Self-Optimization via AUC Bounds
  303. Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models
  304. Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations
  305. Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems
  306. Evolving Inspectable O-RAN Slicing xApps with LLMs
  307. Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance
  308. Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression
  309. A Hybrid Iterative Deep Ritz Method for Elliptic Interface Problems
  310. Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration
  311. Multi-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls
  312. FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems
  313. Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams
  314. Beyond the Illusion of Power: Calibrating Quasi-Experiments in Observational IS
  315. Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation
  316. NGN: Learning Neural Network Size as a Differentiable Count
  317. Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins
  318. Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition
  319. PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
  320. Multitask Regression with Pairwise Fusion
  321. EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory
  322. Graph Learning with Spectral Connectivity Priors for Scarce Data
  323. TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
  324. High Dynamic Range Video Reconstruction from Single-Exposure Raw Sequences
  325. GaussPDE: Graph-Based Partial Differential Equation-Driven Rendering for 3D Gaussian Splatting
  326. Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs
  327. UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
  328. Functional Causal Discovery via Conditional Covariance Ordering
  329. What Converges in the Platonic Representation Hypothesis? Structure over Geometry
  330. The Risk-Sensitive Schr"odinger Bridge: Is Not a KL Projection
  331. Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders
  332. Listening and Mirroring: The Effects of Verbal Attunement and Behavioral Mimicry on Social and Empathic Perceptions of Embodied AI Agents in VR
  333. Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation
  334. Combining LLMs and Genetic Search for ARC-AGI-2
  335. On the Sample Complexity of Active Learning with Membership Queries
  336. Strip Convolution and Direction-Aware Exclusion Loss for Oriented Ship Detection
  337. Distilling Sequential Computation in Transformer Language Models
  338. A Scaling Study for fMRI Foundation Models
  339. Surgical Kinematics from Monocular Video with Learned Articulated Motion Constraints
  340. Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care Residents
  341. Tail-Aware Geometry Learning for Conformal Ellipsoids
  342. Learning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation
  343. KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
  344. Scalable Subgraph Sampling via Resistance Curvature
  345. Benchmarking Active Spot Selection for Cost-Efficient Spatial Transcriptomics
  346. Prediction with Expert Advice: Anytime Regret with Many Experts Matches the Fixed-Time Constant
  347. Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach
  348. XLOG: A CUDA-Native Engine for Neurosymbolic Integration
  349. Reliable Federated TinyML Deployment for IoT Security
  350. A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems
  351. ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization
  352. Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
  353. Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders
  354. Diverse by Design: Architectural Constraints for Prototype-Based Interpretability
  355. Data-driven discrete-time deep recurrent neural network-based modeling for dissipative systems
  356. Artificial intelligence surrogates for treatment effect estimation with before-and-after data
  357. Change detection with conformal martingales: new optimal constructions, and suboptimality of existing methods
  358. LeakScale: Estimating the Causal Effect of Benchmark Exposure
  359. Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences
  360. Realize What Matters: Principled Context Representation for Large-Scale Reasoning