mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 12 May 2026

767 papers

  1. Agentic AI Containment Architecture for Security HardeningLLM agents and tool use → Agent threats, guardrails and governance
  2. Discovering KV Cache Eviction Policies via LLM-Guided Program EvolutionEfficient LLM inference and serving → KV cache optimization
  3. GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction CorpusMixture-of-experts → MoE large language models
  4. Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction MarketsWorld models → World models for language agents
  5. Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved UtilityLLM reasoning → Prompting and chain-of-thought reasoning +1
  6. Semantic Register Compression in Multi-Agent LLM CascadesLLM agents and tool use → Agent memory systems
  7. STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper GenerationLLM agents and tool use → Web, search, and research agents
  8. STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge DistillationKnowledge distillation → Distillation for spiking neural networks
  9. LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMsLLM reasoning → Reasoning benchmarks and evaluation
  10. Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA GenerationLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
  11. The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  12. Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective DeadlockDiffusion models → Diffusion foundations and sampling +1
  13. Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic WorkflowsLLM agents and tool use → Medical and scientific domain agents
  14. Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA ScaffoldsLLM reasoning → Reasoning benchmarks and evaluation
  15. Emergence of Frontier Superposition: M"obius attractor and Cascade SupervisionLLM reasoning → Test-time compute and efficient thinking
  16. Multi-Token Residual PredictionDiffusion models → Discrete and text diffusion
  17. DynaTrain: Fast Online Parallelism Switching for Elastic LLM TrainingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  18. Composition of Memory Experts for Diffusion World ModelsWorld models → Latent predictive world models +1
  19. PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM PipelinesRetrieval-augmented generation → Generation and context integration
  20. D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative DraftingEfficient LLM inference and serving → Speculative decoding
  21. Stable and Near-Reversible Diffusion ODE Solvers for Image EditingDiffusion models → Image generation, text-to-image and editing
  22. OrbiSim: World Models as Differentiable Physics Engines for Embodied IntelligenceWorld models → Embodied and robot world models
  23. Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative LearningDiffusion models → Flow matching, time series and science
  24. CAX-Agent: A Lightweight Agent Harness for Reliable APDL AutomationLLM agents and tool use → Software engineering coding agents
  25. SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime InterfacesLLM agents and tool use → Agent skill learning and evolution
  26. Quantifying Potential Observation Missingness in Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  27. Orthrus: Memory-Efficient Parallel Token Generation via Dual-View DiffusionDiffusion models → Discrete and text diffusion
  28. Mechanism Plausibility in Generative Agent-Based ModelingLLM agents and tool use → Social simulation and multi-agent debate
  29. Neurodata Without Boredom: Benchmarking Agentic AI for Data ReuseLLM agents and tool use → Medical and scientific domain agents
  30. Discrete MeanFlow: One-Step Generation via Conditional Transition KernelsDiffusion models → Flow matching, time series and science
  31. Synthesizing the Expert: A Validated Multimodal Dataset for Trustworthy AI-Assisted Swimming CoachingRetrieval-augmented generation → Agentic RAG, agents and memory
  32. Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge RetentionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  33. ToolMol: Evolutionary Agentic Framework for Multi-objective Drug DiscoveryLLM agents and tool use → Medical and scientific domain agents
  34. Generative Motion In-betweening by Diffusion over Continuous Implicit RepresentationsDiffusion models → Video generation
  35. Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  36. WriteSAE: Sparse Autoencoders for Recurrent StateState-space sequence models (S4, Mamba) → Core SSM architectures for language +1
  37. Inference-Time Machine Unlearning via Gated Activation RedirectionLLM safety and security → Machine unlearning
  38. Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained SamplingDiffusion models → Flow matching, time series and science
  39. CoT-Guard: Small Models for Strong MonitoringLLM reasoning → Prompting and chain-of-thought reasoning
  40. Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  41. Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  42. Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and SafetyLLM agents and tool use → Software engineering coding agents
  43. Before the Last Token: Diagnosing Final-Token Safety Probe FailuresLLM safety and security → Jailbreaking
  44. CHAL: Council of Hierarchical Agentic LanguageLLM reasoning → Reasoning for agents, planning and code +1
  45. DisaBench: A Participatory Evaluation Framework for Disability Harms in Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  46. Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program AnalysisLLM agents and tool use → Software engineering coding agents
  47. 3D RL-DWA: A Hybrid Reinforcement Learning and Dynamic Window Approach for Goal-Directed Local Navigation in Multi-DoF RobotsDeep reinforcement learning methods → RL for robot navigation and UAV control
  48. Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?Multimodal LLMs / vision-language models → Image editing and quality assessment
  49. Learning Transferable Latent User Preferences for Human-Aligned Decision MakingLLM reasoning → Reinforcement learning for reasoning +1
  50. Revealing Interpretable Failure Modes of VLMsLLM reasoning → Chain-of-thought reasoning for driving +1
  51. All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMsLLM reasoning → Reasoning benchmarks and evaluation +1
  52. ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  53. Plan Before You Trade: Inference-Time Optimization for RL Trading AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  54. Multi-Rollout On-Policy Distillation via Peer Successes and FailuresKnowledge distillation → On-policy and self-distillation for LLMs
  55. CRAFT: Clinical Reward-Aligned Finetuning for Medical Image SynthesisMultimodal LLMs / vision-language models → Medical vision-language models +1
  56. MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic SegmentationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  57. OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean ForecastingMechanistic interpretability → Interpreting time-series and weather models
  58. Driving Intents Amplify Planning-Oriented Reinforcement LearningEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
  59. MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
  60. Action Emergence from Streaming IntentDiffusion models → Diffusion and flow policies for robotics +1
  61. Think Twice, Act Once: Verifier-Guided Action Selection For Embodied AgentsLLM reasoning → Spatial and embodied reasoning +1
  62. The critical slowing down in training diffusion modelsDiffusion models → Diffusion foundations and sampling
  63. TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingDiffusion models → Video generation
  64. 3D Primitives are a Spatial Language for VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  65. DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic DistractionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  66. VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer AuthorityLLM agents and tool use → Multimodal and embodied agents
  67. Active Sensing with Meta-Reinforcement Learning for Emitter Localization from RF ObservationsDeep reinforcement learning methods → RL for energy, networks and operations
  68. Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt DiscoveryLLM safety and security → Prompt injection and agent security
  69. Uncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge DistillationKnowledge distillation → Distillation for medical imaging
  70. Covering Human Action Space for Computer Use: Data Synthesis and BenchmarkLLM agents and tool use → GUI and mobile agents +1
  71. SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify ArchitectureMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  72. From Web to Pixels: Bringing Agentic Search into Visual PerceptionLLM agents and tool use → Multimodal and embodied agents
  73. AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable RewardLLM reasoning → Multimodal reasoning
  74. LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced ColleaguesLLM agents and tool use → Agent memory systems
  75. Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-TrainingLLM reasoning → Prompting and chain-of-thought reasoning +1
  76. ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use AgentsLLM agents and tool use → GUI and mobile agents
  77. MEME: Multi-entity & Evolving Memory EvaluationLLM agents and tool use → Agent memory systems
  78. Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  79. Reward Hacking in Rubric-Based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  80. KV-Fold: One-Step KV-Cache Recurrence for Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  81. Solve the Loop: Attractor Models for Language and ReasoningLLM reasoning → Test-time compute and efficient thinking
  82. Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and OutputsLLM reasoning → Reasoning for agents, planning and code
  83. TextSeal: A Localized LLM Watermark for Provenance & Distillation ProtectionLLM safety and security → Watermarking generated content and models
  84. GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent OptimizationDiffusion models → Video generation
  85. ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated MergingLLM reasoning → Reasoning benchmarks and evaluation
  86. Aligning Flow Map Policies with Optimal Q-GuidanceDiffusion models → Diffusion and flow policies for robotics +1
  87. Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional ImagesLLM reasoning → Spatial and embodied reasoning +1
  88. Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular ModelingLLM agents and tool use → Social simulation and multi-agent debate
  89. Model-based Bootstrap of Controlled Markov ChainsOffline RL and imitation learning from data → Offline RL algorithms +1
  90. Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI SystemsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  91. OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  92. GeoQuery: Geometry-Query Diffusion for Sparse-View ReconstructionDiffusion models → 3D, point cloud and scene generation
  93. Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-TrainingDeep reinforcement learning methods → Deep RL algorithms and representations
  94. Discrete Flow Matching for Offline-to-Online Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  95. Fast Image Super-Resolution via Consistency Rectified FlowDiffusion models → Inverse problems and image restoration
  96. ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic WorkflowsLLM agents and tool use → Web, search, and research agents
  97. Agent-Based Post-Hoc Correction of Agricultural Yield ForecastsLLM agents and tool use → Multimodal and embodied agents
  98. Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  99. GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention SpecializationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  100. Classifier Context Rot: Monitor Performance Degrades with Context LengthLLM agents and tool use → Agent threats, guardrails and governance
All 767
  1. QAP-Router: Tackling Qubit Routing as Dynamic Quadratic Assignment with Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  2. MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question AnsweringLLM reasoning → Clinical and biomedical applications
  3. BSO: Safety Alignment Is Density Ratio MatchingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  4. EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health RecordsRetrieval-augmented generation → Medical and biomedical RAG
  5. Reinforcing VLAs in Task-Agnostic World ModelsWorld models → Latent dynamics models and model-based RL +1
  6. Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph ModelingDeep reinforcement learning methods → Deep RL algorithms and representations
  7. G2TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  8. Images in Sentences: Scaling Interleaved Instructions for Unified Visual GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  9. Executable Agentic Memory for GUI AgentLLM agents and tool use → GUI and mobile agents
  10. Targeted Neuron Modulation via Contrastive Pair SearchLLM safety and security → Safety alignment, refusal and guardrails
  11. PriorZero: Bridging Language Priors and World Models for Decision MakingWorld models → World models for language agents
  12. TokenRatio: Principled Token-Level Preference Optimization via Ratio MatchingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. Large-Small Model Collaboration for Farmland Semantic Change DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  14. Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt-Engineering Quality AssuranceLLM agents and tool use → Software engineering coding agents
  15. Delay-Empowered Causal Hierarchical Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  16. PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon AgentsLLM agents and tool use → Agent memory systems
  17. Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  18. Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an InferenceWorld models → World models for language agents
  19. SI-Diff: A Framework for Learning Search and High-Precision Insertion with a Force-Domain Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  20. No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  22. TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy FinetuningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  23. Morphologically Equivariant Flow Matching for Bimanual Mobile ManipulationDiffusion models → Diffusion and flow policies for robotics
  24. A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  25. On the Interpretability of Whisper Encodings Using Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  26. Intrinsic Vicarious Conditioning for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  27. Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM SystemsLLM reasoning → Reasoning for agents, planning and code +1
  28. Train Short, Act Long: Multistability and the Horizon Independence of Recurrent PoliciesDeep reinforcement learning methods → Deep RL algorithms and representations
  29. SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference LearningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  30. Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer DynamicsWorld models → World models for language agents
  31. Correcting Selection Bias in Sparse User Feedback for Large Language Model Quality Estimation: A Multi-Agent Hierarchical Bayesian ApproachLLM agents and tool use → Social simulation and multi-agent debate
  32. Expected Batch Optimal Transport Plans and Consequences for Flow MatchingDiffusion models → Flow matching, time series and science
  33. Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language ModelLLM reasoning → Multimodal reasoning +1
  34. X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose InteractionOffline RL and imitation learning from data → Robot manipulation imitation learning
  35. Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are CompleteVision-language-action models → Generalist VLA models and benchmarks
  36. Rollout Cards: A Reproducibility Standard for Agent ResearchDeep reinforcement learning methods → RL training of language and agent models
  37. Metaphor Is Not All Attention NeedsLLM safety and security → Jailbreaking
  38. Disentangled Sparse Representations for Concept-Separated Diffusion UnlearningDiffusion models → Robustness, privacy and adversarial aspects +1
  39. When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual EntropyDiffusion models → Diffusion and flow policies for robotics +1
  40. AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  41. Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated ContextsLLM agents and tool use → Agent threats, guardrails and governance
  42. World Action Models: The Next Frontier in Embodied AIWorld models → Embodied and robot world models +1
  43. Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic SystemsLLM agents and tool use → Agent memory systems
  44. Property-Level Reconstructability of Agent Decisions: An Anchor-Level Pilot Across Vendor SDK Adapter RegimesLLM agents and tool use → Agent threats, guardrails and governance
  45. Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy CorrectionLLM agents and tool use → Reinforcement learning for LLM agents
  46. SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative MemoryLLM agents and tool use → Agent memory systems +1
  47. Holder Policy OptimisationLLM reasoning → Reinforcement learning for reasoning
  48. SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill GraphsLLM agents and tool use → Agent skill learning and evolution +1
  49. SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack SurfacesLLM agents and tool use → Agent threats, guardrails and governance
  50. L2P: Unlocking Latent Potential for Pixel GenerationDiffusion models → Diffusion foundations and sampling
  51. Learning Agentic Policy from Action GuidanceLLM agents and tool use → Reinforcement learning for LLM agents
  52. Split the Differences, Pool the Rest: Provably Efficient Multi-Objective ImitationOffline RL and imitation learning from data → Imitation learning methods
  53. The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention ArchitecturesEfficient LLM inference and serving → Serving systems and request scheduling
  54. BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft PromptsLLM safety and security → Backdoor and data poisoning attacks
  55. High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  56. Stochastic Minimum-Cost Reach-Avoid Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  57. Multimodal Abstractive Summarization of Instructional Videos with Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  58. From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic ManipulationLLM agents and tool use → Multimodal and embodied agents
  59. Counterfactual Trace Auditing of LLM Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  60. Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  61. From Noise to Diversity: Random Embedding Injection in LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  62. Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement TrainingLLM reasoning → Multimodal reasoning +2
  63. StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  64. Domain Restriction via Multi SAE Layer TransitionsMechanistic interpretability → SAE features and their applications
  65. Delightful Gradients Accelerate Corner EscapeDeep reinforcement learning methods → RL theory and sample complexity
  66. YFPO: Yoked Feature Preference Optimization with Neuron-Guided RewardsLLM reasoning → Mathematical reasoning +1
  67. Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem ProvingLLM reasoning → Mathematical reasoning
  68. Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision TasksDiffusion models → Image generation, text-to-image and editing
  69. Proteus: A Self-Evolving Red Team for Agent Skill EcosystemsLLM agents and tool use → Agent threats, guardrails and governance +2
  70. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language ModelsMechanistic interpretability → SAE features and their applications
  71. On-Policy Self-Evolution via Failure Trajectories for Agentic Safety AlignmentLLM agents and tool use → Agent threats, guardrails and governance +2
  72. RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender SystemsLLM agents and tool use → Agentic recommender systems
  73. h-control: Training-Free Camera Control via Block-Conditional Gibbs RefinementDiffusion models → Video generation
  74. FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved SparsityDiffusion models → Video generation
  75. IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  76. Variance-aware Reward Modeling with Anchor GuidanceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  77. Very Efficient Listwise Multimodal Reranking for Long DocumentsRetrieval-augmented generation → Generation and context integration
  78. UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  79. Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  80. GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-DistillationLLM reasoning → Reinforcement learning for reasoning +2
  81. Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth EstimationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  82. Trade-offs in Decentralized Agentic AI Discovery Across the Compute ContinuumLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model EditingSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  84. Learning Action Manifold with Multi-view Latent Priors for Robotic ManipulationVision-language-action models → 3D and spatial-aware VLA
  85. See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action ModelVision-language-action models → Efficient VLA inference and adaptation
  86. Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action ModelsVision-language-action models → World model-based VLA
  87. Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual EnhancementMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  88. OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  89. ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory SystemsMixture-of-experts → Expert routing strategies
  90. Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo SimulationsLLM agents and tool use → Social simulation and multi-agent debate
  91. Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low VisionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  92. From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical PredictionEfficient LLM inference and serving → Prompt and context compression
  93. Is Monotonic Sampling Necessary in Diffusion Models?Diffusion models → Diffusion foundations and sampling
  94. Behavioral Integrity Verification for AI Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  95. NavOL: Navigation Policy with Online Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  96. M4-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object DetectionMixture-of-experts → Vision mixture-of-experts
  97. One-Step Generative Modeling via Wasserstein Gradient FlowsDiffusion models → Flow matching, time series and science
  98. DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA PoliciesVision-language-action models → Failure recovery and robustness
  99. When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight ChannelLLM reasoning → Prompting and chain-of-thought reasoning
  100. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  101. OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization ModelingLLM agents and tool use → Medical and scientific domain agents
  102. AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  103. Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and MitigationLLM safety and security → Prompt injection and agent security
  104. Allegory of the Cave: Measurement-Grounded Vision-Language LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  105. Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling
  106. CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal ConcentratingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  107. A Research Agenda on Agents and Software Engineering: Outcomes from the Rio A2SE SeminarLLM agents and tool use → Software engineering coding agents
  108. SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  109. Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value GuidanceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  110. Debiased Model-based Representations for Sample-efficient Continuous ControlDeep reinforcement learning methods → RL theory and sample complexity
  111. CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset SelectionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  112. Rainbow Deep Q-Learning with Kinematics-Aware Design for Cooperative Delta and 3-RRS Parallel Robot InsertionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  113. Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPsDeep reinforcement learning methods → RL theory and sample complexity
  114. Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and DiversityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  115. Slicing and Dicing: Configuring Optimal Mixtures of ExpertsMixture-of-experts → Expert routing strategies
  116. Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations MatterLLM safety and security → Machine unlearning
  117. DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs +1
  118. Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional ExpansionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  119. Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity ScalingLLM reasoning → Reinforcement learning for reasoning
  120. Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic AnalysisLLM agents and tool use → Agent threats, guardrails and governance +2
  121. Human-Grounded Multimodal Benchmark with 900K-Scale Aggregated Student Response Distributions from Japan's National Assessment of Academic AbilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  122. Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  123. Every Bit, Everywhere, All at Once: A Binomial Multibit LLM WatermarkLLM safety and security → Watermarking generated content and models
  124. Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM DistillationLLM reasoning → Multimodal reasoning +1
  125. GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive SimulationsLLM agents and tool use → Financial trading and forecasting agents
  126. Seirenes: Adversarial Self-Play with Evolving Distractions for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  127. Unlocking UML Class Diagram Understanding in Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  128. Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency OperationsLLM reasoning → Spatial and embodied reasoning +1
  129. Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  130. OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning ModelsLLM reasoning → Multimodal reasoning +1
  131. Single-Shot HDR Recovery via a Video Diffusion PriorDiffusion models → Inverse problems and image restoration
  132. Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive ReasoningLLM reasoning → Test-time compute and efficient thinking
  133. RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq PredictionDiffusion models → Medical imaging and segmentation
  134. From Generic Correlation to Input-Specific Credit in On-Policy Self DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  135. When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  136. CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAGRetrieval-augmented generation → Agentic RAG, agents and memory +1
  137. Anti-Self-Distillation for Reasoning RL via Pointwise Mutual InformationLLM reasoning → Prompting and chain-of-thought reasoning +1
  138. Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMsEfficient LLM inference and serving → Audio and omni-modal token compression
  139. Targeted Tests for LLM Reasoning: An Audit-Constrained ProtocolLLM reasoning → Prompting and chain-of-thought reasoning
  140. HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving SimulationWorld models → World models for autonomous driving +1
  141. SoK: Unlearnability and Unlearning for Model DememorizationLLM safety and security → Machine unlearning
  142. Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided CalibrationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  143. Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved RegretDeep reinforcement learning methods → RL theory and sample complexity
  144. OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network TrainingSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  145. Dynamic Execution Commitment of Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  146. RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot LearningVision-language-action models → Generalist VLA models and benchmarks
  147. When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMsLLM reasoning → Hallucination detection and mitigation +1
  148. Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free AnswersLLM reasoning → Test-time compute and efficient thinking +1
  149. TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive ReasoningLLM reasoning → LLM reasoning for recommendation
  150. The DAWN of World-Action Interactive ModelsWorld models → Embodied and robot world models
  151. UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  152. Sharpen Your Flow: Sharpness-Aware Sampling for Flow MatchingDiffusion models → Flow matching, time series and science
  153. GeoR-Bench: Evaluating Geoscience Visual ReasoningLLM reasoning → Spatial and embodied reasoning
  154. Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage ReweightingLLM reasoning → Reinforcement learning for reasoning
  155. Fast MoE Inference via Predictive Prefetching and Expert ReplicationMixture-of-experts → Efficient MoE training and inference systems
  156. Primal-Dual Policy Optimization for Linear CMDPs with Adversarial LossesDeep reinforcement learning methods → RL theory and sample complexity
  157. PRISM: : Planning and Reasoning with Intent in Simulated Embodied EnvironmentsLLM reasoning → Spatial and embodied reasoning
  158. FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  159. AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing ExpensiveLLM agents and tool use → General LLM agent frameworks and benchmarks
  160. FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  161. A Study on Hidden Layer Distillation for Large Language Model Pre-TrainingKnowledge distillation → Knowledge distillation for LLMs
  162. Principled Design of Diffusion-based Optimizers for Inverse ProblemsDiffusion models → Inverse problems and image restoration
  163. Selective Off-Policy Reference Tuning with Plan GuidanceLLM reasoning → Reinforcement learning for reasoning
  164. CTFusion: A CTF-based Benchmark for LLM Agent EvaluationLLM agents and tool use → Agent threats, guardrails and governance
  165. Hedwig: Dynamic Autonomy for Coding Agents Under Local OversightLLM agents and tool use → Software engineering coding agents
  166. STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  167. Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow OptimizationLLM reasoning → Reinforcement learning for reasoning
  168. Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous AgentsLLM agents and tool use → Agent threats, guardrails and governance
  169. Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  170. Engagement Process: Rethinking the Temporal Interface of Action and ObservationLLM reasoning → Reasoning for agents, planning and code
  171. StoicLLM: Preference Optimization for Philosophical Alignment in Small Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  172. Efficient Adjoint Matching for Fine-tuning Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  173. FibQuant: Universal Vector Quantization for Random-Access KV-Cache CompressionEfficient LLM inference and serving → KV cache quantization
  174. LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  175. TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic BalancingDeep reinforcement learning methods → RL theory and sample complexity
  176. Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought ReasoningLLM reasoning → Reinforcement learning for reasoning
  177. SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D ImagesLLM reasoning → Spatial and embodied reasoning +2
  178. Breaking textitWinner-Takes-All: Cooperative Policy Optimization Improves Diverse LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  179. Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA ModelsVision-language-action models → Efficient VLA inference and adaptation
  180. Adaptive Teacher Exposure for Self-Distillation in LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  181. Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication TopologiesLLM reasoning → Reasoning for agents, planning and code +1
  182. Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency ExpertsMultimodal LLMs / vision-language models → Image editing and quality assessment
  183. Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State UncertaintyLLM agents and tool use → General LLM agent frameworks and benchmarks
  184. ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion ModelsDiffusion models → Inverse problems and image restoration
  185. A Mechanistic Investigation of Supervised Fine TuningMechanistic interpretability → SAE features and their applications
  186. VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  187. Generative Diffusion Prior Distillation for Long-Context Knowledge TransferDiffusion models → Diffusion foundations and sampling
  188. 20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation AloneMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  189. Attributing Emergence in Million-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
  190. fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculumLLM reasoning → Reinforcement learning for reasoning
  191. Deep Reasoning in General Purpose Agents via Structured Meta-CognitionLLM reasoning → Reasoning for agents, planning and code +1
  192. Behavioral Mode Discovery for Fine-tuning Multimodal Generative PoliciesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  193. LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  194. Test-Time Compute for Frozen Embedding Models through Agentic Program SearchLLM reasoning → Knowledge- and tool-augmented reasoning +1
  195. 3D-Belief: Embodied Belief Inference via Generative 3D World ModelingWorld models → Video-generation world models and simulators
  196. The tractability landscape of diffusion alignment: regularization, rewards, and computational primitivesDiffusion models → Diffusion and flow policies for robotics
  197. Options, Not Clicks: Lattice Refinement for Consent-Driven MCP AuthorizationLLM agents and tool use → Agent threats, guardrails and governance
  198. An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
  199. EduRiskX: A Neuro-Symbolic Framework with F-Logic Reasoning for Early Academic Risk Prediction
  200. Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs
  201. Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models
  202. AsymVerify at SemEval-2026 Task 6: Asymmetric Confidence-Gated Verification for Political Evasion Detection
  203. Preference Tuning as Spectral Update Reorganization
  204. MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers
  205. Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
  206. SemChunk-C: Semantic Segmentation for C Code
  207. Physical-AI: From Channel Awareness to Environmental Intelligence in 6G Wireless Networks
  208. How Well Do Large Language Models Capture Human Personality?
  209. Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science
  210. An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration
  211. SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
  212. Zero-shot Quantum Neural Architecture Search
  213. Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
  214. TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling
  215. Multi-market value-stacking: Battery control for combined imbalance participation and non-uniform FCR bidding
  216. From Index to Equity: Pre-Training Transformers for Stock Return Prediction
  217. Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
  218. Advanced Scientific Methodology Plays Rossini
  219. Automated Big Data Quality Assessment using Knowledge Graph Embeddings
  220. Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
  221. In-Context Learning Operates as Concept Subspace Learning
  222. Lossless Anti-Distillation Sampling
  223. The Routing and Filtering Structure of Attention
  224. Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches
  225. Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
  226. Multi-Pedestrian Safety Warning at Urban Intersections Use Case of Digital Twin
  227. Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
  228. Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods
  229. Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not
  230. Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production
  231. When Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates
  232. How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
  233. Metric-Gradient Projection for Stable Multi-Agent Policy Learning
  234. CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification
  235. Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery
  236. Trajectory-Aware Adaptive Inference in Object Detection Models
  237. Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
  238. Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
  239. Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining
  240. NOVA: Fundamental Limits of Knowledge Discovery Through AI
  241. Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
  242. Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
  243. Ready from Day 1: Population-Aware Coordination for Large-Scale Constrained Multi-Agent Systems
  244. Attention-Based Multimodal Survival Prediction with Cross-Modal Bilinear Fusion
  245. Phylogenetic Tree Inference with Tropical Axial Attention
  246. Physics-Grounded Adversarial Stain Augmentation with Calibrated Coverage Guarantees
  247. Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention
  248. Digital Twins as Synthetic Controls in Single-Arm Trials
  249. GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
  250. FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection
  251. Hessian Matching for Machine-Learned Coarse-Grained Molecular Dynamics
  252. Training Large Language Models to Predict Clinical Events
  253. AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers
  254. Linking Scalar-Intensity Language to Structural Polarization with Validated Signed-Network Measures
  255. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
  256. Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
  257. Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles
  258. Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
  259. SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions
  260. From Heuristics to Analytics: Forecasting Effort and Progress in Online Learning
  261. Identifying the nonlinear string dynamics with port-Hamiltonian neural networks
  262. Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization
  263. When to Trust Confidence Thresholding: Calibration Diagnostics for Pseudo-Labelled Regression
  264. WildPose: A Unified Framework for Robust Pose Estimation in the Wild
  265. Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs
  266. ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
  267. Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage
  268. Center-Manifold Reduction of Learning at Bifurcations: Interference and Rich Learning in Recurrent Neural Networks
  269. Multi-Quantile Regression for Extreme Precipitation Downscaling
  270. Predicting Channel Closures in the Lightning Network with Machine Learning
  271. Uncovering Symmetry Transfer in Large Language Models via Layer-Peeled Optimization
  272. State-Centric Decision Process
  273. Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data
  274. Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
  275. Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
  276. What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind
  277. ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis
  278. From Generalist to Specialist Representation
  279. BEHAVE: Real-Time Modeling of Human Systems as Observable Complex Dynamical Systems and Operational Objects for Physical AI
  280. Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics
  281. Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models
  282. Inline Critic Steers Image Editing
  283. Optimal sequential tests yield log-optimal e-processes
  284. A Five-Layer MLOps Architecture for Connected Automated Driving
  285. The End Justifies the Mean: A Linear Ranking Rule for Proportional Sequential Decisions
  286. Scaling Laws for Mixture Pretraining Under Data Constraints
  287. Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
  288. Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs
  289. Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations
  290. A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data
  291. Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
  292. FePySR: A Neural Feature Extraction Framework for Efficient and Scalable Symbolic Regression
  293. MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence
  294. Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
  295. UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning
  296. Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification
  297. A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention
  298. IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback
  299. On the Size Complexity and Decidability of First-Order Progression
  300. A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
  301. Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
  302. No One Knows the State of the Art in Geospatial Foundation Models
  303. Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
  304. Online Conformal Prediction: Enforcing monotonicity via Online Optimization
  305. Profit Maximization in Bilateral Trade against a Smooth Adversary
  306. scShapeBench: Discovering geometry from high dimensional scRNAseq data
  307. Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
  308. Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
  309. DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
  310. Optimization Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
  311. Learning to Decide with AI Assistance under Human-Alignment
  312. Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering
  313. DocAtlas: Multilingual Document Understanding Across 80+ Languages
  314. Perceived face similarity reflects inverse-generative and naturalistic discriminative objectives
  315. A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline
  316. Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
  317. Ensuring Logic in the Fog: Sound POMDP Synthesis with LTL Objectives
  318. CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
  319. Recurrent Transformer-Based Near- and Far-Field THz Wideband Channel Estimation for UM-MIMO
  320. Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL
  321. Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
  322. M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification
  323. Non-asymptotic quantisation of spherically symmetric distributions
  324. Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
  325. On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning
  326. EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera
  327. CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
  328. Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
  329. Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
  330. Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
  331. Task-Adaptive Embedding Refinement via Test-time LLM Guidance
  332. Learning, Fast and Slow: Towards LLMs That Adapt Continually
  333. OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
  334. High-arity Sample Compression
  335. Search Your Block Floating Point Scales!
  336. Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs
  337. A proximal gradient algorithm for composite log-concave sampling
  338. Enabling AI-Native Mobility in 6G: A Real-World Dataset for Handover, Beam Management, and Timing Advance
  339. The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events
  340. FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
  341. LychSim: A Controllable and Interactive Simulation Framework for Vision Research
  342. ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
  343. A Causal Language Modeling Detour Improves Encoder Continued Pretraining
  344. 3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark
  345. CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction
  346. PyroAdapt: Adapting Wildfire Prediction under Spatial Heterogeneity and Temporal Shift
  347. AOI-SSL: Self-Supervised Framework for Efficient Segmentation of Wire-bonded Semiconductors In Optical Inspection
  348. Learning Minimally Rigid Graphs with High Realization Counts
  349. Geometric Factual Recall in Transformers
  350. Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
  351. Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
  352. Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
  353. Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
  354. A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles
  355. Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
  356. Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning
  357. SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
  358. Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
  359. A Semi-Supervised Framework for Speech Confidence Detection using Whisper
  360. Scalable Token-Level Hallucination Detection in Large Language Models
  361. Pretraining Exposure Explains Popularity Judgments in Large Language Models
  362. Context Convergence Improves Answering Inferential Questions
  363. MetaColloc: Optimization-Free PDE Solving via Meta-Learned Basis Functions
  364. Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
  365. A Family of Quaternion-Valued Differential Evolution Algorithms for Numerical Function Optimization
  366. From Message-Passing to Linearized Graph Sequence Models
  367. δ-mem: Efficient Online Memory for Large Language Models
  368. A New Technique for AI Explainability using Feature Association Map
  369. Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation
  370. Neural-Schwarz Tiling for Geometry-Universal PDE Solving at Scale
  371. Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
  372. Online Learning-to-Defer with Varying Experts
  373. Manifold Sampling via Entropy Maximization
  374. Towards Automated Air Traffic Safety Assessment Around Non-Towered Airports Using Large Language Models
  375. A categorical error sensitivity index (ISEC): A preventive ordinal decision-support measure for irrecoverable errors in manual data entry systems
  376. Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
  377. VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
  378. LIDSA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management
  379. Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
  380. Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
  381. Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering
  382. In-context learning to predict critical transitions in dynamical systems
  383. KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks
  384. From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review
  385. Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
  386. GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
  387. EgoEV-HandPose: Egocentric 3D Hand Pose Estimation and Gesture Recognition with Stereo Event Cameras
  388. STRABLE: Benchmarking Tabular Machine Learning with Strings
  389. Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
  390. What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty
  391. Hypernetworks for Dynamic Feature Selection
  392. NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities
  393. Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
  394. CAD-feature enhanced machine learning for manufacturing effort estimation on sheet metal bending parts
  395. How Useful Is Cross-Domain Generalization for Training LLM Monitors?
  396. Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models
  397. Reconnecting Fragmented Citation Networks with Semantic Augmentation
  398. Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs
  399. From Image Hashing to Scene Change Detection
  400. H3D-MarNet: Wavelet-Guided Dual-Path Learning for Metal Artifact Suppression and CT Modality Transformation for Radiotherapy Workflows
  401. SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization
  402. PreScam: A Benchmark for Predicting Scam Progression from Early Conversations
  403. Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
  404. Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study
  405. Harness Engineering as Categorical Architecture
  406. Optimal Policy Learning under Budget and Coverage Constraints
  407. No More, No Less: Task Alignment in Terminal Agents
  408. TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion
  409. Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction
  410. Heterogeneous SoC Integrating an Open-Source Recurrent SNN Accelerator for Neuromorphic Edge Computing on FPGA
  411. Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
  412. Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
  413. Uncertainty Quantification for LLM-based Code Generation
  414. Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
  415. Overtrained, Not Misaligned
  416. Enhancing Domain Generalization in 3D Human Pose Estimation through Controllable Generative Augmentation
  417. A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
  418. ECTO: Exogenous-Conditioned Temporal Operator for Ultra-Short-Term Wind Power Forecasting
  419. Fair Conformal Classification via Learning Representation-Based Groups
  420. Probing Non-Equilibrium Grain Boundary Dynamics with XPCS and Domain-Adaptive Machine Learning
  421. Information-Theoretic Generalization Bounds for Sequential Decision Making
  422. Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
  423. DriftXpress: Faster Drifting Models via Projected RKHS Fields
  424. MolDeTox: Evaluating Language Model's Stepwise Fragment Editing for Molecular Detoxification
  425. A Deep Learning-based Receiver for Asynchronous Grant-Free Random Access in Control-to-Control Networks
  426. Multi-Task Representation Learning for Conservative Linear Bandits
  427. Lower bounds for one-layer transformers that compute parity
  428. UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
  429. On What We Can Learn from Low-Resolution Data
  430. From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
  431. Machine Learning for neutron source distributions
  432. Fused Gromov-Wasserstein Distance with Feature Selection
  433. ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization
  434. Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection
  435. MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
  436. CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
  437. PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
  438. Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations
  439. PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization
  440. EchoTracker2: Enhancing Myocardial Point Tracking by Modeling Local Motion
  441. BoolXLLM: LLM-Assisted Explainability for Boolean Models
  442. Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
  443. STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
  444. MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
  445. It's Not the Size: Harness Design Determines Operational Stability in Small Language Models
  446. To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands
  447. MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
  448. Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation
  449. Adaptive Multi-Round Allocation with Stochastic Arrivals
  450. Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization
  451. Sign Language Recognition and Translation for Low-Resource Languages: Challenges and Pathways Forward
  452. UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation
  453. Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration
  454. Elicitation-Augmented Bayesian Optimization
  455. The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments
  456. The Deepfakes We Missed: We Built Detectors for a Threat That Didn't Arrive
  457. BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding
  458. Clausal Deletion Backdoors for QBF: a Parameterized Complexity Approach
  459. PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting
  460. Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection
  461. TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images
  462. OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
  463. Do Language Models Encode Knowledge of Linguistic Constraint Violations?
  464. Learning plug-in surrogate endpoints for randomized experiments
  465. Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
  466. Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
  467. Rethink the Role of Neural Decoders in Quantum Error Correction
  468. OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
  469. Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
  470. Resilient Vision-Tabular Multimodal Learning under Modality Missingness
  471. Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
  472. 4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
  473. Spectral Vision Transformer for Efficient Tokenization with Limited Data
  474. Approximation Theory of Laplacian-Based Neural Operators for Reaction-Diffusion System
  475. SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
  476. What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization
  477. Efficient and Adaptive Human Activity Recognition via LLM Backbones
  478. FAME: Feature Activation Map Explanation on Image Classification and Face Recognition
  479. LLMs and the ZPD
  480. LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters
  481. Limits of Learning Linear Dynamics from Experiments
  482. Estimating Subgraph Importance with Structural Prior Domain Knowledge
  483. Robust Promptable Video Object Segmentation
  484. EDGER: EDge-Guided with HEatmap Refinement for Generalizable Image Forgery Localization
  485. CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference
  486. Towards Visually-Guided Movie Subtitle Translation for Indic Languages
  487. A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
  488. Random-Set Graph Neural Networks
  489. On the Limitations of Large Language Models for Conceptual Database Modeling
  490. QDSB: Quantized Diffusion Schr"odinger Bridges
  491. On Predicting the Post-training Potential of Pre-trained LLMs
  492. Optimizing 4D Wires for Sparse 3D Abstraction
  493. Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization
  494. Cooperative Robotics Reinforced by Collective Perception for Traffic Moderation
  495. NOFE - Neural Operator Function Embedding
  496. Assessment of cloud and associated radiation fields from a GAN stochastic cloud subcolumn generator
  497. H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
  498. Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
  499. What Does It Mean for a Medical AI System to Be Right?
  500. Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters
  501. Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement
  502. Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution
  503. When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
  504. RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
  505. STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
  506. Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
  507. Understanding Sample Efficiency in Predictive Coding
  508. Rethinking Positional Encoding for Neural Vehicle Routing
  509. Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 Models
  510. Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
  511. AccLock: Unlocking Identity with Heartbeat Using In-Ear Accelerometers
  512. Mobile Traffic Camera Calibration from Road Geometry for UAV-Based Traffic Surveillance
  513. Toward Modeling Player-Specific Chess Behaviors
  514. Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
  515. From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
  516. Sobolev Regularized MMD Gradient Flow
  517. Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data
  518. Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning
  519. Modulation Consistency-based Contrastive Learning for Self-Supervised Automatic Modulation Classification
  520. LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
  521. Information theoretic underpinning of self-supervised learning by clustering
  522. When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI
  523. GATA2Floor: Graph attention for floor counting in street-view facades
  524. Concordance Comparison as a Means of Assembling Local Grammars
  525. EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models
  526. Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
  527. Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
  528. Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
  529. A Fast and Energy-Efficient Latch-Based Memristive Analog Content-Addressable Memory
  530. Martingale-Consistent Self-Supervised Learning
  531. Probabilistic Calibration Is a Trainable Capability in Language Models
  532. Minimax Rates and Spectral Distillation for Tree Ensembles
  533. Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
  534. Multi-Timescale Conductance Spiking Networks: A Sparse, Gradient-Trainable Framework with Rich Firing Dynamics for Enhanced Temporal Processing
  535. Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media
  536. REFNet++: Multi-Task Efficient Fusion of Camera and Radar Sensor Data in Bird's-Eye Polar View
  537. RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
  538. Fed-BAC: Federated Bandit-Guided Additive Clustering in Hierarchical Federated Learning
  539. MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
  540. Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
  541. Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
  542. Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
  543. SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
  544. Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention
  545. Choosing features for classifying multiword expressions
  546. Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
  547. Revisiting Shadow Detection from a Vision-Language Perspective
  548. Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control
  549. Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling
  550. A nonlinear extension of parametric model embedding for dimensionality reduction in parametric shape design
  551. DiffSegLung: Diffusion Radiomic Distillation for Unsupervised Lung Pathology Segmentation
  552. Focusable Monocular Depth Estimation
  553. Towards Visually Grounded Multimodal Summarization via Cross-Modal Transformer and Gated Attention
  554. Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
  555. Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection
  556. BronchoLumen: Analysis of recent YOLO-based architectures for real-time bronchial orifice detection in video bronchoscopy
  557. Training-Inference Consistent Segmented Execution for Long-Context LLMs
  558. WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
  559. Online Continual Learning with Dynamic Label Hierarchies
  560. U-STS-LLM A Unified Spatio-Temporal Steered Large Language Model for Traffic Prediction and Imputation
  561. EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
  562. Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
  563. Unlocking Compositional Generalization in Continual Few-Shot Learning
  564. GRAFT: Graph-Tokenized LLMs for Tool Planning
  565. ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
  566. WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
  567. Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning
  568. Compositional Neural Operators for Multi-Dimensional Fluid Dynamics
  569. Shaping Zero-Shot Coordination via State Blocking
  570. Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI
  571. Partial Model Sharing Improves Byzantine Resilience in Federated Conformal Prediction
  572. ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes
  573. OOM-Free Alpamayo via CPU-GPU Memory Swapping for Vision-Language-Action Models
  574. A CAP-like Trilemma for Large Language Models: Correctness, Non-bias, and Utility under Semantic Underdetermination
  575. Cochise: A Reference Harness for Autonomous Penetration Testing
  576. Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
  577. Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
  578. The Value of Finite Observation in Positive-Data Learning of Multiple Context-Free Languages
  579. Learning U-Statistics with Active Inference
  580. MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
  581. Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances
  582. PRISM: A Geometric Risk Bound for Decomposing Drift into Scale, Shape, and Head
  583. Exact Stiefel Optimization for Probabilistic PLS: Closed-Form Updates, Error Bounds, and Calibrated Uncertainty
  584. GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization
  585. DiffScore: Text Evaluation Beyond Autoregressive Likelihood
  586. EpiCastBench: Datasets and Benchmarks for Multivariate Epidemic Forecasting
  587. Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
  588. PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
  589. A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods
  590. NexOP: Joint Optimization of NEX-Aware k-space Sampling and Image Reconstruction for Low-Field MRI
  591. Efficient LLM-based Advertising via Model Compression and Parallel Verification
  592. Ada-MK: Adaptive MegaKernel Optimization via Automated DAG-based Search for LLM Inference
  593. The Midas Touch for Metric Depth
  594. BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
  595. Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation
  596. TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning
  597. FedOUI: OUI-Guided Client Weighting for Federated Aggregation
  598. Dual-Temporal LSTM with Hybrid Attention for Airline Passenger Load Factor Forecasting: Integrating Intra-Flight and Inter-Flight Booking Dynamics
  599. TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles
  600. A Composite Activation Function for Learning Stable Binary Representations
  601. ScribbleDose: Scribble-Guided Dose Prediction in Radiotherapy
  602. A Controlled Counterexample to Strong Proxy-Based Explanations of OOD Performance: in a Fixed Pretraining-and-Probing Setup
  603. VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
  604. Optimal LTLf Synthesis
  605. Checkup2Action: A Multimodal Clinical Check-up Report Dataset for Patient-Oriented Action Card Generation
  606. Read, Grep, and Synthesize: Diagnosing Cross-Domain Seed Exposure for LLM Research Ideation
  607. Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies
  608. Multi-Narrow Transformation as a Single-Model Ensemble: Boundary Conditions, Mechanisms, and Failure Modes
  609. Efficient and provably convergent end-to-end training of deep neural networks with linear constraints
  610. OverNaN: NaN-Aware Oversampling for Imbalanced Learning with Meaningful Missingness
  611. EqOD: Symmetry-Informed Stability Selection for PDE Identification
  612. XWOD: A Real-World Benchmark for Object Detection under Extreme Weather Conditions
  613. PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting
  614. Controllable User Simulation
  615. Post-ADC Inference: Valid Inference After Active Data Collection
  616. Hierarchical LLM-Driven Control for HAPS-Assisted UAV Networks: Joint Optimization of Flight and Connectivity
  617. LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
  618. Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations
  619. Decaf: Improving Neural Decompilation with Automatic Feedback and Search
  620. PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
  621. The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested
  622. A Mimetic Detector for Adversarial Image Perturbations
  623. Adaptive Calibration in Non-Stationary Environments
  624. 3DGS3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering
  625. Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation
  626. A Barrier-Metric First-Order Method for Linearly Constrained Bilevel Optimization
  627. Deep Probabilistic Unfolding for Quantized Compressive Sensing
  628. On the Approximation Complexity of Matrix Product Operator (MPO) Born Machines
  629. Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe
  630. CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
  631. Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsals
  632. Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification
  633. Deep Minds and Shallow Probes
  634. Conditional Memory Enhanced Item Representation for Generative Recommendation
  635. Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
  636. Instruct-ICL: Instruction-Guided In-Context Learning for Post-Disaster Damage Assessment
  637. Beyond Masks: The Case for Medical Image Parsing
  638. Diabetic Retinopathy Classification using Downscaling Algorithms and Deep Learning
  639. FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling
  640. PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming
  641. Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
  642. Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
  643. What Do EEG Foundation Models Capture from Human Brain Signals?
  644. MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification
  645. A Boundary-Aware Non-parametric Granular-Ball Classifier Based on Minimum Description Length
  646. More Than Meets the Eye: A Semantics-Aware Traffic Augmentation Framework for Generalizable Website Fingerprinting
  647. AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment
  648. MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization
  649. Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors
  650. Transformer Interpretability from Perspective of Attention and Gradient
  651. Revisiting Privacy Preservation in Brain-Computer Interfaces: Conceptual Boundaries, Risk Pathways, and a Protection-Strength Grading Framework
  652. JACoP: Joint Alignment for Compliant Multi-Agent Prediction
  653. HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
  654. TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning
  655. An Empirical Study of Automating Agent Evaluation
  656. Causal Algorithmic Recourse: Foundations and Methods
  657. Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers
  658. LPDP: Inference-Time Reward Control for Variable-Length DNA Generation with Edit Flows
  659. Causal Bias Detection in Generative Artificial Intelligence
  660. PresentAgent-2: Towards Generalist Multimodal Presentation Agents
  661. Causal Fairness for Survival Analysis
  662. CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing
  663. gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods
  664. Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
  665. Human-AI Productivity Paradoxes: Modeling the Interplay of Skill, Effort, and AI Assistance
  666. Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
  667. Gradient-Free Noise Optimization for Reward Alignment in Generative Models