mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 8 May 2026

783 papers

  1. PrimeAgentOrchestrator: Memory-Primed Agent Spawning for Personal AI InfrastructureLLM agents and tool use → Agent memory systems
  2. Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking +1
  3. Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'HallucinationsMixture-of-experts → MoE large language models
  4. MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic ModelsLLM reasoning → Clinical and biomedical applications +1
  5. PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  6. CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  7. GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional SettingsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  8. PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval CorruptionRetrieval-augmented generation → Privacy and security of RAG
  9. SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  10. Position: The Term "Machine Unlearning" Is Overused in LLMsLLM safety and security → Machine unlearning
  11. Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. Business Utility of Large Language Models as Exploratory Data Analysis AgentsLLM agents and tool use → Financial trading and forecasting agents
  13. StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. LARGER: Lexically Anchored Repository Graph Exploration and RetrievalLLM agents and tool use → Software engineering coding agents
  15. PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution ShiftState-space sequence models (S4, Mamba) → Physiological signal modeling
  16. Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational OverlapMixture-of-experts → Expert routing strategies
  17. HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC SupportRetrieval-augmented generation → RAG pipeline design and evaluation
  18. PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and RemediationLLM agents and tool use → Agent threats, guardrails and governance
  19. Goal-Conditioned Supervised Learning for LLM Fine-TuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  20. DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  21. GEAR: Genetic AutoResearch for Agentic Code EvolutionLLM agents and tool use → Web, search, and research agents
  22. Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  23. Why Retrying Fails: Context Contamination in LLM Agent PipelinesLLM agents and tool use → Software engineering coding agents
  24. ZAYA1-VL-8B Technical ReportMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  25. MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow MatchingDiffusion models → Flow matching, time series and science
  26. Can Revealed Preferences Clarify LLM Alignment and Steering?LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  27. Human-Inspired Memory Architecture for LLM AgentsLLM agents and tool use → Agent memory systems
  28. MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a ServiceLLM reasoning → Reinforcement learning for reasoning +2
  29. Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information BottleneckLLM agents and tool use → Agent skill learning and evolution
  30. FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. Results and Retrospective Analysis of the CODS 2025 AssetOpsBench ChallengeLLM safety and security → Prompt injection and agent security
  32. Quantile-Coupled Flow Matching for Distributional Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  33. A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  34. Trajectory-Consistent Flow Matching for Robust Visuomotor Policy LearningDiffusion models → Diffusion and flow policies for robotics
  35. NARRA-Gym for Evaluating Interactive Narrative AgentsLLM agents and tool use → Multimodal and embodied agents
  36. MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMsLLM reasoning → Mathematical reasoning
  37. Latent Personality Alignment: Improving Harmlessness Without Mentioning HarmsLLM safety and security → Safety alignment, refusal and guardrails
  38. Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and SteerabilityLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  39. AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease CareLLM agents and tool use → Medical and scientific domain agents
  40. When Independent Sampling Outperforms Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  41. Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool CallingLLM reasoning → Reasoning for agents, planning and code +1
  42. Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language ModelsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  43. PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding AgentsLLM agents and tool use → Software engineering coding agents
  44. Behavioral Determinants of Deployed AI Agents in Social Networks: A Multi-Factor Study of Personality, Model, and Guardrail SpecificationLLM agents and tool use → Social simulation and multi-agent debate
  45. Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated AssessmentLLM agents and tool use → Medical and scientific domain agents
  46. When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent NetworksLLM agents and tool use → Agent threats, guardrails and governance +1
  47. NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic PhysicsLLM reasoning → Spatial and embodied reasoning +1
  48. Zero-shot Imitation Learning by Latent Topology MappingOffline RL and imitation learning from data → Robot manipulation imitation learning
  49. Measuring What Matters: Benchmarking Generative, Multimodal, and Agentic AI in HealthcareLLM agents and tool use → Medical and scientific domain agents
  50. Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  51. TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as PurifiersDiffusion models → Robustness, privacy and adversarial aspects
  52. A Dataset of Agentic AI Coding Tool ConfigurationsLLM agents and tool use → Software engineering coding agents
  53. Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness +1
  54. The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-PlayLLM reasoning → Reasoning for agents, planning and code +1
  55. Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AILLM agents and tool use → Social simulation and multi-agent debate
  56. Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at OnceDiffusion models → Flow matching, time series and science
  57. Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RLDeep reinforcement learning methods → RL theory and sample complexity
  58. SYNCR: A Cross-Video Reasoning Benchmark with Synthetic GroundingLLM reasoning → Multimodal reasoning +1
  59. Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language ModelsLLM reasoning → Spatial and embodied reasoning
  60. AIPO: Learning to Reason from Active InteractionLLM reasoning → Reinforcement learning for reasoning
  61. CoCoDA: Co-evolving Compositional DAG for Tool-Augmented AgentsLLM agents and tool use → Tool learning and function calling
  62. Exploring and Exploiting Stability in Latent Flow MatchingDiffusion models → Flow matching, time series and science
  63. Geometry-Aware Discretization Error of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  64. SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  65. Quantifiable Uncertainty: A Stochastic Consensus Multi-Agent RAG Framework for Robust Malware DetectionRetrieval-augmented generation → Privacy and security of RAG
  66. SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt OptimizationLLM agents and tool use → Agent threats, guardrails and governance
  67. Reinforcement Learning for Scalable and Trustworthy Intelligent SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  68. MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGsLLM agents and tool use → Agent memory systems +2
  69. PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
  70. SWE Atlas: Benchmarking Coding Agents Beyond Issue ResolutionLLM agents and tool use → Software engineering coding agents
  71. Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative CriteriaLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  72. How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model CircuitsMechanistic interpretability → Circuits and mechanistic analysis
  73. Sanity Checks for Long-Form Hallucination DetectionLLM reasoning → Hallucination detection and mitigation
  74. What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow MatchingDiffusion models → Flow matching, time series and science
  75. CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  76. P-Flow: Proxy-gradient Flows for Linear Inverse ProblemsDiffusion models → Flow matching, time series and science
  77. Interactive Critique-Revision Training for Reliable Structured LLM GenerationLLM reasoning → Reinforcement learning for reasoning
  78. SDG-MoE: Signed Debate Graph Mixture-of-ExpertsMixture-of-experts → MoE large language models
  79. When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular DomainsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  80. RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV CacheEfficient LLM inference and serving → KV cache quantization
  81. FlashSVD v1.5: Making Low-Rank Transformers Inference Actually FastEfficient LLM inference and serving → KV cache optimization
  82. In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot ClassificationMechanistic interpretability → Probing deception, bias and beliefs
  83. Hierarchical Mixture-of-Experts with Two-Stage OptimizationMixture-of-experts → Expert routing strategies
  84. HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective ControlLLM reasoning → Reinforcement learning for reasoning
  85. Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I BackdoorsLLM safety and security → Backdoor and data poisoning attacks
  86. LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual ObservationsWorld models → Latent predictive world models +1
  87. Mitigating Many-shot Jailbreak Attacks with One Single DemonstrationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  88. Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video ReasoningLLM reasoning → Multimodal reasoning +1
  89. Insider Attacks in Multi-Agent LLM Consensus SystemsWorld models → World models for language agents +1
  90. Execution Envelopes: A Shared Admission Contract for Backend AI Execution RequestsLLM agents and tool use → Agent threats, guardrails and governance
  91. 123D: Unifying Multi-Modal Autonomous Driving Data at ScaleEnd-to-end autonomous driving → End-to-end system architecture
  92. LLMs Improving LLMs: Agentic Discovery for Test-Time ScalingLLM reasoning → Reasoning for agents, planning and code +1
  93. VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer SelectionLLM reasoning → Test-time compute and efficient thinking
  94. Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  95. Flow-OPD: On-Policy Distillation for Flow Matching ModelsDiffusion models → Diffusion and flow policies for robotics +2
  96. Rubric-Grounded RL: Structured Judge Rewards for Generalizable ReasoningLLM reasoning → Reinforcement learning for reasoning
  97. The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  98. CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget AllocationLLM reasoning → Knowledge- and tool-augmented reasoning
  99. Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise OptimizationDiffusion models → Video generation
  100. Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPsDeep reinforcement learning methods → RL theory and sample complexity
All 783
  1. Beyond Pairs: Your Language Model is Secretly Optimizing a Preference GraphLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  2. Object Hallucination-Free Reinforcement Unlearning for Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  3. STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal GenerationEfficient LLM inference and serving → Visual token pruning in multimodal models
  4. Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game LearnersLLM reasoning → Reasoning for agents, planning and code
  5. Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request LifecyclesLLM agents and tool use → Software engineering coding agents
  6. Learning CLI Agents with Structured Action Credit under Selective ObservationLLM agents and tool use → Reinforcement learning for LLM agents
  7. Abductive Reasoning with Probabilistic CommonsenseLLM reasoning → Reasoning benchmarks and evaluation
  8. Interpreting Reinforcement Learning Agents with SusceptibilitiesDeep reinforcement learning methods → RL theory and sample complexity
  9. Tool Calling is Linearly Readable and Steerable in Language ModelsLLM agents and tool use → Tool learning and function calling
  10. Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic InterventionsMechanistic interpretability → Steering and interpreting LLM reasoning
  11. GLiGuard: Schema-Conditioned Classification for LLM SafeguardLLM safety and security → Safety alignment, refusal and guardrails
  12. Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time FeedbackSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  13. HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  14. DVD: Discrete Voxel Diffusion for 3D Generation and EditingDiffusion models → 3D, point cloud and scene generation
  15. When Diffusion Model Can Ignore Dimension: An Entropy-Based TheoryDiffusion models → Diffusion foundations and sampling
  16. TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  17. TraceFix: Repairing Agent Coordination Protocols with TLA+ CounterexamplesLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. How to Train Your Latent Diffusion Language Model Jointly With the Latent SpaceDiffusion models → Discrete and text diffusion
  19. One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA PolicyWorld models → Embodied and robot world models +1
  20. AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  21. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated DistillationDiffusion models → Audio, speech and music
  22. Tree SAE: Learning Hierarchical Feature Structures in Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  23. What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent DiffusionDiffusion models → Diffusion foundations and sampling
  24. Consistency Regularised Gradient Flows for Inverse ProblemsDiffusion models → Inverse problems and image restoration
  25. Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label EnhancementLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  26. Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward ModelsLLM reasoning → Multimodal reasoning +1
  27. KL for a KL: On-Policy Distillation with Control Variate BaselineLLM reasoning → Prompting and chain-of-thought reasoning +1
  28. ADKO: Agentic Decentralized Knowledge OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  29. On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance SystemsDiffusion models → Robustness, privacy and adversarial aspects
  30. Actor-Critic Algorithm for Dynamic Expectile and CVaRDeep reinforcement learning methods → RL theory and sample complexity
  31. RelAgent: LLM Agents as Data Scientists for Relational LearningLLM agents and tool use → Web, search, and research agents
  32. CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack ScenariosLLM agents and tool use → Agent threats, guardrails and governance
  33. Anisotropic Modality AlignMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. Scaling Categorical Flow MapsDiffusion models → Discrete and text diffusion
  35. GazeVLM: Active Vision via Internal Attention Control for Multimodal ReasoningLLM reasoning → Multimodal reasoning
  36. Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  37. Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  38. SARA: Semantically Adaptive Relational Alignment for Video Diffusion ModelsDiffusion models → Video generation
  39. NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action ModelsWorld models → Embodied and robot world models
  40. Tracing Uncertainty in Language Model "Reasoning"LLM reasoning → Test-time compute and efficient thinking
  41. FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion DistancesRetrieval-augmented generation → Vector search and ANN indexes
  42. Coding Agents Don't Know When to ActLLM agents and tool use → Software engineering coding agents
  43. TextLDM: Language Modeling with Continuous Latent DiffusionDiffusion models → Image generation, text-to-image and editing
  44. Flow Matching for Count DataDiffusion models → Flow matching, time series and science
  45. Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMsMixture-of-experts → MoE large language models
  46. SARC: A Governance-by-Architecture Framework for Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  47. SOD: Step-wise On-policy Distillation for Small Language Model AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  48. Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language ModelsEfficient LLM inference and serving → Efficient reasoning and agent inference
  49. An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  50. SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  51. Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language ModelsDiffusion models → Diffusion foundations and sampling
  52. DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail DomainLLM reasoning → Reasoning for agents, planning and code +1
  53. Future Validity is the Missing Statistic: From Impossibility to Phi-Estimation for Grammar-Faithful Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  54. Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix WorksLLM reasoning → Reinforcement learning for reasoning
  55. The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output LimitsLLM reasoning → Prompting and chain-of-thought reasoning
  56. Structured Coupling for Flow MatchingDiffusion models → Flow matching, time series and science
  57. Debiased Counterfactual Generation via Flow Matching from ObservationsDiffusion models → Diffusion foundations and sampling
  58. Stochastic Transition-Map Distillation for Fast Probabilistic InferenceDiffusion models → Diffusion foundations and sampling +1
  59. Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL ReasoningLLM reasoning → Reinforcement learning for reasoning
  60. Reliable Chain-of-Thought via Prefix ConsistencyLLM reasoning → Test-time compute and efficient thinking
  61. Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  62. MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic AuditingLLM reasoning → Reasoning for agents, planning and code +1
  63. Statistical Convergence of Spherical First Hitting Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  64. Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery SimulatorsLLM reasoning → Causal reasoning in LLMs
  65. Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal StatesLLM reasoning → Reinforcement learning for reasoning
  66. PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  67. Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  68. How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention MechanismOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  69. VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention NetworkState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  70. Implicit Preference Alignment for Human Image AnimationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  71. From Pixels to Prompts: Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  72. LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical DocumentationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  73. Is the Future Compatible? Diagnosing Dynamic Consistency in World Action ModelsWorld models → Embodied and robot world models
  74. Tessellations of Semi-Discrete Flow MatchingDiffusion models → Flow matching, time series and science
  75. Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  76. InterLV-Search: Benchmarking Interleaved Multimodal Agentic SearchLLM agents and tool use → Multimodal and embodied agents
  77. MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage SignalsLLM agents and tool use → Software engineering coding agents
  78. LiteGUI: Distilling Compact GUI Agents with Reinforcement LearningLLM agents and tool use → GUI and mobile agents +2
  79. Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion TransformersDiffusion models → Video generation +1
  80. ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought CompressionLLM reasoning → Test-time compute and efficient thinking
  81. DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  82. Cross-Modal Backdoors in Multimodal Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  83. Efficient Data Selection for Multimodal Models via Incremental Optimization UtilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  84. SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit DemotionLLM safety and security → Machine unlearning +1
  85. Vaporizer: Breaking Watermarking Schemes for Large Language Model OutputsLLM safety and security → Watermarking generated content and models
  86. AudioFace: Language-Assisted Speech-Driven Facial Animation with Multimodal Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  87. ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  88. ForgeVLA: Federated Vision-Language-Action Learning without Language AnnotationsVision-language-action models → Generalist VLA models and benchmarks
  89. HBEE: Human Behavioral Entropy Engine -- Pre-Registered Multi-Agent LLM Simulation of Peer-Suspicion-Based Detection InversionLLM agents and tool use → Agent threats, guardrails and governance
  90. SEIF: Self-Evolving Reinforcement Learning for Instruction FollowingSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training +1
  91. Think-with-Rubrics: From External Evaluator to Internal Reasoning GuidanceLLM reasoning → Reinforcement learning for reasoning
  92. EditRefiner: A Human-Aligned Agentic Framework for Image Editing RefinementLLM agents and tool use → Multimodal and embodied agents +1
  93. Inference-Time Attribute Distribution Alignment for Unconditional DiffusionDiffusion models → Diffusion foundations and sampling
  94. Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  95. ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target ReferringLLM reasoning → Multimodal reasoning
  96. OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided FuzzingLLM agents and tool use → Agent threats, guardrails and governance +1
  97. GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability OptimizationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  98. Rubric-based On-policy DistillationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  99. Offline Policy Optimization with Posterior SamplingOffline RL and imitation learning from data → Offline RL algorithms +1
  100. ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D GenerationWorld models → Video-generation world models and simulators
  101. Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric AdaptationVision-language-action models → Reinforcement learning and post-training
  102. RELO: Reinforcement Learning to Localize for Visual Object TrackingDeep reinforcement learning methods → RL training of language and agent models
  103. MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via SimulationEnd-to-end autonomous driving → End-to-end system architecture
  104. A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and ApplicationsLLM agents and tool use → Agent skill learning and evolution
  105. GraphReAct: Reasoning and Acting for Multi-step Graph InferenceLLM reasoning → Knowledge- and tool-augmented reasoning
  106. Confidence-Aware Alignment Makes Reasoning LLMs More ReliableLLM reasoning → Test-time compute and efficient thinking +1
  107. Tools as Continuous Flow for Evolving Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  108. RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and SegmentationLLM reasoning → Multimodal reasoning
  109. Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  110. Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token PerspectiveLLM reasoning → Reinforcement learning for reasoning
  111. SparseRL-Sync: Lossless Weight Synchronization with ~100x Less CommunicationDeep reinforcement learning methods → Deep RL algorithms and representations
  112. Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion RepresentationsDiffusion models → Diffusion foundations and sampling
  113. GEM: Generating LiDAR World Model via Deformable MambaWorld models → World modeling from LiDAR generation +1
  114. Activation Differences Reveal Backdoors: A Comparison of SAE ArchitecturesMechanistic interpretability → Steering and probing for LLM safety
  115. Generative Modeling with Flux MatchingDiffusion models → Flow matching, time series and science
  116. Amortized-Precision Quantization for Early-Exit Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
  117. Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-TrainingLLM reasoning → Test-time compute and efficient thinking
  118. LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit VerificationLLM reasoning → Test-time compute and efficient thinking
  119. AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action ModelsVision-language-action models → Tactile, force-aware and humanoid VLA
  120. Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-ThoughtsLLM reasoning → Prompting and chain-of-thought reasoning
  121. BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory ManipulationLLM reasoning → Spatial and embodied reasoning +1
  122. SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal ModelLLM agents and tool use → Reinforcement learning for LLM agents
  123. EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video StreamsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  124. Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-TrainingWorld models → Embodied and robot world models +1
  125. Predictive but Not Plannable: RC-aux for Latent World ModelsWorld models → Latent predictive world models
  126. Signal Reshaping for GRPO in Weak-Feedback Agentic Code RepairLLM reasoning → Reasoning for agents, planning and code +1
  127. Structured Role-Aware Policy Optimization for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  128. From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAGRetrieval-augmented generation → Privacy and security of RAG
  129. MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble LearningRetrieval-augmented generation → Privacy and security of RAG +1
  130. When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language ModelsMixture-of-experts → Expert routing strategies
  131. LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion SamplingDiffusion models → Diffusion foundations and sampling
  132. Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost ReasoningLLM reasoning → Clinical and biomedical applications +1
  133. Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  134. PaT: Planning-after-Trial for Efficient Test-Time Code GenerationLLM reasoning → Reasoning for agents, planning and code
  135. SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree DraftingEfficient LLM inference and serving → Speculative decoding
  136. MEMOREPAIR: Barrier-First Cascade Repair in Agentic MemoryLLM agents and tool use → Agent memory systems
  137. Teaching Language Models to Think in CodeLLM reasoning → Reasoning for agents, planning and code +1
  138. Reformulating KV Cache Eviction Problem for Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  139. CASCADE: Context-Aware Relaxation for Speculative Image DecodingEfficient LLM inference and serving → Fast autoregressive visual generation
  140. On the Robustness of Distribution Support under Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
  141. Improved Model-based Reinforcement Learning with Smooth KernelsDeep reinforcement learning methods → RL theory and sample complexity
  142. HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  143. DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  144. Towards Autonomous Business Intelligence via Data-to-Insight Discovery AgentLLM agents and tool use → Web, search, and research agents
  145. PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming ChatSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  146. Three-in-One World Model: Energy-Based Consistency, Prediction, and Counterfactual Inference for Marketing InterventionWorld models → World models for language agents
  147. See Tomorrow, Act Today: Foresight-Driven Autonomous DrivingWorld models → World models for autonomous driving +1
  148. Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget ControlLLM reasoning → Test-time compute and efficient thinking +1
  149. Learning Agent Routing From Early ExperienceLLM agents and tool use → General LLM agent frameworks and benchmarks
  150. HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search AgentsDeep reinforcement learning methods → RL training of language and agent models
  151. Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  152. Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information ApproachOffline RL and imitation learning from data → Robot manipulation imitation learning
  153. Rethinking Experience Utilization in Self-Evolving Language Model AgentsLLM reasoning → Reasoning for agents, planning and code +2
  154. SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure ScenariosLLM agents and tool use → Software engineering coding agents
  155. Topic Is Not Agenda: A Citation-Community Audit of Text EmbeddingsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  156. Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMsLLM reasoning → Reinforcement learning for reasoning
  157. Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  158. MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical LibrariesLLM reasoning → Mathematical reasoning
  159. Fine-tuning a vision-language model for fracture-surface morphology recognitionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  160. Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action RecognitionLLM reasoning → Spatial and embodied reasoning
  161. Structural Rationale Distillation via Reasoning Space CompressionLLM reasoning → Prompting and chain-of-thought reasoning +1
  162. Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic AgentsLLM agents and tool use → Social simulation and multi-agent debate +1
  163. Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVRLLM reasoning → Reinforcement learning for reasoning
  164. Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub ActionsLLM agents and tool use → Software engineering coding agents
  165. Region4Web: Rethinking Observation Space Granularity for Web AgentsLLM reasoning → Reasoning for agents, planning and code +1
  166. From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  167. RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM RecommendationLLM reasoning → LLM reasoning for recommendation
  168. Convergence and Emergence of In-Context Reinforcement Learning with Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  169. RepoZero: Can LLMs Generate a Code Repository from Scratch?LLM agents and tool use → Software engineering coding agents
  170. Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVRLLM reasoning → Reinforcement learning for reasoning
  171. Switchcraft: AI Model Router for Agentic Tool CallingLLM agents and tool use → General LLM agent frameworks and benchmarks
  172. Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded ReliabilityLLM agents and tool use → Agent threats, guardrails and governance
  173. Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual ReasoningLLM reasoning → Multimodal reasoning +1
  174. Theoretical Limits of Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  175. Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau DriftDeep reinforcement learning methods → RL theory and sample complexity
  176. ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool ReasoningLLM reasoning → Clinical and biomedical applications +1
  177. Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics
  178. TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching ModelsDiffusion models → Flow matching, time series and science
  179. Actor-Critic with Active Importance SamplingDeep reinforcement learning methods → RL theory and sample complexity
  180. Membership Inference Attacks on Vision-Language-Action ModelsLLM safety and security → Membership inference attacks
  181. ImplantMamba: Long-range Sequential Modeling Mamba For Dental Implant Position PredictionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  182. Learning Visual Feature-Based World Models via Residual Latent ActionWorld models → Embodied and robot world models +1
  183. Test-Time Compositional Generalization in Diffusion Models via Concept DiscoveryDiffusion models → Diffusion foundations and sampling
  184. Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
  185. Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social SystemsLLM agents and tool use → Social simulation and multi-agent debate
  186. WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki SystemsEfficient LLM inference and serving → KV cache optimization
  187. 2.5-D Decomposition for LLM-Based Spatial ConstructionLLM reasoning → Spatial and embodied reasoning
  188. From Assistance to Agency: Rethinking Autonomy and Control in CI/CD PipelinesLLM agents and tool use → Agent threats, guardrails and governance
  189. MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical EnvironmentsLLM agents and tool use → Medical and scientific domain agents
  190. From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RLDeep reinforcement learning methods → Deep RL algorithms and representations
  191. GSM-SEM: Benchmark and Framework for Generating Semantically Variant AugmentationsLLM reasoning → Mathematical reasoning
  192. VLM-based automatic multi-granularity graph representation of building layouts for design informatics
  193. DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation
  194. Heterogeneous Element-Aware Cross-Version Differencing of Scientific Documents via Layout-Aware Alignment and Structure-Aware Reasoning
  195. ReportMedSAM: Guiding Segmentation Through Radiology Reports
  196. DialogueVPR: Towards Conversational Visual Place Recognition
  197. T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting
  198. Limits of Reliability and Scaling in Language Models
  199. Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect
  200. Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework
  201. Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering
  202. Eigenism: Ethics for a Human-AI Future
  203. GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
  204. Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media
  205. Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts
  206. Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects
  207. Multivariate Financial Forecasting using the Chronos Time Series Foundation Models
  208. Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks
  209. A Task-Agnostic Algebraic Integrity Metric for Event-Camera Streams Toward SOTIF-Compliant Perception using Pearson Correlation Coefficient
  210. Generative 3D Gaussians with Learned Density Control
  211. Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?
  212. Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation
  213. Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
  214. A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems
  215. LoopQ: Quantization for Looped Language Models
  216. Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
  217. Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
  218. Rotation-Preserving Supervised Fine-Tuning
  219. Context-Gated Associative Retrieval: From Theory to Transformers
  220. MMTB: Evaluating Terminal Agents on Multimedia-File Tasks
  221. MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration
  222. Finer is Better (with the Right Scaling)
  223. Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks
  224. CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
  225. Structure-Preserving Reconstruction of Convex Lipschitz Functionals on Hilbert Spaces from Finite Samples
  226. Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies
  227. VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
  228. Learnability and Competition in High-Dimensional Multi-Component ICA
  229. A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
  230. Evaluating Developmental Cognition Capabilities of LLMs
  231. Sliced Inner Product Gromov-Wasserstein Distances
  232. Log analysis is necessary for credible evaluation of AI agents
  233. Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation
  234. Continuity Laws for Sequential Models
  235. Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care
  236. A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recovery
  237. The Propagation Field: A Geometric Substrate Theory of Deep Learning
  238. Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation
  239. Geometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models
  240. SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
  241. A Deep Risk Estimator for Known Operator Learning
  242. OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
  243. MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning
  244. Learning Polyhedral Conformal Sets for Robust Optimization
  245. Scaling Limits of Long-Context Transformers
  246. A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
  247. Multi-Level Graph Attention Network Contrastive Learning for Knowledge-Aware Recommendation
  248. NeuralBench: A Unifying Framework to Benchmark NeuroAI Models
  249. CapCLIP: A Vision-Language Representation Alignment Approach for Wireless Capsule Endoscopy Analysis
  250. A Unified Lyapunov-IQC Framework for Uniform Stability of Smooth Quadratic First-Order Accelerated Optimizers
  251. Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
  252. ShifaMind: A Multiplicative Concept Bottleneck for Interpretable ICD-10 Coding
  253. A Computational Operationalisation of Competing Maturational Theories of Syntactic Development via Statistical Grammar Induction
  254. Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
  255. CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
  256. The Geometric Structure of Models Learning Sparse Data
  257. Neurally-plausible radial basis kernels using distributed Fourier embeddings
  258. HEART: A High-Efficiency Adaptive Real-Time Telemonitoring Framework for Secure Electrocardiogram Signal Transmission Using Chaotic Encryption
  259. CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
  260. Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency
  261. Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
  262. RubiConv -- Efficient Boundary-Respecting Convolutions
  263. LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification
  264. Revisiting the syntax of imperatives in Yemeni Arabic: An Agree across phases approach
  265. Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
  266. DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
  267. Can Language Models Identify Side Effects of Breast Cancer Radiation Treatments?
  268. Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks
  269. A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
  270. A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
  271. Active Multiple-Prediction-Powered Inference
  272. Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
  273. Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval
  274. Alignment as Jurisprudence
  275. Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
  276. Playing games with knowledge: AI-Induced delusions need game theoretic interventions
  277. AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training
  278. Effective Explanations Support Planning Under Uncertainty
  279. Belief or Circuitry? Causal Evidence for In-Context Graph Learning
  280. On Observation Time for Recovering Latent Hawkes Networks
  281. Delivering Science as a Service: Sci-Orchestra's Cloud-Native Approach to HPC
  282. SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
  283. The Power of Second Order Methods for Sequence Preconditioning
  284. Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
  285. PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams
  286. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
  287. Change My View? The Dynamics of Persuasion and Polarization in Online Discourse
  288. What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook
  289. Transfer Learning for Dead Fuel Moisture Prediction Using Time-Warping Recurrent Neural Networks
  290. Embedding Dimension Lower Bounds for Universality of Deep Sets and Janossy Pooling
  291. UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement
  292. NeuroGAN-3D: Enhancing Intrinsic Functional Brain Networks via High-Fidelity 3D Generative Super-Resolution
  293. On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective
  294. Embeddings for Preferences, Not Semantics
  295. Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
  296. Private Vertical Federated Inference for Time-Series
  297. CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
  298. Optimal FALQON for Quantum Approximate Optimization via Layer-wise Parameter Tuning
  299. An Efficient Token Compression Framework for Visual Object Tracking
  300. LLM Advertisement based on Neuron Auctions
  301. CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks
  302. FQPDR: Federated Quantum Neural Network for Privacy-preserving Early Detection of Diabetic Retinopathy
  303. The Reciprocity Gradient
  304. LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
  305. Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks
  306. Mazocarta: A Seeded Procedural Deckbuilder for Instrumented Game Development
  307. Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
  308. Seed Hijacking of LLM Sampling and Quantum Random Number Defense
  309. Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
  310. WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
  311. Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns
  312. Non-intrusive Body Composition Assessment from Full-body mmWave Scans
  313. LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems
  314. GNN for Structural Displacement Prediction
  315. SGC-RML: A reliable and interpretable longitudinal assessment for PD in real-world DNS
  316. Priming: Hybrid State Space Models From Pre-trained Transformers
  317. mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
  318. Do not copy and paste! Rewriting strategies for code retrieval
  319. What Cohort INRs Encode and Where to Freeze Them
  320. A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks
  321. BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition
  322. Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion
  323. Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation
  324. Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
  325. What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
  326. UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
  327. Multi-Armed Bandits With Best-Action Queries
  328. Diagnosing Spectral Ceilings in Equivariant Neural Force Fields
  329. Exactness Matters for Physical Rule Enforcement
  330. A Paired Point-of-Care Ultrasound Dataset for Image Quality Enhancement and Benchmarking via a cGAN Baseline
  331. Is Class Signal Clustered or Routed in Task-Induced Implicit Neural Representation Weight Spaces?
  332. Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
  333. Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
  334. Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions
  335. Efficient Prompt Learning for Traffic Forecasting
  336. SAFformer:Improving Spiking Transformer via Active Predictive Filtering
  337. Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification
  338. Normalizing Trajectory Models
  339. Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
  340. Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping
  341. GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
  342. EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction
  343. A Note on Non-Negative L1-Approximating Polynomials
  344. Empirical Bayes Rebiasing
  345. 6D Pose Estimation via Keypoint Heatmap Regression with RGB-D Residual Neural Networks
  346. Period spacings and global seismic parameters for K2 red giants using deep learning
  347. MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation
  348. Accurate and Efficient Statistical Testing for Word Semantic Breadth
  349. Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs
  350. Fast Byte Latent Transformer
  351. SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
  352. Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids
  353. PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting
  354. Semiparametric Efficient Test for Interpretable Distributional Treatment Effects
  355. PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction
  356. Observation-Aligned Two-Stage Domain Decomposition for Physics-Informed Traffic State Estimation with Sparse Fixed Sensors
  357. TRAS: An Interactive Software for Tracing Tree Ring Cross Sections
  358. MPD2-Router: Mask-aware Multi-expert Prior-regularized Dual-head Deferral Router in Glaucoma Screening and Diagnosis
  359. Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees
  360. Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
  361. Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
  362. STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting
  363. SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
  364. Rethinking Dense Optical Flow without Test-Time Scaling
  365. Graph-Structured Hyperdimensional Computing for Data-Efficient and Explainable Process-Structure-Property Prediction
  366. Bayesian Sensitivity of Causal Inference Estimators under Evidence-Based Priors
  367. Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methods
  368. Towards Apples to Apples for AI Evaluations: From Real-World Use Cases to Evaluation Scenarios
  369. Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
  370. Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
  371. The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
  372. Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
  373. It Just Takes Two: Scaling Amortized Inference to Large Sets
  374. Linear Response Estimators for Singular Statistical Models
  375. Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
  376. Aggregation in conformal e-classification
  377. FLAM: Evaluating Model Performance with Aggregatable Measures in Federated Learning
  378. Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
  379. Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA
  380. TimeLesSeg: Unified Contrast-Agnostic Cross-Sectional and Longitudinal MS Lesion Segmentation via a Stochastic Generative Model
  381. Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
  382. Exploring the non-convexity in machine learning using quantum-inspired optimization
  383. Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
  384. Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
  385. Prototype Guided Post-pretraining for Single-Cell Representation Learning
  386. Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
  387. INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
  388. How Value Induction Reshapes LLM Behaviour
  389. MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
  390. Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
  391. Sycophantic AI makes human interaction feel more effortful and less satisfying over time
  392. One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
  393. Statistical inference with belief functions: A survey
  394. CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
  395. BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing
  396. Curvature Beyond Positivity: Greedy Guarantees for Arbitrary Submodular Functions
  397. Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
  398. What if AI systems weren't chatbots?
  399. Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers
  400. Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis
  401. Implicit Target Shift in Online Learning: Characterization and Correction
  402. Black-box model classification under the discriminative factorization
  403. Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
  404. From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data
  405. EyeCue: Driver Cognitive Distraction Detection via Gaze-Empowered Egocentric Video Understanding
  406. MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
  407. Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
  408. BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing
  409. Distributional simplicity bias and effective convexity in Energy Based Models
  410. mathsfVISTA: Decentralized Machine Learning in Adversary Dominated Environments
  411. Exact Regular-Constrained Variable-Order Markov Generation via Sparse Context-State Belief Propagation
  412. PPI-Net connects molecular protein interactions to functional processes in disease
  413. Approximation-Free Differentiable Oblique Decision Trees
  414. Explainable Part-Based Vehicle Classifier with Spatial Awareness
  415. NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces
  416. SCENE: Recognizing Social Norms and Sanctioning in Group Chats
  417. Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
  418. Expectation-Maximization as a Spectrally Governed Relaxation Flow
  419. ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles
  420. OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
  421. GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
  422. A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches for Sentiment Classification on IMDb Movie Reviews
  423. Pre-training Enables Extraordinary All-optical Image Denoising
  424. The Minimax Rate of Perturbed Second-Order Calibration
  425. Text-to-CAD Evaluation with CADTests
  426. Flexible Routing via Uncertainty Decomposition
  427. Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
  428. PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism
  429. Hybrid TF--IDF Logistic Regression and MLP Neural Baseline for Indonesian Three-Class Sentiment Analysis on Social Media Text
  430. Neural Operators as Efficient Function Interpolators
  431. Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
  432. APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation
  433. Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation
  434. Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models
  435. CktFormalizer: Autoformalization of Natural Language into Circuit Representations
  436. Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis
  437. POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
  438. Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
  439. Interactive Trajectory Planning with Learning-based Distributionally Robust Model Predictive Control and Markov Systems
  440. SIMI: Self-information Mining Network for Low-light Image Enhancement
  441. Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition
  442. Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation
  443. RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation
  444. SMT-Based Active Learning of Weighted Automata
  445. Efficient Verification of Neural Control Barrier Functions with Smooth Nonlinear Activations
  446. When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
  447. Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
  448. Robust and Reliable AI for Predictive Quality in Semiconductor Materials Manufacturing with MLOps and Uncertainty Quantification
  449. Vibe coding before the trend
  450. Benchmarking Foundation Models for Renal Lesion Stratification in CT
  451. Alternating Target-Path Planning for Scalable Multi-Agent Coordination
  452. LAMES: A Large-Scale and Artisanal Mining Environmental Segmentation Dataset
  453. Physics-Informed Reduced-Order Operator Learning for Hyperelasticity in Continuum Micromechanics
  454. Online Goal Recognition using Path Signature and Dynamic Time Warping
  455. Intelligent Truck Matching in Full Truckload Shipments using Ping2Hex approach
  456. Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
  457. Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
  458. LLM hallucinations in the wild: Large-scale evidence from non-existent citations
  459. TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
  460. The AI-Native Large-Scale Agile Software Development Manifesto
  461. Hierarchical Task Network Planning with LLM-Generated Heuristics
  462. Bayesian Fine-tuning in Projected Subspaces
  463. Encoder-Decoder Transformers: Logical Characterizations and Periodicity
  464. Finite-Time Analysis of MCTS in Continuous POMDP Planning
  465. OphEdit: Training-Free Text-Guided Editing of Ophthalmic Surgical Videos
  466. Dependence on Early and Late Reverberation of Single-Channel Speaker Distance Estimation
  467. Toward Better Geometric Representations for Molecule Generative Models
  468. GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
  469. Fortifying Time Series: DTW-Certified Robust Anomaly Detection
  470. TRACE: Tourism Recommendation with Accountable Citation Evidence
  471. FactoryBench: Evaluating Industrial Machine Understanding
  472. Differentially Private Auditing Under Strategic Response
  473. The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting
  474. Quotient Semivalues for False-Name-Resistant Data Attribution
  475. Direction-Preserving Number Representations
  476. Towards Billion-scale Multi-modal Biometric Search
  477. Aquatic Neuromorphic Optical Flow
  478. Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal
  479. Learning Large-Scale Modular Addition with an Auxiliary Modulus
  480. Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
  481. EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting
  482. LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
  483. Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference
  484. Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
  485. Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction
  486. Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling
  487. Post-training makes large language models less human-like
  488. Inference Time Causal Probing in LLMs
  489. Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
  490. Is She Even Relevant? When BERT Ignores Explicit Gender Cues
  491. Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation
  492. FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth
  493. N"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification
  494. SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
  495. Optimal Recourse Summaries via Bi-Objective Decision Tree Learning
  496. A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning
  497. TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
  498. Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
  499. Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
  500. Parallel Lifted Planning via Semi-Naive Datalog Evaluation
  501. Bilevel Graph Structure Learning, Revisited: Inner-Channel Origins of the Reported Gain
  502. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
  503. Open-Ended Task Discovery via Bayesian Optimization
  504. Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
  505. Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context
  506. Multimodal Stepwise Clinically-Guided Attention Learning for Pathological Complete Response Prediction in Breast Cancer
  507. Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning
  508. Dynamic Mode Decomposition along Depth in Vision Transformers
  509. ProteinJEPA: Latent prediction improves protein language model pretraining
  510. Disagreement-Regularized Importance Sampling for Adversarial Label Corruption
  511. Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
  512. Probabilistic Object Detection with Conformal Prediction
  513. On the Invariance and Generality of Neural Scaling Laws
  514. Multi-Environment POMDPs with Finite-Horizon Objectives
  515. GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training
  516. Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation
  517. SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching
  518. Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
  519. WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation
  520. From Feasible to Practical: Pareto-Optimal Synthesis Planning
  521. Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration
  522. TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature
  523. Cloud-top infrared observations reveal the four-dimensional precipitation structure
  524. Lightweight Unpaired Smartphone ISP Transfer with Semantic Pseudo-Pairing
  525. How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings
  526. Implicit Multi-Camera System Calibration Using Gaussian Processes
  527. Excluding the Target Domain Improves Extrapolation: Deconfounded Hierarchical Physics Constraints
  528. Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
  529. NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting
  530. Breaking QAOA's Fixed Target Hamiltonian Barrier: A Fully Connected Quantum Boltzmann Machine via Bilevel Optimization
  531. Transfer Learning Across Fast- and Full-Simulation Domains in High-Energy Physics
  532. Uncovering Hidden Systematics in Neural Network Models for High Energy Physics
  533. Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Science
  534. A Unified Framework for the Detection and Classification of Fatty Pancreas in Ultrasound Images
  535. Approximation Error Upper and Lower Bounds for H"older Class with Transformers
  536. The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
  537. Learning Minimal-Deviation Corrections for Multi-Dimensional Mismodelling in HEP Simulations
  538. Estimation of Motor Unit Parameters from Surface Electromyograms using an Informed Autoencoder
  539. EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing
  540. GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks
  541. Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study
  542. Bounded Fitting for Expressive Description Logics
  543. VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification
  544. Robust Tensor Regression with Nonconvexity: Algorithmic and Statistical Theory
  545. SSP-based construction of evaluation-annotated data for fine-grained aspect-based sentiment analysis
  546. Accelerated and data-efficient flow prediction in stirred tanks via physics-informed learning
  547. GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection
  548. Inference of Qualitative Models from Steady-State Data via Weighted MaxSMT
  549. Generating training datasets for legal chatbots in Korean
  550. Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
  551. A Flexible Adaptive Stable Clustering Algorithm for Archive-Scale Online Mass Spectrometry
  552. Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study
  553. SR2-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning
  554. Learning Image-Adaptive Scale Fields for Metric Depth Recovery
  555. Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs
  556. Risk-Consistent Multiclass Learning from Random Label-Subset Membership Queries
  557. Tracking Large-scale Shared Bikes with Inertial Motion Learning in GNSS Blocked Environments
  558. The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
  559. Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
  560. InsHuman: Towards Natural and Identity-Preserving Human Insertion
  561. Exposing and Mitigating Temporal Attack in Deepfake Video Detection
  562. Have Graph -- Will Lift? The Case for Higher-Order Benchmarks
  563. Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
  564. BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
  565. Exploring CoCo Challenges in ML Engineering Teams: Insights From the Semiconductor Industry
  566. A Marine Debris Detection Framework for Ocean Robots via Self-Attention Enhancement and Feature Interaction Optimization
  567. Convex Optimization with Nested Evolving Feasible Sets
  568. Velocity-Space 3D Asset Editing
  569. StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
  570. Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
  571. QuadNorm: Resolution-Robust Normalization for Neural Operators
  572. Weather-Robust Scene Semantics with Vision-Aligned 4D Radar
  573. When Gradient Importance Lies: Adaptive LoRA Rank Allocation Fails Under GRPO
  574. FlightSense: An End-to-End MLOps Platform for Real-Time Flight Delay Prediction via Rotation-Chain Propagation Features and Agentic Conversational AI
  575. MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
  576. UniISP: A Unified ISP Framework for Both Human and Machine Vision
  577. UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition
  578. TTF: Temporal Token Fusion for Efficient Video-Language Model
  579. Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference
  580. Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
  581. SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
  582. Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative
  583. Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate
  584. ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs
  585. CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction
  586. GC-ART: Global Learnable Second-Order Rational Tone Curves for Illumination Robustness
  587. CSR: Infinite-Horizon Real-Time Policies with Massive Cached State Representations
  588. Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
  589. DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation
  590. When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
  591. MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
  592. Latent Order Bandits
  593. Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
  594. Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
  595. On the Complexity of the Matching Problem of Regular Expressions with Backreferences
  596. SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
  597. Sparse Random-Feature Neural Networks with Krylov-Based SVD for Singularly Perturbed ODE
  598. Same Targets, Different Computation: How Post-Training Divides Work Across Model Layers
  599. The Convergence Gap: Instruction-Tuned Language Models Stabilize Later in the Forward Pass
  600. Mask2Cause: Temporal Causal Discovery Beyond Causality in Mean
  601. Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics
  602. Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
  603. bispectrum: Selective G-Bispectra Made Practical
  604. From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs
  605. PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning
  606. How Big Should a Wireless Foundation Model Be?
  607. Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
  608. Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning
  609. Adaptive Subspace Projection for Generative Personalization
  610. TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts
  611. High-Fidelity Surface Splatting-Based 3D Reconstruction from Multi-View Images
  612. PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation
  613. EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation
  614. Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
  615. Sample Complexity of Stochastic Optimization with Integer Variables
  616. Modulated learning for private and distributed regression with just a single sample per client device
  617. Towards multi-modal forgery representation learning for AI-generated video detection and localization
  618. Don't Learn the Shape: Forecasting Periodic Time Series by Rank-1 Decomposition
  619. DINO-MVR: Multi-View Readout of Frozen DINOv3 for Annotation-Efficient Medical Segmentation
  620. LoHGNet: Infrared Small Target Detection through Lorentz Geometric Encoding with High-Order Relation Learning
  621. Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability
  622. HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning
  623. Hallucination Detection via Activations of Open-Weight Proxy Analyzers
  624. FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
  625. Arrow: A Foundation Model for Causal Discovery
  626. From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting
  627. Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
  628. Coupling Models for One-Step Discrete Generation
  629. AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes
  630. Attention Transfer Is Not Universally Effective for Vision Transformers
  631. PicoEyes: Unified Gaze Estimation Framework for Mixed Reality with a Large-Scale Multi-View Dataset
  632. The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval
  633. SatSurfGS: Generalizable 2D Gaussian Splatting for Sparse-View Satellite Surface Reconstruction
  634. Masks Can Talk: Extracting Structured Text Information from Single-Modal Images for Remote Sensing Change Detection
  635. Learning Multi-Relational Graph Representations for DNA Methylation-Based Biological Age Estimation
  636. Repeated Deceptive Path Planning against Learnable Observer
  637. Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy
  638. A Reproducible Multi-Architecture Baseline for Token-Level Chinese Metaphor Identification under the MIPVU Framework
  639. CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
  640. Learned Lagrangian Models of PDEs via Euler-Lagrange Residual Minimization
  641. Hierarchical Perfusion Graphs for Tumor Heterogeneity Modeling in Glioma Molecular Subtyping
  642. Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning
  643. PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition
  644. DPG-CD: Depth-Prior-Guided Cross-Modal Joint 2D-3D Change Detection
  645. Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection
  646. UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection
  647. TriP: A Triangle Puzzle Approach to Robust Translation Averaging
  648. AGA3DNet: Anatomy-Guided Gaussian Priors with Multi-view xLSTM for 3D Brain MRI Subtype Classification
  649. Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
  650. GAD in the Wild: Benchmarking Graph Anomaly Detection under Realistic Deployment Challenges
  651. Simple KNN-Based Outlier Detection Achieves Robust Clustering
  652. The Position Curse: LLMs Struggle to Locate the Last Few Items in a List
  653. An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
  654. AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
  655. When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
  656. Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
  657. Monotone Neural Policy Iteration for High-Dimensional First-Order Hamilton--Jacobi--Bellman Equations
  658. Conformal-Style Quantile Analyses for Stochastic Bandits
  659. Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
  660. Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
  661. Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator
  662. SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions
  663. InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
  664. CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation
  665. Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
  666. Query-efficient model evaluation using cached responses
  667. The Translation Tax Is Not a Scalar: A Counterfactual Audit of English-Source Cue Inheritance in Chinese Multilingual Benchmarks
  668. Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information
  669. Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation
  670. Online Allocation with Unknown Shared Supply
  671. Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
  672. ModelLens: Finding the Best for Your Task from Myriads of Models
  673. TeamBench: Evaluating Agent Coordination under Enforced Role Separation
  674. Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
  675. PolarAdamW: Disentangling Spectral Control and Schur Gauge-Equivariance in Matrix Optimisation
  676. Causal EpiNets: Precision-corrected Bounds on Individual Treatment Effects using Epistemic Neural Networks
  677. Learning to Track Instance from Single Nature Language Description
  678. Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
  679. Do Joint Audio-Video Generation Models Understand Physics?
  680. Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks
  681. Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
  682. A Behavioral Framework for Data-Driven Modeling of Nonlinear Systems in Vector-Valued Reproducing Kernel Hilbert Spaces
  683. NSMQ Riddles: A Benchmark of Scientific and Mathematical Riddles for Quizzing Large Language Models