mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 30 Jan 2026

591 papers

  1. RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented GenerationRetrieval-augmented generation → Conversational and speech RAG
  2. BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance
  3. Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient AgentsLLM agents and tool use → Agent threats, guardrails and governance
  4. Prompt Optimization Via Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  5. Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical SystemsRetrieval-augmented generation → RAG for code
  6. AST-PAC: AST-guided Membership Inference for CodeLLM safety and security → Membership inference attacks
  7. CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact AssessmentRetrieval-augmented generation → Agentic RAG, agents and memory
  8. MELINOE: Fine-Tuning Enables Memory-Efficient Inference for Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
  9. Spectra: Rethinking Optimizers for LLMs Under Spectral AnisotropyLLM reasoning → Test-time compute and efficient thinking
  10. KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language ModelsMixture-of-experts → MoE large language models
  11. Latent-Space Causal Discovery from Indirect Neuroimaging ObservationsState-space sequence models (S4, Mamba) → Physiological signal modeling
  12. ARGOS: Automated Functional Safety Requirement Synthesis for Embodied AI via Attribute-Guided Combinatorial ReasoningLLM reasoning → Spatial and embodied reasoning
  13. iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment ProblemsDeep reinforcement learning methods → RL for energy, networks and operations
  14. Label Curation Using Agentic AILLM agents and tool use → Multimodal and embodied agents
  15. MathlibLemma: Folklore Lemma Generation and Benchmark for Formal MathematicsLLM reasoning → Mathematical reasoning
  16. Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth ObserversLLM agents and tool use → Multimodal and embodied agents
  17. Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  18. HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error GuaranteesLLM reasoning → Test-time compute and efficient thinking
  19. ToolTok: Tool Tokenization for Efficient and Generalizable GUI AgentsLLM agents and tool use → GUI and mobile agents
  20. Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  21. SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  22. Are Coding Agents Generating Over-Mocked Tests? An Empirical StudyLLM agents and tool use → Software engineering coding agents
  23. Variational Approach for Job Shop SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
  24. DROGO: Default Representation Objective via Graph Optimization in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  25. KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQALLM reasoning → Reinforcement learning for reasoning +3
  26. Reinforcement Learning for Control Systems with Time Delays: A Comprehensive SurveyDeep reinforcement learning methods → Deep RL algorithms and representations
  27. Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure ModeLLM safety and security → Jailbreaking
  28. RePaint-Enhanced Conditional Diffusion Model for Parametric Engineering Designs under Performance and Parameter ConstraintsDiffusion models → Flow matching, time series and science
  29. Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  30. MATRIX: A Multimodal Benchmark and Post-Training Framework for Materials ScienceLLM reasoning → Clinical and biomedical applications
  31. Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential DistillationKnowledge distillation → General knowledge distillation methods
  32. Learning Safety-Guaranteed, Non-Greedy Control Barrier Functions Using Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  33. Position: Agentic Evolution is the Path to Evolving LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Planning with Language and Generative Models: Toward General Reward-Guided Wireless Network DesignDiffusion models → Diffusion for compression and wireless
  35. ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion modelsDiffusion models → Robustness, privacy and adversarial aspects +1
  36. MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRIDeep reinforcement learning methods → RL for clinical treatment and surgery
  37. AdaFuse: Adaptive Multimodal Fusion for Lung Cancer Risk Prediction via Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
  38. When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  39. Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  40. Harvest: Opportunistic Peer-to-Peer GPU Caching for LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  41. Agentic Framework for Epidemiological ModelingLLM agents and tool use → Social simulation and multi-agent debate
  42. Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow FinetuningLLM safety and security → Safety alignment, refusal and guardrails
  43. RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG RoutingRetrieval-augmented generation → RAG pipeline design and evaluation
  44. LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual VerificationLLM reasoning → Hallucination detection and mitigation +1
  45. Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic PerspectiveDiffusion models → Discrete and text diffusion +1
  46. Sample Complexity Analysis for Constrained Bilevel Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  47. Localizing and Correcting Errors for LLM-based PlannersLLM reasoning → Reasoning for agents, planning and code
  48. VoxServe: Streaming-Centric Serving System for Speech Language ModelsEfficient LLM inference and serving → Audio and omni-modal token compression
  49. TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
  50. PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic TrajectoriesDiffusion models → Video generation
  51. TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion ModelsDiffusion models → Discrete and text diffusion +1
  52. CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  53. DIVERGE: Diversity-Enhanced RAG for Open-Ended Information SeekingRetrieval-augmented generation → RAG pipeline design and evaluation
  54. TessPay: Verify-then-Pay Infrastructure for Trusted Agentic CommerceLLM agents and tool use → Agent threats, guardrails and governance
  55. Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing ImagesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  56. Reducing Memorisation in Generative Models via Riemannian Bayesian InferenceDiffusion models → Diffusion foundations and sampling
  57. Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation PredictionLLM reasoning → Clinical and biomedical applications +1
  58. GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  59. QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its CapabilitiesLLM agents and tool use → Medical and scientific domain agents
  60. CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial ReasoningLLM reasoning → Multimodal reasoning
  61. Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse ProblemsDiffusion models → Inverse problems and image restoration
  62. The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable OptimizationDiffusion models → Robustness, privacy and adversarial aspects +1
  63. Learning Robust Reasoning through Guided Adversarial Self-PlayLLM reasoning → Reinforcement learning for reasoning
  64. VideoGPA: Distilling Geometry Priors for 3D-Consistent Video GenerationDiffusion models → 3D, point cloud and scene generation
  65. Decoupled Diffusion Sampling for Inverse Problems on Function SpacesDiffusion models → Inverse problems and image restoration
  66. UPA: Unsupervised Prompt Agent via Tree-Based Search and SelectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +3
  68. Particle-Guided Diffusion Models for Partial Differential EquationsDiffusion models → Flow matching, time series and science
  69. From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program RepairLLM reasoning → Reasoning for agents, planning and code
  70. Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  71. Structure Over Scale: Learning Visual Reasoning from Pedagogical VideoLLM reasoning → Multimodal reasoning +1
  72. How well do generative models solve inverse problems? A benchmark studyDiffusion models → Flow matching, time series and science
  73. Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic GraphDiffusion models → Flow matching, time series and science
  74. Agile Reinforcement Learning through Separable Neural Architecture and ApplicationsDeep reinforcement learning methods → Deep RL algorithms and representations
  75. Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop ReasoningLLM reasoning → Multimodal reasoning +1
  76. Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-TrainingMultimodal LLMs / vision-language models → Medical vision-language models
  77. MonoScale: Scaling Multi-Agent System with Monotonic ImprovementLLM agents and tool use → General LLM agent frameworks and benchmarks
  78. Multi-Agent Systems Should be Treated as Principal-Agent ProblemsLLM agents and tool use → Social simulation and multi-agent debate
  79. Scale-Cascaded Diffusion Models for Super-Resolution in Medical ImagingDiffusion models → Medical imaging and segmentation
  80. ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking
  81. FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided GenerationDiffusion models → Discrete and text diffusion
  82. TriSpec: Ternary Speculative Decoding via Lightweight Proxy VerificationEfficient LLM inference and serving → Speculative decoding
  83. Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta OptimizationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  84. Probing the Trajectories of Reasoning Traces in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  85. Unsupervised Hierarchical Skill DiscoveryDeep reinforcement learning methods → Deep RL algorithms and representations
  86. Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  87. THINKSAFE: Self-Generated Safety Alignment for Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +2
  88. Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive GradientsLLM reasoning → Reinforcement learning for reasoning
  89. RAudit: A Blind Auditing Protocol for Large Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
  90. Evaluating the Utility of Grounding Documents with Reference-Free LLM-based MetricsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  91. CATTO: Balancing Preferences and Confidence in Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  92. CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  93. Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasksLLM reasoning → Prompting and chain-of-thought reasoning +1
  94. OrLog: Resolving Complex Queries with LLMs and Probabilistic ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  95. Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety FailuresLLM safety and security → Safety alignment, refusal and guardrails
  96. RN-D: Discretized Categorical Actors for On-Policy Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  97. SplineFlow: Flow Matching for Dynamical Systems with B-Spline InterpolantsDiffusion models → Flow matching, time series and science
  98. From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +2
  99. One-shot Optimized Steering Vector for Hallucination Mitigation for VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  100. Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated ReasoningLLM reasoning → Reasoning for agents, planning and code +1
All 591
  1. Divide-and-Conquer CoT: RL for Reducing Latency via Parallel ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  2. Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  3. SolAgent: A Specialized Multi-Agent Framework for Solidity Code GenerationLLM agents and tool use → Software engineering coding agents
  4. TriCEGAR: A Trace-Driven Abstraction Mechanism for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  5. Cantelli Constrained Policy OptimizationDeep reinforcement learning methods → Safe and constrained RL
  6. dgMARK: Decoding-Guided Watermarking for Diffusion Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  7. Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research TrajectoryLLM agents and tool use → Medical and scientific domain agents
  8. Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet TextLLM reasoning → Reinforcement learning for reasoning
  9. MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task AllocationLLM agents and tool use → Agent memory systems
  10. Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic MethodsDeep reinforcement learning methods → RL theory and sample complexity
  11. Self-Imitated Diffusion Policy for Efficient and Robust Visual NavigationDiffusion models → Diffusion and flow policies for robotics
  12. Improving Supervised Machine Learning Performance in Optical Quality Control via Generative AI for Dataset ExpansionDiffusion models → Flow matching, time series and science
  13. Triage: Hierarchical Visual Budgeting for Efficient Video Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  14. Residual Context Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  15. Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive FilteringLLM agents and tool use → Agent threats, guardrails and governance
  16. OneFlowSBI: One Model, Many Queries for Simulation-Based InferenceDiffusion models → Flow matching, time series and science
  17. Autonomous Chain-of-Thought Distillation for Graph-Based Fraud DetectionLLM reasoning → Knowledge- and tool-augmented reasoning
  18. Reconsidering Positional Supervision in Masked Diffusion Language Model TrainingDiffusion models → Discrete and text diffusion
  19. MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
  20. LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  21. Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and GenerationDiffusion models → Diffusion foundations and sampling
  22. MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn LoopDeep reinforcement learning methods → RL training of language and agent models
  23. PlatoLTL: Scaling LTL-Guided Multi-Task RLDeep reinforcement learning methods → Interpretable and logic-guided RL
  24. DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text DiffusionLLM reasoning → Audio-language model reasoning
  25. DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American EnglishMechanistic interpretability → Knowledge and representations inside LLMs
  26. Reinforcement Learning-Based Co-Design and Operation of Chiller and Thermal Energy Storage for Cost-Optimal HVAC SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  27. EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech SynthesisMechanistic interpretability → Activation steering methods
  28. Degradation-Aware Frequency Regulation of a Heterogeneous Battery Fleet via Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  29. Neural Clothing Tryer: Customized Virtual Try-On via Semantic Enhancement and Controlling Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  30. A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF ConditionsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  31. Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRAMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  32. Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style AlignmentOffline RL and imitation learning from data → Offline RL algorithms
  33. Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language ModelsMechanistic interpretability → Steering and probing for LLM safety
  34. Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type FeaturesDiffusion models → Flow matching, time series and science
  35. CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  36. Clipping-Free Policy Optimization for Large Language ModelsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  37. Conditional Performance Guarantee for Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  38. Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent TrainingLLM agents and tool use → GUI and mobile agents
  39. RASST: Retrieval-Augmented Simultaneous Speech TranslationRetrieval-augmented generation → Generation and context integration
  40. TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  41. AutoRefine: Compiling Trajectories into Validated Typed Agent ArtifactsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. Procedural Knowledge Extraction from Industrial Troubleshooting Guides Using Vision Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  43. UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region ProfilingMixture-of-experts → MoE for time series and graphs
  44. AR-BENCH: Benchmarking Legal Reasoning with Judgment Error Detection, Classification and CorrectionLLM reasoning → Reasoning for agents, planning and code
  45. StreamSense: Streaming Social Task Detection with Selective Vision-Language Model RoutingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  46. Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  47. MM-THEBench: Do Reasoning MLLMs Think Reasonably?LLM reasoning → Hallucination detection and mitigation +1
  48. ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language ModelLLM reasoning → Prompting and chain-of-thought reasoning
  49. GaussianOcc3D: A Gaussian-Based Adaptive Multi-modal 3D Occupancy PredictionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  50. OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On EvaluationDiffusion models → 3D, point cloud and scene generation
  51. A Step Back: Prefix Importance Ratio Stabilizes Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  52. Vision-Language Models Unlock Task-Centric Latent ActionsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  53. Gated Relational Alignment via Confidence-based Distillation for Efficient VLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  54. CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency ControlEfficient LLM inference and serving → Efficient reasoning and agent inference
  55. Best-of-Q: Improving VLM agents with Q-function Action Ranking at InferenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  56. Bi-MCQ: Reformulating Vision-Language Alignment for Negation UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  57. TSLM: Tree-Structured Language Modeling for Divergent ThinkingLLM reasoning → Test-time compute and efficient thinking
  58. Stabilizing Consistency Training: A Flow Map Analysis and Self-DistillationDiffusion models → Diffusion foundations and sampling +1
  59. VisionTrim: Unified Vision Token Compression for Training-Free MLLM AccelerationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  60. Real-Time Aligned Reward Model beyond SemanticsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  61. GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via UnlearningDiffusion models → Diffusion foundations and sampling +1
  62. Test-Time Mixture of World Models for Embodied Agents in Dynamic EnvironmentsWorld models → World models for language agents +2
  63. Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic VerificationLLM reasoning → Reasoning benchmarks and evaluation +1
  64. Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N SamplingLLM safety and security → Jailbreaking
  65. Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  66. TTCS: Test-Time Curriculum Synthesis for Self-EvolvingLLM reasoning → Test-time compute and efficient thinking +1
  67. SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model AssemblyLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. Layer-wise Swapping for Generalizable Multilingual SafetyLLM safety and security → Safety alignment, refusal and guardrails
  69. EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  70. Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated UnlearningLLM safety and security → Federated unlearning and poisoning
  71. Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVRLLM reasoning → Reinforcement learning for reasoning
  72. Language Model Circuits Are Sparse in the Neuron BasisMechanistic interpretability → Circuits and mechanistic analysis
  73. FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant RecoveryLLM safety and security → Federated unlearning and poisoning
  74. Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity AsymmetryLLM reasoning → Reasoning benchmarks and evaluation
  75. MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  76. SpanNorm: Reconciling Training Stability and Performance in Deep TransformersMixture-of-experts → MoE large language models
  77. PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile ScenariosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  78. Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  79. PerfGuard: A Performance-Aware Agent for Visual Content GenerationLLM agents and tool use → Multimodal and embodied agents
  80. Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  81. VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter InjectionLLM safety and security → Watermarking generated content and models
  82. PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble AuditingLLM agents and tool use → Agentic recommender systems
  83. Towards the Holographic Characteristic of LLMs for Efficient Short-text GenerationLLM reasoning → Reasoning benchmarks and evaluation
  84. Adapting Reinforcement Learning for Path Planning in Constrained Parking ScenariosDeep reinforcement learning methods → RL for autonomous driving and traffic
  85. Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex ReasoningLLM reasoning → Mathematical reasoning
  86. Enhancing Table Reasoning with Deterministic Table-State RewardsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  87. Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent EvolutionLLM agents and tool use → GUI and mobile agents
  88. ρ-textttEOS: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMsDiffusion models → Discrete and text diffusion
  89. Variational Bayesian Flow Network for Graph GenerationDiffusion models → Flow matching, time series and science
  90. One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean GeometryLLM reasoning → Reinforcement learning for reasoning
  91. Corrected Samplers for Discrete Flow ModelsDiffusion models → Diffusion foundations and sampling
  92. Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  93. Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based RewardsLLM agents and tool use → Reinforcement learning for LLM agents
  94. DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image GenerationDiffusion models → Image generation, text-to-image and editing
  95. Action-Sufficient Goal RepresentationsDeep reinforcement learning methods → Deep RL algorithms and representations
  96. Gradual Fine-Tuning for Flow Matching ModelsDiffusion models → Flow matching, time series and science
  97. SSL: Sweet Spot Learning for Differentiated Guidance in Agentic OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  98. Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike SteeringLLM reasoning → Test-time compute and efficient thinking
  99. Head-Aware Visual Cropping: Enhancing Fine-Grained VQA with Attention-Guided SubimageMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  100. Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  101. Continual Policy Consolidation for Lifelong Robot LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  102. Training-Free Representation Guidance for Diffusion Models with a Representation Alignment ProjectorDiffusion models → Diffusion foundations and sampling
  103. CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot ControlVision-language-action models → Human-video and latent-action pretraining
  104. Machine Unlearning in Low-Dimensional Feature SubspaceLLM safety and security → Machine unlearning
  105. Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation FrameworkMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  106. Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from k-ParityDiffusion models → Discrete and text diffusion
  107. Emergence of Physical Intelligence via Controllable Information ProductionDeep reinforcement learning methods → Deep RL algorithms and representations
  108. HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  109. Beyond Activation Patterns: A Weight-Based Out-of-Context Explanation of Sparse Autoencoder FeaturesMechanistic interpretability → SAE features and their applications
  110. Anytime Safe PAC Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
  111. Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem PerformanceDiffusion models → Inverse problems and image restoration
  112. Towards Resiliency in Large Language Model Serving with KevlarFlowEfficient LLM inference and serving → Serving systems and request scheduling
  113. Large Language Model Agents Are Not Always Faithful Self-EvolversLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  114. ReNCE: Learning to Reason by Noise Contrastive EstimationLLM reasoning → Reinforcement learning for reasoning
  115. SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
  116. Toward a Universal Color Naming System: A Clustering-Based Approach using Multisource Data
  117. Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction
  118. Applied Sociolinguistic AI for Community Development (ASA-CD): A New Scientific Paradigm for Linguistically-Grounded Social Intervention
  119. EQ-5D Classification Using Biomedical Entity-Enriched Pre-trained Language Models and Multiple Instance Learning
  120. Inference-time Alignment via Sparse Junction Steering
  121. Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned
  122. Hybrid operator learning of wave scattering maps in high-contrast media
  123. Position-Aware Self-supervised Representation Learning for Cross-mode Radar Signal Recognition
  124. Predicting the post-wildfire mudflow onset using machine learning models on multi-parameter experimental data
  125. Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting
  126. MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization
  127. TDPNavigator-Placer: Thermal- and Wirelength-Aware Chiplet Placement in 2.5D Systems Through Multi-Agent Reinforcement Learning
  128. GAC-KAN: An Ultra-Lightweight GNSS Interference Classifier for GenAI-Powered Consumer Edge Devices
  129. Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
  130. URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres
  131. Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
  132. Efficient Distance Pruning for Process Suffix Comparison in Prescriptive Process Monitoring
  133. Scaling GraphLLM with Bilevel-Optimized Sparse Querying
  134. Predicting Gene Disease Associations in Type 2 Diabetes Using Machine Learning on Single-Cell RNA-Seq Data
  135. E2CAR: An Efficient 2D-CNN Framework for Real-Time EEG Artifact Removal on Edge Devices
  136. Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
  137. Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks
  138. Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints
  139. Scalable spatial point process models for forensic footwear analysis
  140. Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction
  141. PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG
  142. A Comparative Simulation Study of the Fairness and Accuracy of Predictive Policing Systems in Baltimore City
  143. High Rank Matrix Completion via Grassmannian Proxy Fusion
  144. A General ReLearner: Empowering Spatiotemporal Prediction by Re-learning Input-label Residual
  145. Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
  146. PA-MIL: Phenotype-Aware Multiple Instance Learning Guided by Language Prompting and Genotype-to-Phenotype Relationships
  147. The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
  148. Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
  149. BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
  150. Super-r'esolution non supervis'ee d'images hyperspectrales de t'el'ed'etection utilisant un entrainement enti`erement synth'etique
  151. EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis
  152. naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement
  153. D2Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
  154. Norm Anchors Make Model Edits Last
  155. Auto-Augmentation Contrastive Learning for Wearable-based Human Activity Recognition
  156. Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks
  157. RobustDebias: Debiasing Language Models using Distributionally Robust Optimization
  158. A Conditional Companion: Lived Experiences of People with Mental Health Disorders Using LLMs
  159. ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control
  160. MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
  161. Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity
  162. 3DGS2-TR: Scalable Second-Order Trust-Region Method for 3D Gaussian Splatting
  163. Modeling Art Evaluations from Comparative Judgments: A Deep Learning Approach to Predicting Aesthetic Preferences
  164. Brazilian Portuguese Image Captioning with Transformers: A Study on Cross-Native-Translated Dataset
  165. Localized, High-resolution Geographic Representations with Slepian Functions
  166. Robust automatic brain vessel segmentation in 3D CTA scans using dynamic 4D-CTA data
  167. Singular Bayesian Neural Networks
  168. Generalized Inverses of Matrix Products: From Fundamental Subspaces to Randomized Decompositions
  169. Deep Learning-Based Object Detection for Autonomous Vehicles: A Comparative Study of One-Stage and Two-Stage Detectors on Basic Traffic Objects
  170. Modeling Image-Caption Rating from Comparative Judgments
  171. Parametrization of subgrid scales in long-term simulations of the shallow-water equations using machine learning and convex limiting
  172. DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models
  173. POET: Protocol Optimization via Eligibility Tuning
  174. Quantum Generator Kernels
  175. Leveraging Textual-Cues for Enhancing Multimodal Sentiment Analysis by Object Recognition
  176. MHDash: An Online Platform for Benchmarking Mental Health-Aware AI Assistants
  177. DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoning
  178. Standardized Methods and Recommendations for Green Federated Learning
  179. Adaptive Momentum and Nonlinear Damping for Neural Network Training
  180. Efficient and accurate steering of Large Language Models through attention-guided feature learning
  181. Prototype-based Explainable Neural Networks with Channel-specific Reasoning for Geospatial Learning Tasks
  182. In-Run Data Shapley for Adam Optimizer
  183. SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?
  184. Dual Quaternion SE(3) Synchronization with Recovery Guarantees
  185. Detecting AI-Generated Content in Academic Peer Reviews
  186. Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
  187. MiNER: A Two-Stage Pipeline for Metadata Extraction from Municipal Meeting Minutes
  188. Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors
  189. On the Assessment of Sensitivity of Autonomous Vehicle Perception
  190. Opportunistic Promptable Segmentation: Leveraging Routine Radiological Annotations to Guide 3D CT Lesion Segmentation
  191. Autonomous Data Processing using Meta-Agents
  192. Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors
  193. Neural Ising Machines via Unrolling and Zeroth-Order Training
  194. Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models
  195. From Observations to States: Latent Time Series Forecasting
  196. Multi-Speaker Conversational Audio Deepfake: Taxonomy, Dataset and Pilot Study
  197. Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation
  198. Computer Vision and Its Relationship to Cognitive Science: A perspective from Bayes Decision Theory
  199. TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
  200. Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA
  201. Training LLMs with Fault Tolerant HSDP on 100,000 GPUs
  202. Complete Identification of Deep ReLU Networks through Lukasiewicz Logic
  203. World-Shaper: A Unified Framework for 360deg Panoramic Editing
  204. Subspace Clustering on Incomplete Data with Self-Supervised Contrastive Learning
  205. Intelligent Reasoning Cues: A Framework and Case Study of the Roles of AI Information in Complex Decisions
  206. SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis
  207. Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
  208. MapDream: Task-Driven Map Learning for Vision-Language Navigation
  209. Benchmarking Vanilla GAN, DCGAN, and WGAN Architectures for MRI Reconstruction: A Quantitative Analysis
  210. Deep learning Based Correction Algorithms for 3D Medical Reconstruction in Computed Tomography and Macroscopic Imaging
  211. Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation
  212. GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection
  213. Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
  214. Development of a Cacao Disease Identification and Management App Using Deep Learning
  215. A Renderer-Enabled Framework for Computing Parameter Estimation Lower Bounds in Plenoptic Imaging Systems
  216. A Geometric Multimodal Foundation Model Integrating Bp-MRI and Clinical Reports in Prostate Cancer Classification
  217. Deep Learning Based CNN Model for Automated Detection of Pneumonia from Chest XRay Images
  218. Interpretable Unsupervised Deformable Image Registration via Confidence-bound Multi-Hop Visual Reasoning
  219. Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementarity
  220. Reducing Class-Wise Performance Disparity via Margin Regularization
  221. Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs
  222. SCALED : Surrogate-gradient for Codec-Aware Learning of Downsampling in ABR Streaming
  223. On the calibration of survival models with competing risks
  224. AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange
  225. From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
  226. LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild
  227. Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets
  228. SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation
  229. Visible Singularities Guided Correlation Network for Limited-Angle CT Reconstruction
  230. RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
  231. EigenAI: Deterministic Inference, Verifiable Results
  232. Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants
  233. How Understanding Forecast Uncertainty Resolves the Explainability Problem in Machine Learning Models
  234. Intra-Class Subdivision for Pixel Contrastive Learning: Application to Semi-supervised Cardiac Image Segmentation
  235. Neuron Block Dynamics for XOR Classification with Zero-Margin
  236. Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervals
  237. The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
  238. End-to-end Optimization of Belief and Policy Learning in Shared Autonomy Paradigms
  239. User Prompting Strategies and Prompt Enhancement Methods for Open-Set Object Detection in XR Environments
  240. FOCUS: DLLMs Know How to Tame Their Compute Bound
  241. Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
  242. PaperBanana: Automating Academic Illustration for AI Scientists
  243. TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
  244. Agnostic Language Identification and Generation
  245. Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models
  246. Nested Slice Sampling: Vectorized Nested Sampling for GPU-Accelerated Inference
  247. Graph Attention Network for Node Regression on Random Geometric Graphs with ErdHos--R'enyi contamination
  248. YuriiFormer: A Suite of Nesterov-Accelerated Transformers
  249. ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search
  250. Solving Inverse Problems with Flow-based Models via Model Predictive Control
  251. Strongly Polynomial Time Complexity of Policy Iteration for L_∞ Robust MDPs
  252. Scaling Multiagent Systems with Process Rewards
  253. Are you going to finish that? A Practical Study of the Partial Token Problem
  254. Region-Normalized DPO for Medical Image Segmentation under Noisy Judges
  255. Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints
  256. Tackling air quality with SAPIENS
  257. Disentangling multispecific antibody function with graph neural networks
  258. A Random Matrix Theory of Masked Self-Supervised Regression
  259. Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
  260. High-quality generation of dynamic game content via small language models: A proof of concept
  261. TSAQA: Time Series Analysis Question And Answering Benchmark
  262. Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
  263. JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual R'esum'es and JDs
  264. Ensuring Semantics in Weights of Implicit Neural Representations through the Implicit Function Theorem
  265. MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanics
  266. Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
  267. Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
  268. Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm
  269. Monotonic Reference-Free Refinement for Autoformalization
  270. Stochastic Linear Bandits with Parameter Noise
  271. DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
  272. Segment Any Events with Language
  273. No More, No Less: Least-Privilege Language Models
  274. SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training
  275. On Safer Reinforcement Learning for Sedation and Analgesia in Intensive Care
  276. Manifold-Aware Perturbations for Constrained Generative Modeling
  277. Compressed BC-LISTA via Low-Rank Convolutional Decomposition
  278. Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failures
  279. Machine Learning for Energy-Performance-aware Scheduling
  280. Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines
  281. Regularisation in neural networks: a survey and empirical analysis of approaches
  282. Distribution-informed Efficient Conformal Prediction for Full Ranking
  283. To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
  284. FlowCalib: LiDAR-to-Vehicle Miscalibration Detection using Scene Flows
  285. Vision-Language Controlled Deep Unfolding for Joint Medical Image Restoration and Segmentation
  286. Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective
  287. Safer Policy Compliance with Dynamic Epistemic Fallback
  288. WiFiPenTester: Advancing Wireless Ethical Hacking with Governed GenAI
  289. From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
  290. ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
  291. Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection
  292. EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing
  293. HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation
  294. On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study
  295. Adaptive Edge Learning for Density-Aware Graph Generation
  296. MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration
  297. From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
  298. The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
  299. Avoiding Premature Collapse: Adaptive Annealing for Entropy-Regularized Structural Inference
  300. Scale Equivariance Regularization and Feature Lifting in High Dynamic Range Modulo Imaging
  301. Breaking the Stochasticity Barrier: An Adaptive Variance-Reduced Method for Variational Inequalities
  302. Asymptotic Theory of Iterated Empirical Risk Minimization, with Applications to Active Learning
  303. Neural Backward Filtering Forward Guiding
  304. Root Cause Analysis of Measurement and Mechanistic Anomalies
  305. DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis
  306. Integrating Multi-Label Classification and Generative AI for Scalable Analysis of User Feedback
  307. Mem-T: Densifying Rewards for Long-Horizon Memory Agents
  308. Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG
  309. Leveraging Multi-Rater Annotations to Calibrate Object Detectors in Microscopy Imaging
  310. InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
  311. Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs
  312. Mano: Restriking Manifold Optimization for LLM Training
  313. Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI
  314. ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform
  315. PIDSMaker: Building and Evaluating Provenance-based Intrusion Detection Systems
  316. About an Automating Annotation Method for Robot Markers
  317. Learnable Permutation for Structured Sparsity on Transformer Models
  318. Quantifying Model Uniqueness in Heterogeneous AI Ecosystems
  319. Improved Algorithms for Nash Welfare in Linear Bandits
  320. A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
  321. EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
  322. Perplexity Cannot Always Tell Right from Wrong
  323. Alignment among Language, Vision and Action Representations
  324. From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models
  325. Environment-Conditioned Tail Reweighting for Invariant Learning under Mixed Shifts
  326. Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
  327. A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration
  328. Protecting Private Code in IDE Autocomplete using Differential Privacy
  329. DC-LA: Difference-of-Convex Langevin Algorithm
  330. Benchmarking Machine Translation on Chinese Social Media Texts
  331. Semantic Leakage from Image Embeddings
  332. BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
  333. Evaluating Large Language Models for Security Bug Report Prediction
  334. Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment
  335. Deep in the Jungle: Towards Automating Chimpanzee Population Estimation
  336. Multi-Cue Anomaly Detection and Localization under Data Contamination
  337. FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
  338. Uncertainty-Aware Extrapolation in Bayesian Oblique Trees
  339. Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery
  340. Calibrated Multivariate Distributional Regression with Pre-Rank Regularization
  341. MoVE: Mixture of Value Embeddings -- A New Axis for Scaling Parametric Memory in Autoregressive Models
  342. Leveraging LLMs For Turkish Skill Extraction
  343. Synthetic Time Series Generation via Complex Networks
  344. Development of Domain-Invariant Visual Enhancement and Restoration (DIVER) Approach for Underwater Images
  345. Matterhorn: Masked Time-to-First-Spike Encoding by Reassigning the Silent State for Sparse and Energy-Efficient Spiking Transformers
  346. From Labels to Facets: Building a Taxonomically Enriched Turkish Learner Corpus
  347. Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild
  348. Conditional Compatibility Learning for Context-Dependent Anomaly Detection
  349. Under-Canopy Terrain Reconstruction in Dense Forests Using RGB Imaging and Neural 3D Reconstruction
  350. Bayesian Interpolating Neural Network (B-INN): a scalable and reliable Bayesian model for large-scale physical systems
  351. MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
  352. Learning to Build Shapes by Extrusion
  353. OptiMAG: Structure-Semantic Alignment via Unbalanced Optimal Transport
  354. Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
  355. Hierarchical Shift Mixing -- Beyond Dense Attention in Transformers
  356. When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training
  357. Unconditional flow-based time series generation with equivariance-regularised latent spaces
  358. How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
  359. NativeTok: Native Visual Tokenization for Improved Image Generation
  360. Just-in-Time Catching Test Generation at Meta
  361. User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering
  362. Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
  363. FarmMind: Reasoning-Query-Driven Dynamic Segmentation for Farmland Remote Sensing Images
  364. Diachronic Stereo Matching for Multi-Date Satellite Imagery
  365. Aligning the Unseen in Attributed Graphs: Interplay between Graph Geometry and Node Attributes Manifold
  366. SOMBRERO: Measuring and Steering Boundary Placement in End-to-End Hierarchical Sequence Models
  367. Trackly: A Unified SaaS Platform for User Behavior Analytics and Real Time Rule Based Anomaly Detection
  368. HeatMat: Simulation of City Material Impact on Urban Heat Island Effect
  369. Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
  370. CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
  371. Float8@2bits: Entropy Coding Enables Data-Free Model Compression
  372. Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework
  373. Approximating f-Divergences with Rank Statistics
  374. Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval
  375. Color Matters: Demosaicing-Guided Color Correlation Training for Generalizable AI-Generated Image Detection
  376. GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
  377. Beyond Abstract Compliance: Operationalising trust in AI as a moral relationship
  378. Sparse Attention as Compact Kernel Regression
  379. Bayesian Matrix Completion Under Geometric Constraints
  380. How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation
  381. Is Task-Specific Training Necessary for Anomaly Detection?
  382. AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
  383. Qualitative Evaluation of LLM-Designed GUI
  384. Unveiling Scaling Behaviors in Molecular Language Models: Effects of Model Size, Data, and Representation
  385. Understanding Generalization from Embedding Dimension and Distributional Convergence
  386. OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
  387. Discovering Scaling Exponents with Physics-Informed M"untz-Sz'asz Networks
  388. Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss
  389. Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing
  390. Uncertainty-aware Causal Decision Making via Effect Bound Decomposition
  391. Active Learning-Driven Lightweight YOLOv9: Enhancing Efficiency in Smart Agriculture
  392. A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement
  393. Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
  394. AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises
  395. Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation
  396. SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks
  397. AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
  398. A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation
  399. Deep Learning-Based Early-Stage IR-Drop Estimation via CNN Surrogate Modeling
  400. DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation
  401. Metric Hub: A metric library and practical selection workflow for use-case-driven data quality assessment in medical AI
  402. Models Know Models Best: Evaluation via Model-Preferred Formats
  403. PEAR: Pixel-aligned Expressive humAn mesh Recovery
  404. FNF: Functional Network Fingerprint for Large Language Models
  405. Do Transformers Have the Ability for Periodicity Generalization?
  406. OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection
  407. Visual Personalization Turing Test
  408. Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective
  409. Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition
  410. Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning
  411. From Horizontal Layering to Vertical Integration: A Comparative Study of the AI-Driven Software Development Paradigm
  412. ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding
  413. Unsupervised Synthetic Image Attribution: Alignment and Disentanglement
  414. Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support
  415. Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks
  416. NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models
  417. Human-Centered Explainability in AI-Enhanced UI Security Interfaces: Designing Trustworthy Copilots for Cybersecurity Analysts
  418. Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
  419. Generative and Nonparametric Approaches for Conditional Distribution Estimation: Methods, Perspectives, and Comparative Evaluations
  420. UCPO: Uncertainty-Aware Policy Optimization
  421. Beyond Medical Chatbots: Meddollina and the Rise of Continuous Clinical Intelligence
  422. ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review
  423. Training Beyond Convergence: Grokking nnU-Net for Glioma Segmentation in Sub-Saharan MRI
  424. What can Computer Vision learn from Ranganathan?
  425. MCP-Diag: A Deterministic, Protocol-Driven Architecture for AI-Native Network Diagnostics
  426. DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
  427. PEFT-MuTS: A Multivariate Parameter-Efficient Fine-Tuning Framework for Remaining Useful Life Prediction based on Cross-domain Time Series Representation Model
  428. LINA: Linear Autoregressive Image Generative Models with Continuous Tokens
  429. RPWithPrior: Label Differential Privacy in Regression
  430. UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating
  431. TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
  432. Stabilizing Transformer Training Through Consensus
  433. Local-Global Multimodal Contrastive Learning for Molecular Property Prediction
  434. From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
  435. An Efficient Algorithm for Thresholding Monte Carlo Tree Search
  436. TimeMachine-bench: A Benchmark for Evaluating Model Capabilities in Repository-Level Migration Tasks
  437. FOTBCD: A Large-Scale Building Change Detection Benchmark from French Orthophotos and Topographic Data
  438. Heterogeneous Graph Alignment for Joint Reasoning and Interpretability
  439. WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction
  440. HetCCL: Accelerating LLM Training with Heterogeneous GPUs
  441. Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model
  442. Non-Intrusive Graph-Based Bot Detection for E-Commerce Using Inductive Graph Neural Networks
  443. FedDis: A Causal Disentanglement Framework for Federated Traffic Prediction
  444. Bonnet: Ultra-fast whole-body bone segmentation from CT scans
  445. DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library
  446. Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
  447. EUGens: Efficient, Unified, and General Dense Layers
  448. Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion
  449. Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation
  450. Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
  451. Detect and Act: Automated Dynamic Optimizer through Meta-Black-Box Optimization
  452. Benchmarking Long Roll-outs of Auto-regressive Neural Operators for the Compressible Navier-Stokes Equations with Conserved Quantity Correction
  453. Neural-Inspired Posterior Approximation (NIPA)
  454. Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models
  455. EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation
  456. Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
  457. Learn from A Rationalist: Distilling Intermediate Interpretable Rationales
  458. SHED Light on Segmentation for Dense Prediction
  459. Can 3D point cloud data improve automated body condition score prediction in dairy cattle?
  460. SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making
  461. DNA: Uncovering Universal Latent Forgery Knowledge
  462. DRL-Enabled Trajectory Planing for UAV-Assisted VLC: Optimal Altitude and Reward Design
  463. Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
  464. Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks
  465. CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content
  466. MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
  467. PromptMAD: Cross-Modal Prompting for Multi-Class Visual Anomaly Localization
  468. Elastic Spectral State Space Models for Train-Once Budgeted Inference
  469. AI Literacy, Safety Awareness, and STEM Career Aspirations of Australian Secondary Students: Evaluating the Impact of Workshop Interventions
  470. FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
  471. Changepoint Detection As Model Selection: A General Framework
  472. RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning
  473. Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology
  474. EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug Design
  475. Toward Non-Expert Customized Congestion Control: Large Language Model-Assisted CCA Code Generation with eBPF Deployment
  476. AI Decodes Historical Chinese Archives to Reveal Lost Climate History
  477. ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction
  478. Temporal Graph Pattern Machine
  479. Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot Interaction
  480. High-Definition 5MP Stereo Vision Sensing for Robotics
  481. Automating Forecasting Question Generation and Resolution for AI Evaluation
  482. AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
  483. Simulation-based Bayesian inference with ameliorative learned summary statistics -- Part I
  484. AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
  485. Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss
  486. Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective
  487. When LLM meets Fuzzy-TOPSIS for Personnel Selection through Automated Profile Analysis
  488. CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks
  489. MetaLead: A Comprehensive Human-Curated Leaderboard Dataset for Transparent Reporting of Machine Learning Experiments
  490. Dynamic Welfare-Maximizing Pooled Testing
  491. AI-Enabled Waste Classification as a Data-Driven Decision Support Tool for Circular Economy and Urban Sustainability