mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 3 Feb 2026

585 papers

  1. WebExpert: domain-aware web agents with critic-guided expert experience for high-precision searchLLM agents and tool use → Web, search, and research agents
  2. One Size Does Not Fit All: Token-Wise Adaptive Compression for KV CacheEfficient LLM inference and serving → KV cache optimization
  3. SalamahBench: Toward Standardized Safety Evaluation for Arabic Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  4. TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured GenerationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. Developing a Multi-Agent System to Generate Next Generation Science Assessments with Evidence-Centered DesignLLM agents and tool use → Educational agents and math problem solving
  6. MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI SystemsLLM agents and tool use → Agent memory systems
  7. Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-AssistabilityLLM agents and tool use → Software engineering coding agents
  8. DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech SynthesisDiffusion models → Audio, speech and music
  9. UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual DocumentsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  10. DLLM-Searcher: Adapting Diffusion Large Language Model for Search AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  11. ST-Raptor: An Agentic System for Semi-Structured Table QALLM agents and tool use → Web, search, and research agents
  12. TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in HealthcareDiffusion models → Medical imaging and segmentation
  13. LLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code GenerationLLM reasoning → Reasoning for agents, planning and code
  14. PackInfer: Compute- and I/O-Efficient Attention for Batched LLM InferenceEfficient LLM inference and serving → KV cache optimization
  15. Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  16. Phantom Transfer: Data Poisoning can Survive Data-Level DefencesLLM safety and security → Backdoor and data poisoning attacks
  17. Semantic-level Backdoor Attack against Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  18. Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  19. BASS: Benchmarking Audio LMs for Musical Structure and Semantic ReasoningLLM reasoning → Audio-language model reasoning
  20. A Probabilistic Framework for Solving High-Frequency Helmholtz Equations via Diffusion ModelsDiffusion models → Flow matching, time series and science
  21. Agentic AI-Empowered Dynamic Survey FrameworkLLM agents and tool use → Web, search, and research agents
  22. DADP: Domain Adaptive Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  23. PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation ModelsSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  24. After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona InteractionsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  25. Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  26. Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document RetrievalRetrieval-augmented generation → Multimodal RAG
  27. Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic DisentanglementVision-language-action models → Efficient VLA inference and adaptation
  28. Likelihood-Based Reward Designs for General LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  29. Monitorability as a Free Gift: How RLVR Spontaneously Aligns ReasoningLLM reasoning → Reinforcement learning for reasoning
  30. Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical StructureLLM reasoning → Test-time compute and efficient thinking
  31. VLS: Steering Pretrained Robot Policies via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  32. Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal FlightDeep reinforcement learning methods → Safe and constrained RL
  33. AgentArk: Distilling Multi-Agent Intelligence into a Single LLM AgentLLM reasoning → Reasoning for agents, planning and code +1
  34. Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning AugmentationLLM reasoning → Mathematical reasoning
  35. Autonomous AI Agents for Real-Time Affordable Housing Site Selection: Multi-Objective Reinforcement Learning Under Regulatory ConstraintsDeep reinforcement learning methods → RL for games and combinatorial optimization
  36. SpecMD: A Comprehensive Study On Speculative Expert PrefetchingMixture-of-experts → Efficient MoE training and inference systems
  37. SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?LLM reasoning → Spatial and embodied reasoning +1
  38. The Role of Target Update Frequencies in Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
  39. Knowledge Model Prompting Increases LLM Performance on Planning TasksLLM reasoning → Reasoning for agents, planning and code
  40. 4DPC2hat: Towards Dynamic Point Cloud Understanding with Failure-Aware BootstrappingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  41. SymPlex: A Structure-Aware Transformer for Symbolic PDE SolvingDeep reinforcement learning methods → Interpretable and logic-guided RL
  42. Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  43. Conformal Thinking: Risk Control for Reasoning on a Compute BudgetLLM reasoning → Test-time compute and efficient thinking
  44. Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code GenerationOffline RL and imitation learning from data → Offline RL algorithms
  45. FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-TranslationLLM agents and tool use → Software engineering coding agents
  46. Understanding Agent Scaling in LLM-Based Multi-Agent Systems via DiversityLLM agents and tool use → General LLM agent frameworks and benchmarks
  47. BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment MasksWorld models → Embodied and robot world models
  48. WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  49. Inference-time Unlearning Using Conformal PredictionLLM safety and security → Machine unlearning
  50. AOrchestra: Automating Sub-Agent Creation for Agentic OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  51. Fix the Structural Bottleneck: Context Compression via Explicit Information TransmissionLLM agents and tool use → Agent memory systems +1
  52. Efficient Estimation of Kernel Surrogate Models for Task AttributionLLM reasoning → Reinforcement learning for reasoning
  53. QVLA: Not All Channels Are Equal in Vision-Language-Action Model's QuantizationVision-language-action models → Efficient VLA inference and adaptation
  54. DiffLOB: Diffusion Models for Counterfactual Generation in Limit Order BooksDiffusion models → Flow matching, time series and science
  55. An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model AgentsLLM agents and tool use → Social simulation and multi-agent debate
  56. Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RLLLM reasoning → Reinforcement learning for reasoning
  57. Reasoning with Latent Tokens in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  58. Conditional Flow Matching for Visually-Guided Acoustic HighlightingDiffusion models → Audio, speech and music
  59. Test-Time Conditioning with Representation-Aligned Visual FeaturesDiffusion models → Diffusion foundations and sampling
  60. Zero-shot large vision-language model prompting for automated bone identification in paleoradiology x-ray archivesMultimodal LLMs / vision-language models → Medical vision-language models
  61. LIVE: Long-horizon Interactive Video World ModelingWorld models → Video-generation world models and simulators
  62. Edge-Optimized Vision-Language Models for Underground Infrastructure AssessmentMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  63. RegionReasoner: Region-Grounded Multi-Round Visual ReasoningLLM reasoning → Multimodal reasoning +1
  64. CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device DeploymentRetrieval-augmented generation → RAG pipeline design and evaluation
  65. BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  66. Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal StatesEfficient LLM inference and serving → Speculative decoding
  67. OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question AnsweringLLM agents and tool use → Multimodal and embodied agents
  68. Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language ModelsLLM agents and tool use → Educational agents and math problem solving
  69. Agent Primitives: Reusable Latent Building Blocks for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  70. OCRTurk: A Comprehensive OCR Benchmark for TurkishRetrieval-augmented generation → Multimodal RAG
  71. Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  72. TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
  73. MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint ReconstructionVision-language-action models → Human-video and latent-action pretraining
  74. MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise AlignmentLLM reasoning → Reasoning benchmarks and evaluation +2
  75. Mitigating Conversational Inertia in Multi-Turn AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. RAGTurk: Best Practices for Retrieval Augmented Generation in TurkishRetrieval-augmented generation → RAG pipeline design and evaluation
  77. Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAGRetrieval-augmented generation → Agentic RAG, agents and memory
  78. Tutorial on Reasoning for IR & IR for ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  79. Can LLMs Do Rocket Science? Exploring the Limits of Complex Reasoning with GTOC 12LLM reasoning → Reasoning for agents, planning and code
  80. Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report GenerationLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  81. KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  82. Explanations Leak: Membership Inference with Differential Privacy and Active Learning DefenseLLM safety and security → Membership inference attacks
  83. A Lightweight Library for Energy-Based Joint-Embedding Predictive ArchitecturesWorld models → Latent predictive world models
  84. Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object SegmentationLLM reasoning → Multimodal reasoning +1
  85. CL-bench: A Benchmark for Context LearningLLM reasoning → Reasoning benchmarks and evaluation
  86. Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool DescriptionsLLM agents and tool use → Agent threats, guardrails and governance
  87. Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  88. EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical TrajectoriesWorld models → Medical and surgical world models
  89. EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate UnlearningLLM safety and security → Machine unlearning
  90. CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series ForecastingDiffusion models → Flow matching, time series and science
  91. HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache SharingMixture-of-experts → Efficient MoE training and inference systems +1
  92. When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMsLLM reasoning → Clinical and biomedical applications
  93. SEAD: Self-Evolving Agent for Multi-Turn Service DialogueLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  94. AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic GraspingLLM reasoning → Spatial and embodied reasoning
  95. PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  96. Channel-Aware Conditional Diffusion Model for Secure MU-MISO CommunicationsDiffusion models → Diffusion for compression and wireless
  97. D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation From Lead sheetDiffusion models → Audio, speech and music
  98. Not All Negative Samples Are Equal: LLMs Learn Better from Plausible ReasoningLLM reasoning → Reinforcement learning for reasoning
  99. Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  100. FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness MaximizationLLM reasoning → Reinforcement learning for reasoning
All 585
  1. Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression ModelsMechanistic interpretability → Circuits and mechanistic analysis
  2. Reparameterization Flow Policy OptimizationDeep reinforcement learning methods → RL with diffusion and flow models
  3. DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCsMixture-of-experts → Efficient MoE training and inference systems
  4. Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware GuidanceLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. Path Integration and Object-Location Binding Emerge in an Action-Conditioned Predictive Sequence NetworkWorld models → World models for navigation
  6. Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  7. ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and ExpressionDiffusion models → Flow matching, time series and science
  8. Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-ExpertsMixture-of-experts → Mixture of LoRA experts
  9. IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  10. Contextualized Visual Personalization in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional PairingLLM reasoning → Reinforcement learning for reasoning
  12. Score-based diffusion models for severely ill-posed problems in diffuse optical tomographyDiffusion models → Inverse problems and image restoration
  13. Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image GenerationDiffusion models → Image generation, text-to-image and editing
  14. CRL-VLA: Continual Vision-Language-Action LearningVision-language-action models → Reinforcement learning and post-training
  15. A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval InterfacesLLM reasoning → Knowledge- and tool-augmented reasoning +2
  16. Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agentsLLM agents and tool use → Web, search, and research agents
  17. Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal GraphsLLM agents and tool use → Web, search, and research agents
  18. ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-TuningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  19. CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation SteeringMechanistic interpretability → Activation steering methods
  20. SWE-World: Building Software Engineering Agents in Docker-Free EnvironmentsLLM agents and tool use → Software engineering coding agents
  21. Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent InteractionLLM reasoning → Spatial and embodied reasoning +3
  22. Verified Critical Step Optimization for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  23. SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-TrainingLLM agents and tool use → Software engineering coding agents
  24. UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA UnlearningDiffusion models → Image generation, text-to-image and editing +1
  25. Enhancing Quantum Diffusion Models for Complex Image GenerationDiffusion models → Diffusion foundations and sampling
  26. Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising UtilityLLM reasoning → Reasoning for agents, planning and code +2
  27. Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RLOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  28. An Approximate Ascent Approach To Prove Convergence of PPODeep reinforcement learning methods → RL theory and sample complexity
  29. Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference OptimizationLLM reasoning → Hallucination detection and mitigation +1
  30. Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning FailuresLLM safety and security → Machine unlearning
  31. SLIM-Diff: Shared Latent Image-Mask Diffusion with Lp loss for Data-Scarce Epilepsy FLAIR MRIDiffusion models → Medical imaging and segmentation
  32. GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression RecognitionDiffusion models → Image generation, text-to-image and editing
  33. Pursuing Best Industrial Practices for Retrieval-Augmented Generation in the Medical DomainRetrieval-augmented generation → Medical and biomedical RAG
  34. PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  35. Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  36. MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric DiagnosisLLM reasoning → Clinical and biomedical applications
  37. Accurate Failure Prediction in Agents Does Not Imply Effective Failure PreventionLLM agents and tool use → Software engineering coding agents
  38. GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and AudioLLM safety and security → Safety alignment, refusal and guardrails
  39. MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement LearningLLM agents and tool use → Medical and scientific domain agents
  40. MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations ResearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Invisible Clean-Label Backdoor Attacks for Generative Data AugmentationLLM safety and security → Backdoor and data poisoning attacks
  42. RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment GeneralizationVision-language-action models → Generalist VLA models and benchmarks
  43. medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential FunctionsOffline RL and imitation learning from data → Safe offline RL
  44. Periodic Regularized Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
  45. R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  46. POP: Prefill-Only Pruning for Efficient Large Model InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  47. Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill SynthesisLLM reasoning → Reasoning for agents, planning and code +1
  48. Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  49. CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  50. LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial ScenariosLLM agents and tool use → Agent threats, guardrails and governance
  51. Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  52. InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video GenerationWorld models → World models for autonomous driving +1
  53. "LLM Agent Performance" Is Not a Single Evaluation TargetLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. EventFlash: Towards Efficient MLLMs for Event-Based VisionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  55. TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic BenchmarkingLLM agents and tool use → Agent memory systems
  56. PokeFusion Attention: A Lightweight Cross-Attention Mechanism for Style-Conditioned Image GenerationDiffusion models → Image generation, text-to-image and editing
  57. Beyond Quantity: Trajectory Diversity Scaling for Code AgentsLLM agents and tool use → Software engineering coding agents
  58. FARTrack: Fast Autoregressive Visual Tracking with High PerformanceKnowledge distillation → Detection and dense prediction distillation
  59. ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance MaskWorld models → World models for autonomous driving +1
  60. Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  61. VIRAL: Visual In-Context Reasoning via Analogy in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  62. Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image GenerationLLM reasoning → Diffusion reasoning and test-time scaling
  63. Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical GeometryMixture-of-experts → Expert routing strategies
  64. ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term ContributionLLM reasoning → Test-time compute and efficient thinking +1
  65. SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  66. PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  67. Hierarchical Proportion Models for Motion Generation via Integration of Motion PrimitivesOffline RL and imitation learning from data → Robot manipulation imitation learning
  68. DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  69. LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  70. Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-DebuggingLLM reasoning → Reasoning for agents, planning and code
  71. StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret ModelingDeep reinforcement learning methods → RL training of language and agent models
  72. MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned ReasoningLLM reasoning → Time series reasoning
  73. VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  74. PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation DetectionLLM agents and tool use → Web, search, and research agents
  75. When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual TokensVision-language-action models → Safety and adversarial attacks
  76. FASA: Frequency-aware Sparse AttentionEfficient LLM inference and serving → KV cache optimization
  77. Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature RestorationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  78. General Agents Contain World Models, even under Partial Observability and StochasticityWorld models → World models for language agents
  79. Internet of Agentic AI: Incentive-Compatible Distributed Teaming and WorkflowLLM agents and tool use → General LLM agent frameworks and benchmarks
  80. Self-Hinting Language Models Enhance Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  81. Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge OptimizationLLM reasoning → Test-time compute and efficient thinking
  82. SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token BypassMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  83. FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent EvaluationLLM reasoning → Reasoning for agents, planning and code +2
  84. Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM PerformanceLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  86. Function-Space Empirical Bayes Regularisation with Large Vision-Language Model PriorsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  87. A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  88. Gromov Wasserstein Optimal Transport for Semantic CorrespondencesDiffusion models → Image generation, text-to-image and editing
  89. Consensus Group Relative Policy Optimization for Text GenerationLLM reasoning → Reinforcement learning for reasoning
  90. Risky-Bench: Probing Agentic Safety Risks under Real-World DeploymentLLM agents and tool use → Agent threats, guardrails and governance
  91. De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language ModelsLLM reasoning → LLM reasoning for recommendation +1
  92. Test-time Recursive Thinking: Self-Improvement without External FeedbackLLM reasoning → Reinforcement learning for reasoning +1
  93. Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot locomotion and manipulation
  94. Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  95. The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor TriggersLLM safety and security → Backdoor and data poisoning attacks
  96. AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop FeedbackLLM reasoning → Test-time compute and efficient thinking
  97. TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFTLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  98. Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative SignalsLLM reasoning → Mathematical reasoning
  99. IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  100. MAS-ProVe: Understanding the Process Verification of Multi-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
  101. SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM CompressionMechanistic interpretability → SAE features and their applications
  102. CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMsLLM reasoning → Reinforcement learning for reasoning
  103. Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD GenerationLLM agents and tool use → Multimodal and embodied agents
  104. SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision BackbonesEfficient LLM inference and serving → Early exit and edge inference
  105. DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision TransformersLLM safety and security → Backdoor and data poisoning attacks
  106. Bongards at the Boundary of Perception and Reasoning: Programs or Language?LLM reasoning → Multimodal reasoning +1
  107. LatentMem: Customizing Latent Memory for Multi-Agent SystemsLLM agents and tool use → Agent memory systems
  108. Visual Reasoning over Time Series via Multi-Agent SystemLLM reasoning → Time series reasoning +1
  109. RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling AgentsLLM reasoning → Reinforcement learning for reasoning +1
  110. STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  111. CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security VulnerabilityLLM agents and tool use → Agent threats, guardrails and governance
  112. Distilling LLM Reasoning into Graph of Concept PredictorsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  113. Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  114. Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use AgentsLLM reasoning → Reasoning for agents, planning and code +1
  115. Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy DistillationLLM reasoning → Multimodal reasoning +2
  116. Learning to Repair Lean Proofs from Compiler FeedbackLLM agents and tool use → Educational agents and math problem solving
  117. Why Some Models Resist Unlearning: A Linear Stability PerspectiveLLM safety and security → Machine unlearning
  118. Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute BudgetsLLM reasoning → Causal reasoning in LLMs
  119. CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  120. Structuring Value Representations via Geometric Coherence in Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  121. Aligning Forest and Trees in Images & Long Captions for Visually Grounded UnderstandingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  122. Where Norms and References Collide: Evaluating LLMs on Normative ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  123. Learning Fast Monomial Orders for Gr"obner Basis ComputationsDeep reinforcement learning methods → RL theory and sample complexity
  124. Generative Engine Optimization: A VLM and Agent Framework for Pinterest Acquisition GrowthLLM agents and tool use → Multimodal and embodied agents
  125. Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  126. Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache QuantizationDiffusion models → Video generation +1
  127. N"uwa: Mending the Spatial Integrity Torn by VLM Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  128. 3D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused LearningDiffusion models → Diffusion foundations and sampling
  129. AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit IdentificationLLM agents and tool use → Software engineering coding agents
  130. Distance Marching for Generative ModelingDiffusion models → Flow matching, time series and science
  131. Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
  132. To Throw a Stone with Six Birds: On Agents and Agenthood
  133. One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
  134. Verify as You Go: An LLM-Powered Browser Extension for Fake News Detection
  135. Multiclass Hate Speech Detection with RoBERTa-OTA: Integrating Transformer Attention and Graph Convolutional Networks
  136. Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
  137. Additive Multi-Step Markov Chains and the Curse of Dimensionality in Large Language Models
  138. Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
  139. Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World
  140. Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs
  141. Riemannian Dueling Optimization
  142. Noise reduction in BERT NER models for clinical entity extraction
  143. From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization
  144. Universality of shallow and deep neural networks on non-Euclidean spaces
  145. Contextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound
  146. BamaER: A Behavior-Aware Memory-Augmented Model for Exercise Recommendation
  147. IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation
  148. Multimodal Consistency-Guided Reference-Free Data Selection for ASR Accent Adaptation
  149. General learned delegation by clones
  150. A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks
  151. Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition
  152. The Anatomy of the Moltbook Social Graph
  153. OMNI-Dent: Towards an Accessible and Explainable AI Framework for Automated Dental Diagnosis
  154. Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods
  155. When Excellence Stops Producing Knowledge: A Practitioner's Observation on Research Funding
  156. Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian
  157. MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
  158. Lagged backward-compatible physics-informed neural networks for unsaturated soil consolidation analysis
  159. Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models
  160. LISA: Laplacian In-context Spectral Analysis
  161. DCER: Dual-Stage Compression and Energy-Based Reconstruction
  162. Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering
  163. Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction
  164. Evaluating Kubernetes Performance for GenAI Inference: From Automatic Speech Recognition to LLM Summarization
  165. Privacy Amplification Persists under Unlimited Synthetic Data Release
  166. Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL
  167. Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition
  168. Abstraction Induces the Brain Alignment of Language and Speech Models
  169. Principles of Lipschitz continuity in neural networks
  170. Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion
  171. Thermodynamic assessment of machine learning models for solid-state synthesis prediction
  172. Stroke Lesions as a Rosetta Stone for Language Model Interpretability
  173. An Empirical Survey and Benchmark of Learned Distance Indexes for Road Networks
  174. iSight: Towards expert-AI co-assessment for improved immunohistochemistry staining interpretation
  175. SEIS: Subspace-based Equivariance and Invariance Scores for Neural Representations
  176. Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal
  177. Artifact Removal and Image Restoration in AFM:A Structured Mask-Guided Directional Inpainting Approach
  178. Fast, Unsupervised Framework for Registration Quality Assessment of Multi-stain Histological Whole Slide Pairs
  179. A Parameterizable Convolution Accelerator for Embedded Deep Learning Applications
  180. AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting
  181. Partition Tree: Conditional Density Estimation over General Outcome Spaces
  182. On the Credibility of Evaluating LLMs using Survey Questions
  183. MS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment
  184. The Illusion of Generalization in Tabular Language Models
  185. TiCLS : Tightly Coupled Language Text Spotter
  186. Axiomatic Foundations of Counterfactual Explanations
  187. A Consensus-Bayesian Framework for Detecting Malicious Activity in Enterprise Directory Access Graphs
  188. Group Contrastive Learning for Weakly Paired Multimodal Data
  189. Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models
  190. Chaplains' Reflections on the Design and Usage of AI for Conversational Care
  191. A Multi-Modal Foundational Model for Wireless Communication and Sensing
  192. PromptSplit: Revealing Prompt-Level Disagreement in Generative Models
  193. Rational ANOVA Networks
  194. When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
  195. Functional Stochastic Localization
  196. AtlasPatch: Scalable Foundation Model-based Tissue Detection and Patch Extraction for Computational Pathology
  197. eCP: Equivariant Conformal Prediction with pre-trained models
  198. DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks
  199. Transformers perform adaptive partial pooling
  200. Active Epistemic Control for Query-Efficient Verified Planning
  201. Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
  202. Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
  203. Structural shifts in institutional participation and collaboration within the AI arXiv preprint research ecosystem
  204. Non-linear PCA via Evolution Strategies: a Novel Objective Function
  205. Automatic Classification of Pedagogical Materials against CS Curriculum Guidelines
  206. Temporal Validation Changes the Apparent Public-Health Utility of Under-Five Mortality Prediction in Bangladesh: A Four-Round DHS Machine-Learning Study
  207. Learning Multi-type heterogeneous interacting particle systems
  208. Representation Geometry as a Diagnostic for Out-of-Distribution Robustness
  209. Semantic Rate Distortion and Posterior Design: Compute Constraints, Multimodality, and Strategic Inference
  210. Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks
  211. Grables: When Graph Structure Helps Tabular Prediction
  212. Linguistic Blind Spots in Clinical Decision Extraction
  213. C-IDS: Solving Contextual POMDP via Information-Directed Objective
  214. First-Principles AI finds crystallization of fractional quantum Hall liquids
  215. WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling
  216. Online Vector Quantized Attention
  217. Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers
  218. Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science
  219. Causal Discovery for Cross-Sectional Data Based on Super-Structure and Divide-and-Conquer
  220. Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition
  221. Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
  222. Beyond the Vehicle: Cooperative Localization by Fusing Point Clouds for GPS-Challenged Urban Scenarios
  223. HY3D-Bench: Generation of 3D Assets
  224. GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
  225. All-Atom GPCR-Ligand Dynamics Simulation via a Residual Latent Flow Mode
  226. NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
  227. Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
  228. A hitchhiker's guide to Poisson gradient estimation
  229. Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
  230. Vision Transformers for Zero-Shot Clustering of Animal Images: A Comparative Benchmarking Study
  231. GPAIR: Gaussian-Kernel-Based Ultrafast 3D Photoacoustic Iterative Reconstruction
  232. Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation
  233. Sounding Highlights: Dual-Pathway Audio Encoders for Audio-Visual Video Highlight Detection
  234. Transcendental Regularization of Finite Mixtures:Theoretical Guarantees and Practical Limitations
  235. To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?
  236. Prenatal Stress Detection from Electrocardiography Using Self-Supervised Deep Learning: Development and External Validation
  237. Explainable Computer Vision Framework for Automated Pore Detection and Criticality Assessment in Additive Manufacturing
  238. PriorProbe: Recovering Individual-Level Priors for Personalizing Neural Networks in Facial Expression Recognition
  239. EventNeuS: 3D Mesh Reconstruction from a Single Event Camera
  240. PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
  241. Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
  242. Investigating Quantum Circuit Designs Using Neuro-Evolution
  243. Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL
  244. PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization
  245. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
  246. AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
  247. Continuous Control of Editing Models via Adaptive-Origin Guidance
  248. The Geometry of Learning to Avoid Interventions
  249. Quantifying Avian Morphological Evolution through Deep Representation Learning
  250. Preference-based Conditional Treatment Effects and Policy Learning
  251. They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References
  252. Adaptive Evidence Weighting for Audio-Spatiotemporal Fusion
  253. Antidistillation Fingerprinting
  254. Progressive Checkerboards for Autoregressive Multiscale Image Generation
  255. Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network
  256. Prediction of Critical Heat Flux in Rod Bundles Using Tube-Based Hybrid Machine Learning Models in CTF
  257. Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
  258. Conformal Reachability for Safe Control in Unknown Environments
  259. Manifold Random Features
  260. 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
  261. Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation
  262. Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants
  263. From Pre- to Intra-operative MRI: Predicting Brain Shift in Temporal Lobe Resection for Epilepsy Surgery
  264. Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
  265. UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining
  266. Decision-oriented benchmarking to transform AI weather forecast access: Application to the Indian monsoon
  267. FOVI: A biologically-inspired foveated interface for deep vision models
  268. RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images
  269. See-through: Single-image Layer Decomposition for Anime Characters
  270. Soft Sensor for Bottom-Hole Pressure Estimation in Petroleum Wells Using Long Short-Term Memory and Transfer Learning
  271. Fast-MWEM: Private Data Release in Sublinear Time
  272. Efficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators
  273. Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
  274. VR-VFL: Joint Rate and Client Selection for Vehicular Federated Learning Under Imperfect CSI
  275. No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
  276. Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging
  277. Data-Driven Graph Filters via Adaptive Spectral Shaping
  278. Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
  279. LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization
  280. QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
  281. Universal One-third Time Scaling in Learning Peaked Distributions
  282. Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
  283. Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
  284. ContraLog: Log File Anomaly Detection with Contrastive Learning and Masked Language Modeling
  285. Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
  286. Referring Industrial Anomaly Segmentation
  287. Equilibrium Propagation for Non-Conservative Systems
  288. Efficient Sequential Neural Network with Spatial-Temporal Attention and Linear LSTM for Robust Lane Detection Using Multi-Frame Images
  289. Sequential Group Composition: A Window into the Mechanics of Deep Learning
  290. Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
  291. CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets
  292. TRE: Encouraging Exploration in the Trust Region
  293. SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection
  294. BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish
  295. Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
  296. Multi-Objective Optimization for Synthetic-to-Real Style Transfer
  297. Quasi-multimodal-based pathophysiological feature learning for retinal disease diagnosis
  298. Quantization-Aware Regularizers for Deep Neural Networks Compression
  299. Simulation-Based Inference via Regression Projection and Batched Discrepancies
  300. Generator-based Graph Generation via Heat Diffusion
  301. Controlling Output Rankings in Generative Engines for LLM-based Search
  302. SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network
  303. TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
  304. High-Resolution Underwater Camouflaged Object Detection: GBU-UCOD Dataset and Topology-Aware and Frequency-Decoupled Networks
  305. SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
  306. Efficient Algorithms for Partial Constraint Satisfaction Problems over Control-flow Graphs
  307. APEX: Probing Neural Networks via Activation Perturbation
  308. V0: A Generalist Value Model for Any Policy at State Zero
  309. Optimization and Generation in Aerodynamics Inverse Design
  310. Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization
  311. Riemannian Neural Optimal Transport
  312. ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning
  313. NPCNet: Navigator-Driven Pseudo Text for Deep Clustering of Early Sepsis Phenotyping
  314. ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images
  315. Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets
  316. Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models
  317. How to Train Your Resistive Network: Generalized Equilibrium Propagation and Analytical Learning
  318. Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts
  319. Can Large Language Models Generalize Procedures Across Representations?
  320. Group Selection as a Safeguard Against AI Substitution
  321. Constrained Dynamic Gaussian Splatting
  322. MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models
  323. Sparse Training of Neural Networks based on Multilevel Mirror Descent
  324. Robust Representation Learning in Masked Autoencoders
  325. Interpretable Logical Anomaly Classification via Constraint Decomposition and Instruction Fine-Tuning
  326. Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model
  327. WARP Logic Neural Networks
  328. Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms
  329. Rank-Learner: Orthogonal Ranking of Treatment Effects
  330. Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation
  331. A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
  332. CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains
  333. Generative Decompression: Optimal Lossy Decoding Against Distribution Mismatch
  334. Lookahead Path Likelihood Optimization for Diffusion LLMs
  335. Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs
  336. DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications
  337. Preferences for Idiomatic Language are Acquired Slowly -- and Forgotten Quickly: A Case Study on Swedish
  338. When Routing Collapses: On the Degenerate Convergence of LLM Routers
  339. Inlier-Centric Post-Training Quantization for Object Detection Models
  340. The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding
  341. Quantum Circuit Generation via test-time learning with large language models
  342. Soft-Radial Projection for Constrained End-to-End Learning
  343. Causal Inference on Networks under Misspecified Exposure Mappings: A Partial Identification Framework
  344. HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic
  345. Acceleration of Atomistic NEGF: Algorithms, Parallelization, and Machine Learning
  346. DiscoverLLM: From Executing Intents to Discovering Them
  347. Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection
  348. FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
  349. Most Convolutional Networks Suffer from Small Adversarial Perturbations
  350. Feasible strategies for conflict resolution within intuitionistic fuzzy preference-based conflict situations
  351. Precision in Practice: Knowledge Guided Code Summarizing Grounded in Industrial Expectations
  352. Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective
  353. The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting
  354. Improving the Linearized Laplace Approximation via Quadratic Approximations
  355. On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
  356. From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
  357. Toward a Sustainable Federated Learning Ecosystem: A Practical Least Core Mechanism for Payoff Allocation
  358. Dynamic Topology Optimization for Non-IID Data in Decentralized Learning
  359. PlanTRansformer: Unified Prediction and Planning with Goal-conditioned Transformer
  360. Unifying Watermarking via Dimension-Aware Mapping
  361. Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion
  362. Z3D: Zero-Shot 3D Visual Grounding from Images
  363. MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
  364. GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
  365. Achieving Linear Speedup for Composite Federated Learning
  366. PACE: Pretrained Audio Continual Learning
  367. Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship
  368. Building Interpretable Models for Moral Decision-Making
  369. Robustness as an Emergent Property of Task Performance
  370. Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability
  371. PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
  372. Bayesian Conformal Prediction as a Decision Risk Problem
  373. From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
  374. Pi-GS: Sparse-View Gaussian Splatting with Dense π3 Initialization
  375. A Novel approach to portfolio construction
  376. Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design
  377. Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)
  378. Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
  379. PQTNet: Pixel-wise Quantitative Thermography Neural Network for Estimating Defect Depth in Polylactic Acid Parts by Additive Manufacturing
  380. Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
  381. Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
  382. Full end-to-end diagnostic workflow automation of 3D OCT via foundation model-driven AI for retinal diseases
  383. Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach
  384. LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices
  385. Anomaly Detection via Mean Shift Density Enhancement
  386. A3-TTA: Adaptive Anchor Alignment Test-Time Adaptation for Image Segmentation
  387. Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities
  388. Rejecting Arguments Based on Doubt in Structured Bipolar Argumentation
  389. MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings
  390. Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
  391. Orthogonal Approximate Message Passing Algorithms for Rectangular Spiked Matrix Models with Rotationally Invariant Noise
  392. Global Geometry Is Not Enough for Vision Representations
  393. BlockRR: A Unified Framework of RR-type Algorithms for Label Differential Privacy
  394. Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework
  395. HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis
  396. Principled Federated Random Forests for Heterogeneous Data
  397. GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
  398. LaVPR: Benchmarking Language and Vision for Place Recognition
  399. Mi'ci Princ -- A Little Boy Teaching Speech Technologies the Chakavian Dialect
  400. Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
  401. BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
  402. Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
  403. ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
  404. Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
  405. Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks
  406. Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
  407. Latent Neural-ODE for Model-Informed Precision Dosing: Overcoming Structural Assumptions in Pharmacokinetics
  408. WebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU
  409. Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures
  410. Hand3R: Online 4D Hand-Scene Reconstruction in the Wild
  411. From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization
  412. Reinforcement Learning with Promising Tokens for Large Language Models
  413. Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
  414. BinaryDemoire: Moir'e-Aware Binarization for Image Demoir'eing
  415. Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedback
  416. Adversarial construction as a potential solution to the experiment design problem in large task spaces
  417. NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data
  418. Online Conformal Prediction via Universal Portfolio Algorithms
  419. Entropic Mirror Monte Carlo
  420. Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval
  421. Fully Kolmogorov-Arnold Deep Model in Medical Image Segmentation
  422. Intelligent Front-End Personalization: AI-Driven UI Adaptation
  423. What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations
  424. Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
  425. SATORIS-N: Spectral Analysis based Traffic Observation Recovery via Informed Subspaces and Nuclear-norm minimization
  426. FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
  427. Enhanced Parcel Arrival Forecasting for Logistic Hubs: An Ensemble Deep Learning Approach
  428. Contrastive Concept-Tree Search for LLM-Assisted Algorithm Discovery
  429. Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks
  430. Beyond Cropping and Rotation: Automated Evolution of Powerful Task-Specific Augmentations with Generative Models
  431. Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost
  432. Digital Lifelong Learning in the Age of AI: Trends and Insights
  433. One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
  434. ChemPro: A Progressive Chemistry Benchmark for Large Language Models
  435. The Mask of Civility: Benchmarking Chinese Mock Politeness Comprehension in Large Language Models
  436. "I'm happy even though it's not real": GenAI Photo Editing as a Remembering Experience
  437. Task--Specificity Score: Measuring How Much Instructions Really Matter for Supervision
  438. TextME: Bridging Unseen Modalities Through Text Descriptions
  439. PRISM: Structured Optimization via Anisotropic Spectral Shaping
  440. Geometry-Preserving Neural Architectures on Manifolds with Boundary
  441. A generalizable large-scale foundation model for musculoskeletal radiographs
  442. ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
  443. Finding Optimal Video Moment without Training: Gaussian Boundary Optimization for Weakly Supervised Video Grounding
  444. FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
  445. Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
  446. JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Robotics
  447. From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality
  448. Stationarity and Spectral Characterization of Random Signals on Simplicial Complexes
  449. Towards Considerate Embodied AI: Co-Designing Situated Multi-Site Healthcare Robots from Abstract Concepts to High-Fidelity Prototypes
  450. Fedcompass: Federated Clustered and Periodic Aggregation Framework for Hybrid Classical-Quantum Models
  451. Unified Inference Framework for Single and Multi-Player Performative Prediction: Method and Asymptotic Optimality
  452. HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency
  453. Generalizable and Interpretable RF Fingerprinting with Shapelet-Enhanced Large Language Models
  454. KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
  455. Physics-inspired transformer quantum states via latent imaginary-time evolution
  456. MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration
  457. Consistency Deep Equilibrium Models
  458. Rethinking Music Captioning with Music Metadata LLMs
  459. FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models
  460. From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
  461. A Vision-Based Analysis of Congestion Pricing in New York City
  462. Thinking inside the Convolution for Image Inpainting: Reconstructing Texture via Structure under Global and Local Side
  463. VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering
  464. Graph Autoencoder for Process Monitoring
  465. Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
  466. Large Language Models Can Take False First Steps at Inference-time Planning
  467. SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation
  468. NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
  469. WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection
  470. SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences
  471. Fisheye Stereo Vision: Depth and Range Error
  472. Co2PO: Coordinated Constrained Policy Optimization for Multi-Agent RL
  473. Dynamic High-frequency Convolution for Infrared Small Target Detection
  474. TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation
  475. Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
  476. Human-Centric Traffic Signal Control for Equity: A Multi-Agent Action Branching Deep Reinforcement Learning Approach
  477. Synthetic Data Augmentation for Medical Audio Classification: A Preliminary Evaluation
  478. UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers
  479. Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification
  480. SRA-Seg: Synthetic to Real Alignment for Semi-Supervised Medical Image Segmentation
  481. A vector logic for intensional formal semantics
  482. Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness
  483. Weighted Sum-of-Trees Model for Clustered Data
  484. Rare Event Early Detection: A Dataset of Sepsis Onset for Critically Ill Trauma Patients
  485. RPG-AE: Neuro-Symbolic Graph Autoencoders with Rare Pattern Mining for Provenance-Based Anomaly Detection