mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 29 Sep 2025

692 papers

  1. Advancing mathematics research with generative AILLM reasoning → Mathematical reasoning
  2. Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security AuditsLLM reasoning → Reasoning for agents, planning and code
  3. From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts RoutingMixture-of-experts → Efficient MoE training and inference systems
  4. Why mask diffusion does not workDiffusion models → Discrete and text diffusion
  5. A-MemGuard: A Proactive Defense Framework for LLM-Based Agent MemoryLLM agents and tool use → Agent threats, guardrails and governance
  6. AutoContext: Instance-Level Context Learning for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. Think Twice, Generate Once: Safeguarding by Progressive Self-ReflectionLLM reasoning → Test-time compute and efficient thinking +1
  8. Safe Reinforcement Learning-Based Vibration Control: Overcoming Training Risks with LQR GuidanceDeep reinforcement learning methods → Safe and constrained RL
  9. Unlocking Zero-Shot Geospatial Reasoning via Indirect RewardsLLM reasoning → Spatial and embodied reasoning +1
  10. ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language ModelsLLM reasoning → Test-time compute and efficient thinking
  11. OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  12. AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in AstronomyMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  13. Less is More: Lean yet Powerful Vision-Language Model for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  14. RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free GuidanceLLM reasoning → Diffusion reasoning and test-time scaling +1
  15. MoReFlow: Motion Retargeting Learning through Unsupervised Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  16. Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic TasksLLM agents and tool use → Reinforcement learning for LLM agents +1
  17. Binary Sparse Coding for InterpretabilityMechanistic interpretability → Sparse autoencoder training and evaluation
  18. K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation ModelMixture-of-experts → Medical and biomedical MoE
  19. Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM AgentLLM agents and tool use → Medical and scientific domain agents
  20. Machine Learning Algorithms for Improving Black Box Optimization SolversDeep reinforcement learning methods → RL for games and combinatorial optimization
  21. ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  23. Safe In-Context Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  24. Probing the Limits of Stylistic Alignment in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  25. FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biologyMultimodal LLMs / vision-language models → Agricultural vision-language models
  26. IRIS: Intrinsic Reward Image SynthesisLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  27. Radiology's Last Exam (RadLE): Benchmarking Frontier Multimodal AI Against Human Experts and a Taxonomy of Visual Reasoning Errors in RadiologyLLM reasoning → Clinical and biomedical applications +1
  28. Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed ApproachesLLM safety and security → Federated unlearning and poisoning
  29. Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert ModelLLM reasoning → Reasoning benchmarks and evaluation
  30. Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-PlayMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  31. VISOR++: Universal Visual Inputs based Steering for Large Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  32. Calibrating Verbalized Confidence with Self-Generated DistractorsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  33. MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text SourcesLLM reasoning → Reasoning benchmarks and evaluation
  34. Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  35. Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  36. Flow Matching with Semidiscrete CouplingsDiffusion models → Flow matching, time series and science
  37. World Model for AI Autonomous Navigation in Mechanical ThrombectomyWorld models → Medical and surgical world models +1
  38. EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal CircuitLLM agents and tool use → Software engineering coding agents
  39. Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference OptimizationLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
  40. Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image DetectionLLM reasoning → Multimodal reasoning +1
  41. Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based ProvocationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. TDHook: A Lightweight Framework for InterpretabilityDeep reinforcement learning methods → Interpretable and logic-guided RL
  43. SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QARetrieval-augmented generation → RAG robustness and adaptive retrieval
  44. PIPer: On-Device Environment Setup via Online Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  45. DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree SearchLLM reasoning → Reinforcement learning for reasoning
  46. Fingerprinting LLMs via Prompt InjectionLLM safety and security → Watermarking generated content and models
  47. CoTaP: Compliant Task Pipeline and Reinforcement Learning of Its Controller with Compliance ModulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  48. Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress MonitoringDeep reinforcement learning methods → Deep RL algorithms and representations
  49. RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMsLLM reasoning → Test-time compute and efficient thinking
  50. Polychromic Objectives for Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  51. Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase SearchLLM reasoning → Test-time compute and efficient thinking +1
  52. Emotion-Aligned Generation in Diffusion Text to Speech Models via Preference-Guided OptimizationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  53. Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAsLLM reasoning → Test-time compute and efficient thinking
  54. DepthLM: Metric Depth From Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  55. Boolean Satisfiability via Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  56. From Faithfulness to Correctness: Generative Reward Models that Think CriticallyLLM reasoning → Reinforcement learning for reasoning +1
  57. Parallel Heuristic Search as Inference for Actor-Critic Reinforcement Learning ModelsDeep reinforcement learning methods → RL theory and sample complexity
  58. FlashOmni: A Unified Sparse Attention Engine for Diffusion TransformersDiffusion models → Video generation
  59. SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMsLLM reasoning → Spatial and embodied reasoning +1
  60. Let Physics Guide Your Protein Flows: Topology-aware Unfolding and GenerationDiffusion models → Flow matching, time series and science
  61. From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  62. Where LLM Agents Fail and How They can Learn From FailuresLLM agents and tool use → Software engineering coding agents
  63. Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  64. SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation PredictionLLM reasoning → Clinical and biomedical applications
  65. LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion ModelDiffusion models → Video generation
  66. Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  67. Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel ExecutionLLM agents and tool use → Web, search, and research agents
  68. Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  69. ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative AgentsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  70. Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven DevelopmentLLM agents and tool use → Software engineering coding agents
  71. A Measurement Study of Model Context Protocol EcosystemLLM agents and tool use → Agent threats, guardrails and governance
  72. Optimisation of Resource Allocation in Heterogeneous Wireless Networks Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  73. Toward Causal-Visual Programming: Enhancing Agentic Reasoning in Low-Code EnvironmentsLLM reasoning → Causal reasoning in LLMs +1
  74. MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time SeriesMixture-of-experts → MoE for time series and graphs
  75. Visual Jigsaw Post-Training Improves MLLMsLLM reasoning → Multimodal reasoning +1
  76. InfoAgent: Advancing Autonomous Information-Seeking AgentsLLM agents and tool use → Web, search, and research agents
  77. Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel DecodingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  78. PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured ImagesLLM reasoning → Multimodal reasoning +2
  79. DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent SpaceDiffusion models → Diffusion foundations and sampling
  80. GHOST: Hallucination-Inducing Image Generation for Multimodal LLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  81. Mitigating Hallucination in Multimodal LLMs with Layer Contrastive DecodingLLM reasoning → Hallucination detection and mitigation +1
  82. SIRI: Scaling Iterative Reinforcement Learning with Interleaved CompressionLLM reasoning → Test-time compute and efficient thinking +1
  83. XQC: Well-conditioned Optimization Accelerates Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  84. TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete DiffusionDiffusion models → Diffusion and flow policies for robotics +1
  85. GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion ModelsDiffusion models → Flow matching, time series and science
  86. AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  87. Rolling Forcing: Autoregressive Long Video Diffusion in Real TimeWorld models → Video-generation world models and simulators +1
  88. GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual ContextsLLM reasoning → Multimodal reasoning +1
  89. Chance-constrained Flow Matching for High-Fidelity Constraint-aware GenerationDiffusion models → Flow matching, time series and science
  90. VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  91. AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  92. Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text GenerationKnowledge distillation → Knowledge distillation for LLMs
  93. TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  94. Visual serial processing deficits explain divergences in human and VLM reasoningLLM reasoning → Multimodal reasoning +1
  95. ReasoningBank: Scaling Agent Self-Evolving with Reasoning MemoryLLM reasoning → Reasoning for agents, planning and code +2
  96. Rethinking Entropy Regularization in Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  97. Score Distillation of Flow Matching ModelsDiffusion models → Diffusion foundations and sampling
  98. Towards Personalized Deep Research: Benchmarks and EvaluationsLLM agents and tool use → Web, search, and research agents
  99. ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM DistillationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  100. Curriculum Imitation Learning of Distributed Multi-Robot PoliciesOffline RL and imitation learning from data → Imitation learning methods
All 692
  1. Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMsKnowledge distillation → Knowledge distillation for LLMs
  2. Scaling Generalist Data-Analytic AgentsLLM agents and tool use → Web, search, and research agents
  3. MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
  4. UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D GenerationDiffusion models → 3D, point cloud and scene generation
  5. CharGen: Fast and Fluent Portrait ModificationDiffusion models → Image generation, text-to-image and editing
  6. Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and PlanningLLM reasoning → Reasoning for agents, planning and code +1
  7. Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion ModelsDiffusion models → Discrete and text diffusion
  8. Scaling Synthetic Task Generation for Agents via ExplorationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  9. Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic ArchitecturesMechanistic interpretability → Knowledge and representations inside LLMs
  10. GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  11. Ultra-Fast Language Generation via Discrete Diffusion Divergence InstructDiffusion models → Discrete and text diffusion
  12. STAGE: Stable and Generalizable GRPO for Autoregressive Image GenerationLLM reasoning → Reinforcement learning for reasoning
  13. GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing ReasoningLLM reasoning → Spatial and embodied reasoning
  14. Deep Thinking by Markov Chain of Continuous ThoughtsLLM reasoning → Prompting and chain-of-thought reasoning
  15. CLPO: Curriculum Learning meets Policy Optimization for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  16. Score-based Membership Inference on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  17. PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video DiffusionDiffusion models → 3D, point cloud and scene generation
  18. Path Diffuser: Diffusion Model for Data-Driven Traffic SimulatorDiffusion models → Diffusion and flow policies for robotics
  19. Sampling Complexity of TD and PPO in RKHSDeep reinforcement learning methods → RL theory and sample complexity
  20. Random Policy Valuation is Enough for LLM Reasoning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  21. SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose EstimationDiffusion models → 3D, point cloud and scene generation
  22. Agentic Exploration of Physics ModelsLLM agents and tool use → Web, search, and research agents
  23. Double Descent as a Lens for Sample Efficiency in Autoregressive vs. Discrete Diffusion ModelsDiffusion models → Discrete and text diffusion
  24. Annotation-Free One-Shot Imitation Learning for Multi-Step Manipulation TasksOffline RL and imitation learning from data → Robot manipulation imitation learning
  25. SecInfer: Preventing Prompt Injection via Inference-time ScalingLLM reasoning → Reasoning for agents, planning and code +1
  26. The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry CapabilityLLM agents and tool use → Medical and scientific domain agents
  27. Intra-request branch orchestration for efficient LLM reasoningLLM reasoning → Test-time compute and efficient thinking
  28. MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  29. World-Env: Leveraging World Model as a Virtual Environment for VLA Post-TrainingWorld models → Embodied and robot world models +2
  30. Learning Distinguishable Representations in Deep Q-Networks for Linear TransferDeep reinforcement learning methods → Deep RL algorithms and representations
  31. MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training RecipesLLM reasoning → Reasoning benchmarks and evaluation
  32. Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive AgentsLLM agents and tool use → Multimodal and embodied agents
  33. OAT-FM: Optimal Acceleration Transport for Improved Flow MatchingDiffusion models → Flow matching, time series and science
  34. MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  35. From Code to Action: Hierarchical Learning of Diffusion-VLM PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  36. When Scores Learn Geometry: Rate Separations under the Manifold HypothesisDiffusion models → Diffusion foundations and sampling
  37. Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion TransformerDiffusion models → Video generation
  38. JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  39. VAGUEGAN: Stealthy Poisoning and Backdoor Attacks on Image Generative PipelinesDiffusion models → Robustness, privacy and adversarial aspects +1
  40. MMRQA: Signal-Enhanced Multimodal Large Language Models for MRI Quality AssessmentMultimodal LLMs / vision-language models → Medical vision-language models
  41. Expanding Computation Spaces of LLMs at Inference TimeLLM reasoning → Test-time compute and efficient thinking
  42. Environment-Aware Satellite Image Generation with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  43. StreamForest: Efficient Online Video Understanding with Persistent Event MemoryMultimodal LLMs / vision-language models → Video understanding with MLLMs
  44. Retro*: Optimizing LLMs for Reasoning-Intensive Document RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning +1
  45. PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent SystemLLM agents and tool use → Web, search, and research agents
  46. ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language ModelsLLM reasoning → Multimodal reasoning +2
  47. Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density EstimationLLM reasoning → Reasoning benchmarks and evaluation
  48. SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH MatchingEfficient LLM inference and serving → KV cache optimization
  49. AIPOM: Agent-aware Interactive Planning for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  50. DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation FrameworkKnowledge distillation → Knowledge distillation for LLMs
  51. Intelligent Optimization of Wireless Access Point Deployment for Communication-Based Train Control Systems Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  52. KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  53. Query Circuits: Explaining How Language Models Answer User PromptsMechanistic interpretability → Circuits and mechanistic analysis
  54. DyMoDreamer: World Modeling with Dynamic ModulationWorld models → Latent dynamics models and model-based RL +1
  55. Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual GenerationDiffusion models → Image generation, text-to-image and editing
  56. Sparse Autoencoders Make Audio Foundation Models more ExplainableMechanistic interpretability → SAE features and their applications
  57. Vision Function Layer in Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  58. LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step ReasoningLLM reasoning → Multimodal reasoning
  59. Quantifying Generalisation in Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  60. SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  61. VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual GroundingLLM reasoning → Multimodal reasoning +1
  62. VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint LearningDiffusion models → Audio, speech and music
  63. LatentEvolve: Self-Evolving Test-Time Scaling in Latent SpaceLLM reasoning → Test-time compute and efficient thinking +1
  64. IA-VLA: Input Augmentation for Vision-Language-Action models in settings with semantically complex tasksVision-language-action models → Generalist VLA models and benchmarks
  65. Semantic-Aware Logical Reasoning via a Semiotic FrameworkLLM reasoning → Reasoning benchmarks and evaluation
  66. ExGS: Extreme 3D Gaussian Compression with Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  67. Robust Policy Expansion for Offline-to-Online RL under Diverse Data CorruptionOffline RL and imitation learning from data → Offline RL algorithms
  68. Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  69. Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolutionLLM reasoning → Reasoning for agents, planning and code +2
  70. Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  71. Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  72. MAD: Manifold Attracted DiffusionDiffusion models → Diffusion foundations and sampling
  73. SenSE: Semantic-Aware High-Fidelity Universal Speech EnhancementDiffusion models → Audio, speech and music
  74. MemGen: Weaving Generative Latent Memory for Self-Evolving AgentsLLM agents and tool use → Agent memory systems +1
  75. Enhancing Physical Plausibility in Video Generation by Reasoning the ImplausibilityDiffusion models → Video generation
  76. LISA Technical Report: An Agentic Framework for Smart Contract AuditingLLM agents and tool use → Agent threats, guardrails and governance
  77. Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed SteeringOffline RL and imitation learning from data → Real-world robot offline RL
  78. T-POP: Test-Time Personalization with Online Preference FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  79. SANA-Video: Efficient Video Generation with Block Linear Diffusion TransformerDiffusion models → Video generation +1
  80. Understanding the Dilemma of Unlearning for Large Language ModelsLLM safety and security → Machine unlearning
  81. Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity BridgeLLM reasoning → Knowledge- and tool-augmented reasoning
  82. Learning Object-Centric Representations Based on Slots in Real World ScenariosDiffusion models → Image generation, text-to-image and editing
  83. RIFLE: Removal of Image Flicker-Banding via Latent Diffusion EnhancementDiffusion models → Inverse problems and image restoration
  84. Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMsLLM reasoning → Multimodal reasoning
  85. SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM ServingEfficient LLM inference and serving → KV cache optimization
  86. PRIVMARK: Private Large Language Models Watermarking with MPCLLM safety and security → Watermarking generated content and models
  87. FreeRet: MLLMs as Training-Free RetrieversMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  88. OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  89. Inducing Dyslexia in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  90. PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action ControlDiffusion models → Diffusion and flow policies for robotics
  91. SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse ProblemsDiffusion models → Inverse problems and image restoration
  92. U-DiT Policy: U-shaped Diffusion Transformers for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  93. TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  94. AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty QuantificationLLM reasoning → Clinical and biomedical applications
  95. Emergent World Representations in OpenVLAWorld models → Embodied and robot world models +3
  96. Deep Reinforcement Learning in Action: Real-Time Control of Vortex-Induced VibrationsDeep reinforcement learning methods → RL with diffusion and flow models
  97. Unlocking the Potential of Soft Actor-Critic for Imitation LearningOffline RL and imitation learning from data → Imitation learning methods +1
  98. Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative AnalysisDiffusion models → Flow matching, time series and science
  99. Training Agents Inside of Scalable World ModelsWorld models → Latent dynamics models and model-based RL
  100. CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map ModelsDiffusion models → Flow matching, time series and science
  101. PhysiAgent: An Embodied Agent Framework in Physical WorldVision-language-action models → Generalist VLA models and benchmarks +1
  102. Agentic Specification Generator for Move ProgramsLLM agents and tool use → Software engineering coding agents
  103. Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPOLLM reasoning → Reinforcement learning for reasoning
  104. Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  105. Sanitize Your Responses: Mitigating Privacy Leakage in Large Language ModelsLLM safety and security → Prompt injection and agent security
  106. One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual LearningMixture-of-experts → Mixture of LoRA experts
  107. Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate TasksLLM reasoning → Spatial and embodied reasoning +1
  108. LaMoGen: Laban Movement-Guided Diffusion for Text-to-Motion GenerationDiffusion models → Video generation
  109. ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time ScalingLLM reasoning → Reinforcement learning for reasoning +1
  110. Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student NetworksKnowledge distillation → Detection and dense prediction distillation
  111. UI2V-Bench: An Understanding-based Image-to-video Generation BenchmarkDiffusion models → Video generation
  112. CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  113. FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving SystemsEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
  114. Muon: Training and Trade-offs with Latent Attention and MoEMixture-of-experts → Efficient MoE training and inference systems
  115. Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language AgentsLLM agents and tool use → Web, search, and research agents
  116. Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time ScalingLLM reasoning → Knowledge- and tool-augmented reasoning
  117. Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding GuidanceDiffusion models → Audio, speech and music
  118. Towards Safe Reasoning in Large Reasoning Models via Corrective InterventionLLM reasoning → Reasoning for agents, planning and code +1
  119. UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-ModalitiesDiffusion models → Audio, speech and music
  120. LLaDA-MoE: A Sparse MoE Diffusion Language ModelDiffusion models → Discrete and text diffusion +1
  121. Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning SynergyLLM reasoning → Spatial and embodied reasoning +1
  122. HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness AssessmentLLM safety and security → Safety alignment, refusal and guardrails
  123. Agentic Services ComputingLLM agents and tool use → General LLM agent frameworks and benchmarks
  124. Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMsLLM reasoning → Mathematical reasoning +1
  125. Reinforcement Mid-TrainingLLM reasoning → Reinforcement learning for reasoning
  126. From Satellite to Street: A Hybrid Framework Integrating Stable Diffusion and PanoGAN for Consistent Cross-View SynthesisDiffusion models → Diffusion and flow policies for robotics
  127. Watermarking Diffusion Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  128. UI-UG: A Unified MLLM for UI Understanding and GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  129. NeRV-Diffusion: Diffuse Implicit Neural Representations for Video SynthesisDiffusion models → Video generation
  130. From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process SupervisionLLM reasoning → Reinforcement learning for reasoning +1
  131. Hyperspherical Latents Improve Continuous-Token Autoregressive GenerationDiffusion models → Image generation, text-to-image and editing
  132. Wavelet-Assisted Mamba for Satellite-Derived Sea Surface Temperature Super-ResolutionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  133. Speculative Verification: Exploiting Information Gain to Refine Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  134. MAS2: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  135. Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A SurveyLLM reasoning → Audio-language model reasoning +1
  136. SONAR: Semantic-Object Navigation with Aggregated Reasoning through a Cross-Modal Inference ParadigmLLM reasoning → Spatial and embodied reasoning +1
  137. Similarity-Aware Selective State-Space Modeling for Semantic CorrespondenceState-space sequence models (S4, Mamba) → Vision Mamba backbones
  138. MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical ReasoningLLM reasoning → Clinical and biomedical applications +2
  139. Learning to Sample: Reinforcement Learning-Guided Sampling for Autonomous Vehicle Motion PlanningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  140. Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  141. FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame SpotlightingLLM reasoning → Multimodal reasoning +1
  142. SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG GenerationLLM reasoning → Multimodal reasoning
  143. Q-Mirror: Unlocking the Multi-Modal Potential of Scientific Text-Only QA PairsLLM reasoning → Knowledge- and tool-augmented reasoning
  144. DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language ModelsLLM safety and security → Jailbreaking
  145. ASIA: Adaptive 3D Segmentation using Few Image AnnotationsDiffusion models → 3D, point cloud and scene generation
  146. SCI-Verifier: Scientific Verifier with ThinkingLLM reasoning → Knowledge- and tool-augmented reasoning
  147. SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  148. G-reasoner: Foundation Models for Unified Reasoning over Graph-structured KnowledgeLLM reasoning → Knowledge- and tool-augmented reasoning
  149. Adversarial Reinforcement Learning Framework for ESP Cheater SimulationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  150. AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +2
  151. Cycle Diffusion Model for Counterfactual Image GenerationDiffusion models → Medical imaging and segmentation
  152. PAME-AI: Patient Messaging Creation and Optimization using Agentic AILLM agents and tool use → Medical and scientific domain agents
  153. Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  154. Rethinking and Benchmarking Large Language Models for Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  155. When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  156. MRAG-Suite: A Diagnostic Evaluation Platform for Visual Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  157. Latent Visual ReasoningLLM reasoning → Multimodal reasoning +1
  158. SpecExit: Accelerating Large Reasoning Model via Speculative ExitLLM reasoning → Test-time compute and efficient thinking +1
  159. SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier FunctionsDiffusion models → Diffusion and flow policies for robotics
  160. FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video GenerationWorld models → Embodied and robot world models
  161. Takedown: How It's Done in Modern Coding Agent ExploitsLLM agents and tool use → Agent threats, guardrails and governance
  162. ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  163. Learning to Ponder: Adaptive Reasoning in Latent SpaceLLM reasoning → Test-time compute and efficient thinking +1
  164. EVLF-FM: Explainable Vision Language Foundation Model for MedicineLLM reasoning → Clinical and biomedical applications +1
  165. ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  166. ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  167. MDD-Thinker: Towards Large Reasoning Models for Major Depressive Disorder DiagnosisLLM reasoning → Clinical and biomedical applications
  168. ScenarioBench: Trace-Grounded Compliance Evaluation for Text-to-SQL and RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  169. BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  170. Humanline: Online Alignment as Perceptual LossLLM reasoning → Reinforcement learning for reasoning +1
  171. Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its FriendsLLM reasoning → Reinforcement learning for reasoning
  172. An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI GenerationDiffusion models → Medical imaging and segmentation
  173. AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-PlayLLM reasoning → Knowledge- and tool-augmented reasoning +1
  174. Talk in Pieces, See in Whole: Disentangled and Hierarchical Representation Learning in Language-based Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  175. SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM InferenceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  176. Retrieval-augmented GUI Agents with Generative GuidelinesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  177. Model Correlation Detection via Random Selection ProbingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  178. Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation ModelsLLM safety and security → Machine unlearning
  179. Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  180. RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  181. Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  182. Your thoughts tell who you are: Characterize the reasoning patterns of LRMsLLM reasoning → Test-time compute and efficient thinking
  183. Asymmetric VAE for One-Step Video Super-Resolution AccelerationDiffusion models → Inverse problems and image restoration
  184. Predicting Oscar-Nominated Screenplays with Sentence Embeddings
  185. A Biophysical-Model-Informed Source Separation Framework For EMG Decomposition
  186. Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding
  187. AutoCode: LLMs as Problem Setters for Competitive Programming
  188. Responsible AI Adoption in the Public Sector: A Data-Centric Taxonomy of AI Adoption Challenges
  189. Towards Structured Knowledge: Advancing Triple Extraction from Regional Trade Agreements using Large Language Models
  190. A Fuzzy Logic-Based Framework for Explainable Machine Learning in Big Data Analytics
  191. Hallucination is Inevitable for LLMs with the Open World Assumption
  192. CAFL-L: Constraint-Aware Federated Learning with Lagrangian Dual Optimization for On-Device Language Models
  193. Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanced Regimes
  194. Multimodal Arabic Captioning with Interpretable Visual Concept Integration
  195. Domain-Robust Marine Plastic Detection Using Vision Models
  196. Visualizing Celebrity Dynamics in Video Content: A Proposed Approach Using Face Recognition Timestamp Data
  197. UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
  198. Single-Core Superscalar Optimization of Clifford Neural Layers
  199. LogAction: Consistent Cross-system Anomaly Detection through Logs via Active Domain Adaptation
  200. SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics
  201. A Biologically Interpretable Cognitive Architecture for Online Structuring of Episodic Memories into Cognitive Maps
  202. Pretraining with hierarchical memories: separating long-tail and common knowledge
  203. A Hybrid CAPTCHA Combining Generative AI with Keystroke Dynamics for Enhanced Bot Detection
  204. Federated Spatiotemporal Graph Learning for Passive Attack Detection in Smart Grids
  205. How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
  206. Modeling Others' Minds as Code
  207. Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations
  208. AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
  209. Identifying All ε-Best Arms in (Misspecified) Linear Bandits
  210. Intelligent 5S Audit: Application of Artificial Intelligence for Continuous Improvement in the Automotive Industry
  211. FedLLM-Align: Feature Extraction From Heterogeneous Clients
  212. Efficient CNN Compression via Multi-method Low Rank Factorization and Feature Map Similarity
  213. Survey of AI-Powered Approaches for Osteoporosis Diagnosis in Medical Imaging
  214. FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation
  215. GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification
  216. Echoes of Humanity: Exploring the Perceived Humanness of AI Music
  217. Coupling Generative Modeling and an Autoencoder with the Causal Bridge
  218. Building the EHR Foundation Model via Next Event Prediction
  219. MetaChest: Generalized few-shot learning of pathologies from chest X-rays
  220. Conservative Decisions with Risk Scores
  221. AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
  222. Lightweight and Robust Federated Data Valuation
  223. A(I)nimism: Re-enchanting the World Through AI-Mediated Object Interaction
  224. Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer
  225. Unifying Agent Interaction and World Information for Multi-agent Coordination
  226. Hybrid Approach for Enhancing Lesion Segmentation in Fundus Images
  227. Don't Sweat the Small Stuff: Segment-Level Meta-Evaluation Based on Pairwise Difference Correlation
  228. Performance and competence intertwined: A computational model of the Null Subject stage in English-speaking children
  229. Online Mapping for Autonomous Driving: Addressing Sensor Generalization and Dynamic Map Updates in Campus Environments
  230. RadOnc-GPT: An Autonomous LLM Agent for Real-Time Patient Outcomes Labeling at Scale
  231. Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions
  232. Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization
  233. Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics
  234. Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
  235. Personalized Auto-Grading and Feedback System for Constructive Geometry Tasks Using Large Language Models on an Online Math Platform
  236. LLM-RG: Referential Grounding in Outdoor Scenarios using Large Language Models
  237. Economic Competition, EU Regulation, and Executive Orders: A Framework for Discussing AI Policy Implications in CS Courses
  238. Understanding Generative Recommendation with Semantic IDs from a Model-scaling View
  239. Robust Visual Localization in Compute-Constrained Environments by Salient Edge Rendering and Weighted Hamming Similarity
  240. Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels
  241. AGNOMIN -- Architecture Agnostic Multi-Label Function Name Prediction
  242. One-shot Conditional Sampling: MMD meets Nearest Neighbors
  243. XR Blocks: Accelerating Human-centered AI + XR Innovation
  244. DeepFake Detection in Dyadic Video Calls using Point of Gaze Tracking
  245. Not Wrong, But Untrue: LLM Overconfidence in Document-Based Queries
  246. EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition
  247. Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph
  248. Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
  249. Message passing-based inference in an autoregressive active inference agent
  250. Fair Classification by Direct Intervention on Operating Characteristics
  251. Translation from Wearable PPG to 12-Lead ECG
  252. Discontinuous Epitope Fragments as Sufficient Target Templates for Efficient Binder Design
  253. The Rise of AfricaNLP: A Survey of Contributions, Contributors, Community Impact, and Bibliometric Analysis
  254. Conformal Prediction for Signal Temporal Logic Inference
  255. Data-Efficient Multitask DAgger
  256. Plug-and-Play Emotion Graphs for Compositional Prompting in Zero-Shot Speech Emotion Recognition
  257. Infrastructure Sensor-enabled Vehicle Data Generation using Multi-Sensor Fusion for Proactive Safety Applications at Work Zone
  258. Multi-patch isogeometric neural solver for partial differential equations on computer-aided design domains
  259. Joint Embeddings Go Temporal
  260. Neural Optimal Transport Meets Multivariate Conformal Prediction
  261. Norm-Q: Effective Compression Method for Hidden Markov Models in Neuro-Symbolic Applications
  262. Bayesian Transformer for Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
  263. GESA: Graph-Enhanced Semantic Allocation for Generalized, Fair, and Explainable Candidate-Role Matching
  264. The Open Syndrome Definition
  265. Feedback Control for Small Budget Pacing
  266. Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults
  267. Multi-Task Equation Discovery
  268. A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
  269. Crowdsourcing Without People: Modelling Clustering Algorithms as Experts
  270. Multi-modal Spatio-Temporal Transformer for High-resolution Land Subsidence Prediction
  271. On the Shape of Latent Variables in a Denoising VAE-MoG: A Posterior Sampling-Based Study
  272. Deep Survival Analysis for Competing Risk Modeling with Functional Covariates and Missing Data Imputation
  273. Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs
  274. Cold-Start Active Correlation Clustering
  275. Saliency Guided Longitudinal Medical Visual Question Answering
  276. Generative Value Conflicts Reveal LLM Priorities
  277. Geometric Metrics and LLMs: What They Measure and When They Work
  278. Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region
  279. Editing Physiological Signals in Videos Using Latent Representations
  280. Spontaneous High-Order Generalization in Neural Theory-of-Mind Networks
  281. VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
  282. Uncertainty-Aware Generative Oversampling Using an Entropy-Guided Conditional Variational Autoencoder
  283. Aspects of holographic entanglement using physics-informed-neural-networks
  284. Learning Relationships Between Separate Audio Tracks for Creative Applications
  285. AI in Pakistani Schools: Adoption, Usage, and Perceived Impact among Educators
  286. ClustRecNet: A Novel End-to-End Deep Learning Framework for Clustering Algorithm Recommendation
  287. Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
  288. ActorDB: A Unified Database Model Integrating Single-Writer Actors, Incremental View Maintenance, and Zero-Trust Messaging
  289. Effectiveness of Large Language Models in Simulating Regional Psychological Structures: An Empirical Examination of Personality and Subjective Well-being
  290. Mechanisms of Matter: Language Inferential Benchmark on Physicochemical Hypothesis in Materials Synthesis
  291. Anatomy-DT: A Cross-Diffusion Digital Twin for Anatomical Evolution
  292. RL in the Wild: Characterizing RLVR Training in LLM Deployment
  293. VGGT-X: When VGGT Meets Dense Novel View Synthesis
  294. FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation
  295. Guided Diffusion for the Discovery of New Superconductors
  296. Incentive-Aligned Multi-Source LLM Summaries
  297. PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos
  298. DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
  299. NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation
  300. EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
  301. Personalized Vision via Visual In-Context Learning
  302. YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
  303. Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids
  304. Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units
  305. Who's Your Judge? On the Detectability of LLM-Generated Judgments
  306. High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
  307. Pretraining Large Language Models with NVFP4
  308. Fast Feature Field (F3): A Predictive Representation of Events
  309. Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs
  310. Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection
  311. The Era of Real-World Human Interaction: RL from User Conversations
  312. BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
  313. Learning in an Echo Chamber: Online Learning with Replay Adversary
  314. LayerD: Decomposing Raster Graphic Designs into Layers
  315. MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
  316. On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms
  317. From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
  318. Triangle Splatting+: Differentiable Rendering with Opaque Triangles
  319. AI Driven Discovery of Bio Ecological Mediation in Cascading Heatwave Risks
  320. Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?
  321. Towards generalizable deep ptychography neural networks
  322. Benchmarking ECG FMs: A Reality Check Across Clinical Tasks
  323. Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives
  324. Scaling with Collapse: Efficient and Predictable Training of LLM Families
  325. jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking
  326. Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI
  327. BRIDGE -- Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation
  328. GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction
  329. An empirical study on the limitation of Transformers in program trace generation
  330. Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
  331. Learning from Convenience Samples: A Case Study on Fine-Tuning LLMs for Survey Non-response in the German Longitudinal Election Study
  332. Symmetry-Aware Bayesian Optimization via Max Kernels
  333. Efficient Hyperparameter Tuning via Trajectory Invariance Principle
  334. Confidence-Guided Error Correction for Disordered Speech Recognition
  335. A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration
  336. Large Language Models for Software Testing: A Research Roadmap
  337. Fast Real-Time Pipeline for Robust Arm Gesture Recognition
  338. A multiscale analysis of mean-field transformers in the moderate interaction regime
  339. GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis
  340. VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
  341. AIRoA MoMa Dataset: A Large-Scale Hierarchical Dataset for Mobile Manipulation
  342. Bayesian Surrogates for Risk-Aware Pre-Assessment of Aging Bridge Portfolios
  343. Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting
  344. CLASP: Adaptive Spectral Clustering for Unsupervised Per-Image Segmentation
  345. Circuit Distillation
  346. LVT: Large-Scale Scene Reconstruction via Local View Transformers
  347. Embedded Deep Learning for Bio-hybrid Plant Sensors to Detect Increased Heat and Ozone Levels
  348. Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
  349. Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes
  350. Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
  351. DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern
  352. On-the-Fly Data Augmentation for Brain Tumor Segmentation
  353. Event-based Facial Keypoint Alignment via Cross-Modal Fusion Attention and Self-Supervised Multi-Event Representation Learning
  354. Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots
  355. Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
  356. SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
  357. Evaluating Temperature Scaling Calibration Effectiveness for CNNs under Varying Noise Levels in Brain Tumour Detection
  358. Scalable GANs with Transformers
  359. KIRETT -- A wearable device to support rescue operations using artificial intelligence to improve first aid
  360. Is Sequence Information All You Need for Bayesian Optimization of Antibodies?
  361. Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization
  362. How Well Do LLMs Imitate Human Writing Style?
  363. When Autonomous Vehicle Meets V2X Cooperative Perception: How Far Are We?
  364. When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
  365. A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
  366. Meta-Learning Theory-Informed Inductive Biases using Deep Kernel Gaussian Processes
  367. Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
  368. Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
  369. Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
  370. BOE-XSUM: Extreme Summarization in Clear Language of Spanish Legal Decrees and Notifications
  371. Neural network embeddings recover value dimensions from psychometric survey items on par with human data
  372. DRCP: Diffusion on Reinforced Cooperative Perception for Perceiving Beyond Limits
  373. Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
  374. OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
  375. Accurate Cobb Angle Estimation via SVD-Based Curve Detection and Vertebral Wedging Quantification
  376. RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
  377. DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation
  378. Towards Understanding the Shape of Representations in Protein Language Models
  379. Improved Stochastic Optimization of LogSumExp
  380. HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping
  381. Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
  382. Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
  383. Vehicle Classification under Extreme Imbalance: A Comparative Study of Ensemble Learning and CNNs
  384. ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
  385. The Emergence of Social Science of Large Language Models
  386. Uncertainty-Guided Expert-AI Collaboration for Efficient Soil Horizon Annotation
  387. DRIFT-Net: A Spectral--Coupled Neural Operator for PDEs Learning
  388. Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning
  389. Improved Robustness from Biologically Inspired Sparse Contrast Representations
  390. ELPG-DTFS: Prior-Guided Adaptive Time-Frequency Graph Neural Network for EEG Depression Diagnosis
  391. Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
  392. Beyond the Hook: Predicting Billboard Hot 100 Chart Inclusion with Machine Learning from Streaming, Audio Signals, and Perceptual Features
  393. PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement
  394. A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication
  395. Cell2Text: Multimodal LLM for Generating Single-Cell Descriptions from RNA-Seq Data
  396. Evaluating SAP Joule for Code Generation
  397. Putnam-like dataset summary: LLMs as mathematical competition contestants
  398. Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
  399. UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections
  400. Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets
  401. A Greedy PDE Router for Blending Neural Operators and Classical Methods
  402. RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off
  403. TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
  404. TACO-Net: Topological Signatures Triumph in 3D Object Classification
  405. Physics-informed learning under mixing: How physical knowledge speeds up learning
  406. DSAT-HD: Dual-Stream Adaptive Transformer with Hybrid Decomposition for Multivariate Time Series Forecasting
  407. Fidelity-Aware Data Composition for Robust Robot Generalization
  408. Evaluating Spatiotemporal Consistency in Automatically Generated Sewing Instructions
  409. Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting
  410. Assessing the risk of future Dunkelflaute events for Germany using generative deep learning
  411. SkyLink: Unifying Street-Satellite Geo-Localization via UAV-Mediated 3D Scene Alignment
  412. MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models
  413. Neural Message-Passing on Attention Graphs for Hallucination Detection
  414. In-Context Learning of Temporal Point Processes with Foundation Inference Models
  415. Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG
  416. Surjective Independence of Causal Influences for Local Bayesian Network Structures
  417. ProxyAttn: Guided Sparse Attention via Representative Heads
  418. Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm
  419. Bundle Network: a Machine Learning-Based Bundle Method
  420. A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
  421. Who invented deep residual learning?
  422. Evaluation of Polarimetric Fusion for Semantic Segmentation in Aquatic Environments
  423. Beyond Softmax: A Natural Parameterization for Categorical Random Variables
  424. Q-Net: Queue Length Estimation via Kalman-based Neural Networks
  425. Discrete Variational Autoencoding via Policy Search
  426. IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
  427. FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
  428. CoTune: Co-evolutionary Configuration Tuning
  429. Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models
  430. Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
  431. Data-Driven Discrete Geofence Design Using Binary Quadratic Programming
  432. Reference-Free Rating of LLM Responses via Latent Information
  433. InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
  434. Community detection robustness of graph neural networks
  435. CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representations
  436. Successful Misunderstandings: Learning to Coordinate Without Being Understood
  437. VNODE: A Piecewise Continuous Volterra Neural Network
  438. HyperHELM: Hyperbolic Hierarchy Encoding for mRNA Language Modeling
  439. "Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching
  440. Hype or not? Formalizing Automatic Promotional Language Detection in Biomedical Research
  441. Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach
  442. LTLf Learning Meets Boolean Set Cover
  443. HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition
  444. Evaluating classification performance across operating contexts: A comparison of decision curve analysis and cost curves
  445. Algorithms and data structures for automatic precision estimation of neural networks
  446. Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw
  447. Discovering "Words" in Music: Unsupervised Learning of Compositional Sparse Code for Symbolic Music
  448. CURA: Size Isnt All You Need -- A Compact Universal Architecture for On-Device Intelligence
  449. Comprehensive Benchmarking of YOLOv11 Architectures for Scalable and Granular Peripheral Blood Cell Detection
  450. BPMN Assistant: An LLM-Based Approach to Business Process Modeling
  451. BFSM: 3D Bidirectional Face-Skull Morphable Model
  452. Prompting Robot Teams with Natural Language
  453. Learning to Solve Optimization Problems Constrained with Partial Differential Equations
  454. SCOPE: Semantic Conditioning for Sim2Real Category-Level Object Pose Estimation in Robotics
  455. Bandits roaming Hilbert space
  456. NeMo: Needle in a Montage for Video-Language Understanding
  457. Short window attention enables long-term memorization
  458. Training-Free Multimodal Guidance for Video to Audio Generation
  459. LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection
  460. Foggy Crowd Counting: Combining Physical Priors and KAN-Graph
  461. Quantitative convergence of trained single layer neural networks to Gaussian processes
  462. CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D
  463. Performance-Carbon Trade-Offs across Architectural Biases in Shear Flow Forecasting
  464. Instruction Guided Multi Object Image Editing with Quantity and Layout Consistency
  465. Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
  466. Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design
  467. Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings
  468. Robust Multimodal Semantic Segmentation with Balanced Modality Contributions
  469. SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings
  470. A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy
  471. LLM DNA: Tracing Model Evolution via Functional Representations
  472. Neuroplasticity-inspired dynamic ANNs for multi-task demand forecasting
  473. Preference-Based Dynamic Ranking Structure Recognition
  474. Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
  475. Overcoming Over-Fitting in Constraint Acquisition via Query-Driven Interactive Refinement
  476. A Text-To-Text Alignment Algorithm for Better Evaluation of Modern Speech Recognition Systems
  477. Performance-Efficiency Trade-off for Fashion Image Retrieval
  478. FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
  479. Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
  480. Interpretable Self-Supervised Learning via Representer Landmarks and Nystr"om Approximation
  481. Moravec's Paradox and Restrepo's Model: Limits of AGI Automation in Growth
  482. An Agent-Based Framework for Automated Higher-Voice Harmony Generation
  483. Distributionally Robust Federated Learning with Outlier Resilience
  484. Convergence of graph Dirichlet energies and graph Laplacians on intersecting manifolds of varying dimensions
  485. Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions
  486. Contrastive Learning for Correlating Network Incidents
  487. Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
  488. A Systematic Review of Digital Twin-Driven Predictive Maintenance in Industrial Engineering: Taxonomy, Architectural Elements, and Future Research Directions
  489. NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
  490. EOE: Evolutionary Optimization of Experts for Training Language Models
  491. Alternatives To Next Token Prediction In Text Generation -- A Survey
  492. Semantic Compression via Multimodal Representation Learning
  493. BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification
  494. Multi-Item-Query Attention for Stable Sequential Recommendation
  495. Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
  496. CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task
  497. Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting
  498. A Data-Centric Perspective on the Influence of Image Data Quality in Machine Learning Models
  499. ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection
  500. Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure
  501. RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis
  502. From Sound to Setting: AI-Based Equalizer Parameter Prediction for Piano Tone Replication
  503. The 2025 OpenAI Preparedness Framework does not guarantee any AI risk mitigation practices: a proof-of-concept for affordance analyses of AI safety policies
  504. PCICF: A Pedestrian Crossing Identification and Classification Framework
  505. REMAP: Regularized Matching and Partial Alignment of Video Embeddings
  506. AXIS: Explainable Time Series Anomaly Detection with Large Language Models
  507. Mask Clustering-based Annotation Engine for Large-Scale Submeter Land Cover Mapping
  508. Prediction-Powered Communication with Distortion Guarantees
  509. Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
  510. DINOReg: Strong Point Cloud Registration with Vision Foundation Model
  511. R2M: Real-Aware Residual Model Merging for Robust and Generalizable Deepfake Detection
  512. Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
  513. DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
  514. An Enhanced Pyramid Feature Network Based on Long-Range Dependencies for Multi-Organ Medical Image Segmentation
  515. Beyond Repetition: Text Simplification and Curriculum Learning for Data-Constrained Pretraining
  516. Dynamic Orchestration of Multi-Agent System for Real-World Multi-Image Agricultural VQA
  517. Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters
  518. Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning
  519. humancompatible.detect: a Python Toolkit for Detecting Bias in AI Models
  520. AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
  521. Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
  522. H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
  523. TP-MVCC: Tri-plane Multi-view Fusion Model for Silkie Chicken Counting
  524. Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks
  525. TraitSpaces: Towards Interpretable Visual Creativity for Human-AI Co-Creation
  526. ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
  527. AuON: A Linear-time Alternative to Orthogonal Momentum Updates
  528. Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
  529. Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
  530. PEARL: Performance-Enhanced Aggregated Representation Learning
  531. Towards Foundation Models for Cryo-ET Subtomogram Analysis
  532. OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction
  533. A study of Universal ODE approaches to predicting soil organic carbon
  534. Experience Paper: Adopting Activity Recognition in On-demand Food Delivery Business
  535. LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces
  536. Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports
  537. LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research
  538. ActiveCQ: Active Estimation of Causal Quantities
  539. Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
  540. Overview of SCIDOCA 2025 Shared Task on Citation Prediction, Discovery, and Placement
  541. Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context
  542. Skeleton-based Robust Registration Framework for Corrupted 3D Point Clouds
  543. S2NN: Sub-bit Spiking Neural Networks
  544. Graph-Based Learning of Free Surface Dynamics in Generalized Newtonian Fluids using Smoothed Particle Hydrodynamics
  545. LAMP-PRo: Label-aware Attention for Multi-label Prediction of DNA- and RNA-binding Proteins using Protein Language Models
  546. VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
  547. Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
  548. Cognitive State Inference from VR Motion via Motion Foundation Model
  549. Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns
  550. Interactive Program Synthesis for Modeling Collaborative Physical Activities from Narrated Demonstrations
  551. Prompt and Parameter Co-Optimization for Large Language Models
  552. Model Merging Scaling Laws in Large Language Models
  553. PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization
  554. Model Fusion with Multi-LoRA Inference for Tool-Enhanced Game Dialogue Agents
  555. Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
  556. Non-Invasive Detection of PROState Cancer with Novel Time-Dependent Diffusion MRI and AI-Enhanced Quantitative Radiological Interpretation: PROS-TD-AI
  557. Proposing a Framework for Machine Learning Adoption on Legacy Systems
  558. Semantic Editing with Coupled Stochastic Differential Equations
  559. Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
  560. Conda: Column-Normalized Adam for Training Large Language Models Faster
  561. MoVa: Towards Generalizable Classification of Human Morals and Values
  562. Metamorphic Testing for Audio Content Moderation Software
  563. Scalable Audio-Visual Masked Autoencoders for Efficient Affective Video Facial Analysis
  564. Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos
  565. BALR-SAM: Boundary-Aware Low-Rank Adaptation of SAM for Resource-Efficient Medical Image Segmentation
  566. Can Large Language Models Express Uncertainty Like Human?
  567. UniVid: The Open-Source Unified Video Model
  568. Negative Pre-activations Differentiate Syntax
  569. Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
  570. Measuring Competency, Not Performance: Item-Aware Evaluation Across Medical Benchmarks
  571. Simulating Post-Neoadjuvant Chemotherapy Breast Cancer MRI via Diffusion Model with Prompt Tuning
  572. Tumor Synthesis conditioned on Radiomics
  573. Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification
  574. High-Order Progressive Trajectory Matching for Medical Image Dataset Distillation
  575. FM-FoG: A Real-Time Foundation Model-based Wearable System for Freezing-of-Gait Mitigation
  576. Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
  577. Multi-Scale Geometric Autoencoder
  578. LatXGen: Towards Radiation-Free and Accurate Quantitative Analysis of Sagittal Spinal Alignment Via Cross-Modal Radiographic View Synthesis
  579. Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
  580. Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation
  581. Towards Efficient Inference under Nonmonotone Missingness with General Imputation
  582. STRAPSim: A Portfolio Similarity Metric for ETF Alignment and Portfolio Trades
  583. Neural Visibility of Point Sets
  584. Accelerating Cerebral Diagnostics with BrainFusion: A Comprehensive MRI Tumor Framework
  585. TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation
  586. Evaluation of Machine and Deep Learning Techniques for Cyclone Trajectory Regression and Status Classification by Time Series Data
  587. From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions
  588. A signal separation view of classification
  589. Analysis of Bias in Deep Learning Facial Beauty Regressors
  590. EYE-DEX: Eye Disease Detection and EXplanation System
  591. ASTROCO: Self-Supervised Conformer-Style Transformers for Light-Curve Embeddings
  592. Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding