mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 19 Mar 2026

459 papers

  1. Soft-Label Governance for Distributional Safety in Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  2. Lossless Prompt Compression via Dictionary-Encoding and In-Context Learning: Enabling Cost-Effective LLM Analysis of Repetitive DataEfficient LLM inference and serving → Prompt and context compression
  3. Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM LogicLLM reasoning → Test-time compute and efficient thinking
  4. Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI ModellinLLM reasoning → Mathematical reasoning
  5. Agentic AI in Engineering and Manufacturing: Industry Perspectives on Utility, Adoption, Challenges, and OpportunitiesLLM agents and tool use → Software engineering coding agents
  6. Multi-User Large Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel SpaceOffline RL and imitation learning from data → Safe offline RL
  8. UniFluids: Unified Neural Operator Learning with Conditional Flow-matchingDiffusion models → Flow matching, time series and science
  9. The Causal Impact of Tool Affordance on Safety Alignment in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  10. VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool SelectionLLM agents and tool use → Tool learning and function calling
  12. kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline GenerationLLM agents and tool use → Web, search, and research agents
  13. BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  14. Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency BridgesDiffusion models → Robustness, privacy and adversarial aspects +1
  15. InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow MatchingDiffusion models → Flow matching, time series and science
  16. From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native SystemsLLM reasoning → Reasoning for agents, planning and code +1
  17. HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMsRetrieval-augmented generation → RAG for code
  18. Collaborative Adaptive Curriculum for Progressive Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  19. HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on ForgettingKnowledge distillation → Detection and dense prediction distillation
  20. ReXInTheWild: A Unified Benchmark for Medical Photograph UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  21. Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer AnalysisLLM reasoning → Clinical and biomedical applications +1
  22. Learning to Disprove: Formal Counterexample Generation with Large Language ModelsLLM reasoning → Mathematical reasoning
  23. Teaching an Agent to Sketch One Part at a TimeLLM agents and tool use → Agent skill learning and evolution
  24. Instruction-Free Tuning of Large Vision Language Models for Medical Instruction FollowingMultimodal LLMs / vision-language models → Medical vision-language models
  25. Narrative Aligned Long Form Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
  26. TRACE: Trajectory Recovery with State Propagation Diffusion for Urban MobilityDiffusion models → Diffusion and flow policies for robotics
  27. A Framework for Formalizing LLM Agent SecurityLLM agents and tool use → Agent threats, guardrails and governance +1
  28. ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Deep Hilbert--Galerkin Methods for Infinite-Dimensional PDEs and Optimal ControlDeep reinforcement learning methods → RL theory and sample complexity
  30. Near-Equivalent Q-learning Policies for Dynamic Treatment RegimesDeep reinforcement learning methods → RL for clinical treatment and surgery
  31. Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt StructureMechanistic interpretability → Probing deception, bias and beliefs
  32. The Autonomy Tax: Defense Training Breaks LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  33. Optimizing Resource-Constrained Non-Pharmaceutical Interventions for Multi-Cluster Outbreak Control Using Hierarchical Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
  34. Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  35. Warm-Start Flow Matching for Guaranteed Fast Text/Image GenerationDiffusion models → Flow matching, time series and science
  36. Exploring the Agentic Frontier of Verilog Code GenerationLLM agents and tool use → Software engineering coding agents
  37. Diffusion-Guided Semantic Consistency for Multimodal HeterogeneityDiffusion models → Robustness, privacy and adversarial aspects
  38. Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking InversionsLLM reasoning → Test-time compute and efficient thinking +1
  39. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene UnderstandingLLM reasoning → Spatial and embodied reasoning +1
  40. Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization
  41. Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation TokensDiffusion models → Diffusion foundations and sampling
  42. Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion TokenizerDiffusion models → Video generation
  43. FinTradeBench: A Financial Reasoning Benchmark for LLMsLLM reasoning → Reasoning for agents, planning and code
  44. Spectrally-Guided Diffusion Noise SchedulesDiffusion models → Diffusion foundations and sampling
  45. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy DistillationLLM agents and tool use → General LLM agent frameworks and benchmarks +2
  46. DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and UnderstandingWorld models → World models for autonomous driving +1
  47. Rethinking Vector Field Learning for Generative SegmentationDiffusion models → Medical imaging and segmentation
  48. RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and EditingDiffusion models → Diffusion foundations and sampling
  49. Tinted Frames: Question Framing Blinds Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  50. OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic ManipulationWorld models → Embodied and robot world models
  51. FASTER: Rethinking Real-Time Flow VLAsVision-language-action models → Efficient VLA inference and adaptation
  52. OS-Themis: A Scalable Critic Framework for Generalist GUI RewardsLLM agents and tool use → GUI and mobile agents +1
  53. Markov Potential Game and Multi-Agent Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
  54. MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular dataDiffusion models → Robustness, privacy and adversarial aspects +1
  55. Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA ModelsVision-language-action models → Generalist VLA models and benchmarks
  56. Box Maze: A Process-Control Architecture for Reliable LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +2
  57. Few-shot Acoustic Synthesis with Multimodal Flow MatchingDiffusion models → Audio, speech and music
  58. SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware LimitsLLM agents and tool use → Software engineering coding agents
  59. DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on EdgeMixture-of-experts → Efficient MoE training and inference systems
  60. Evaluating Counterfactual Strategic Reasoning in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  61. Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language NavigationLLM agents and tool use → Multimodal and embodied agents
  62. Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion GenerationDiffusion models → Image generation, text-to-image and editing
  63. ADAPT: Attention Driven Adaptive Prompt Scheduling and InTerpolating Orthogonal Complements for Rare Concepts GenerationDiffusion models → Image generation, text-to-image and editing
  64. D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion DecodingDiffusion models → Discrete and text diffusion
  65. Implicit Patterns in LLM-Based Binary AnalysisLLM reasoning → Reasoning for agents, planning and code +1
  66. GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and ReasoningLLM reasoning → Spatial and embodied reasoning
  67. Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning ControlDeep reinforcement learning methods → Adversarial robustness and RL in finance
  68. A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM InferenceEfficient LLM inference and serving → Early exit and edge inference
  69. From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  70. On Optimizing Multimodal Jailbreaks for Spoken Language ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  71. Revisiting Autoregressive Models for Generative Image ClassificationDiffusion models → Image generation, text-to-image and editing
  72. How Uncertainty Estimation Scales with Sampling in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  73. LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG ModelingState-space sequence models (S4, Mamba) → Physiological signal modeling
  74. TAU-R1: Visual Language Model for Traffic Anomaly UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  75. DaPT: A Dual-Path Framework for Multilingual Multi-hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  76. SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic CuesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  77. Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  78. SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset CurationLLM agents and tool use → General LLM agent frameworks and benchmarks
  79. MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  80. TerraScope: Pixel-Grounded Visual Reasoning for Earth ObservationLLM reasoning → Spatial and embodied reasoning +1
  81. SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs +1
  82. Rethinking MLLM Itself as a Segmenter with a Single Segmentation TokenMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  83. What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?LLM reasoning → Knowledge- and tool-augmented reasoning
  84. Security awareness in LLM agents: the NDAI zone caseLLM agents and tool use → Agent threats, guardrails and governance
  85. Hypothesis-Conditioned Query Rewriting for Decision-Useful RetrievalRetrieval-augmented generation → RAG robustness and adaptive retrieval
  86. Foundations of Schr"odinger Bridges for Generative ModelingDiffusion models → Diffusion foundations and sampling
  87. CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You ThinkDiffusion models → Diffusion and flow policies for robotics +1
  88. MERGE: Guided Vision-Language Models for Multi-Actor Event Reasoning and Grounding in Human-Robot InteractionLLM reasoning → Spatial and embodied reasoning +1
  89. Maximum-Entropy Exploration with Future State-Action Visitation MeasuresDeep reinforcement learning methods → RL theory and sample complexity
  90. Context Bootstrapped Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  91. Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thoughtLLM reasoning → Test-time compute and efficient thinking
  92. Agentic Business Process Management: A Research ManifestoLLM agents and tool use → Software engineering coding agents
  93. Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflectionsLLM agents and tool use → Agent threats, guardrails and governance
  94. Safety-Guaranteed Imitation Learning from Nonlinear Model Predictive Control for Spacecraft Close Proximity OperationsOffline RL and imitation learning from data → Safe offline RL
  95. Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  96. Parallelizing Tool Execution and LLM Generation for Low-Latency Agent ServingLLM agents and tool use → Software engineering coding agents
  97. Translating MRI to PET through Conditional Diffusion Models with Enhanced Pathology AwarenessDiffusion models → Medical imaging and segmentation
  98. I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance SystemsLLM agents and tool use → Social simulation and multi-agent debate
  99. Quantitative Introspection in Language Models: Tracking Emotive States Across ConversationMechanistic interpretability → Probing deception, bias and beliefs
  100. MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language ModelLLM reasoning → Spatial and embodied reasoning +2
All 459
  1. Reasoning over mathematical objects: on-policy reward modeling and test time aggregationLLM reasoning → Mathematical reasoning +1
  2. DriftGuard: Mitigating Asynchronous Data Drift in Federated LearningMixture-of-experts → Federated mixture-of-experts
  3. RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map ConstructionDiffusion models → Diffusion for compression and wireless
  4. RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language ModelsLLM reasoning → Reinforcement learning for reasoning +2
  5. Motion-o: Trajectory-Grounded Video ReasoningLLM reasoning → Multimodal reasoning
  6. Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World ModelWorld models → World models for navigation
  7. HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  8. ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  9. Perceptio: Perception Enhanced Vision Language Models via Spatial Token GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  10. Functional Subspace Watermarking for Large Language ModelsLLM safety and security → Watermarking generated content and models +1
  11. Mi:dm K 2.5 ProLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. ViTac-Tracing: Visual-Tactile Imitation Learning of Deformable Object TracingOffline RL and imitation learning from data → Robot manipulation imitation learning
  13. A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  14. ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security EvaluationLLM agents and tool use → Agent threats, guardrails and governance +1
  15. DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  16. Are complicated loss functions necessary for teaching LLMs to reason?LLM reasoning → Reinforcement learning for reasoning
  17. Memento-Skills: Let Agents Design AgentsLLM agents and tool use → Agent memory systems
  18. 6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  19. CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User FeedbacksLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  20. Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI ArchitecturesLLM agents and tool use → Social simulation and multi-agent debate
  21. Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real TransferDiffusion models → Image generation, text-to-image and editing
  22. MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-EvolutionLLM reasoning → Reasoning for agents, planning and code +1
  23. HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  24. Thinking with Constructions: A Benchmark and Policy Optimization for Visual-Text Interleaved Geometric ReasoningLLM reasoning → Spatial and embodied reasoning
  25. Balanced Thinking: Improving Chain of Thought Training in Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  26. MOSAIC: Multi-Objective Slice-Aware Iterative Curation for AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  27. Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-ClusteringDiffusion models → Video generation
  28. D-Mem: A Dual-Process Memory System for LLM AgentsLLM agents and tool use → Agent memory systems
  29. Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image GenerationLLM agents and tool use → Multimodal and embodied agents
  30. Learning to Self-EvolveSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  31. ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMsLLM reasoning → Reasoning for agents, planning and code +1
  32. Improving Joint Audio-Video Generation with Cross-Modal Context LearningDiffusion models → Audio, speech and music
  33. Complementary Text-Guided Attention for Zero-Shot Adversarial RobustnessMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  34. SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  35. Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provablyLLM reasoning → Reasoning for agents, planning and code +1
  36. CausalVAD: De-confounding End-to-End Autonomous Driving via Causal InterventionEnd-to-end autonomous driving → End-to-end system architecture
  37. HiMu: Hierarchical Multimodal Frame Selection for Long Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
  38. CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  39. Beyond Passive Aggregation: Active Auditing and Topology-Aware Defense in Decentralized Federated LearningLLM safety and security → Federated unlearning and poisoning
  40. Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  41. Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D WorldsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  42. Correlation-Weighted Multi-Reward Optimization for Compositional GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  43. Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +2
  44. Total Recall QA: A Verifiable Evaluation Suite for Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  45. CAFlow: Adaptive-Depth Single-Step Flow Matching for Efficient Histopathology Super-ResolutionDiffusion models → Medical imaging and segmentation
  46. Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISMLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  47. Efficient Video Diffusion with Sparse Information Transmission for Video CompressionDiffusion models → Diffusion for compression and wireless
  48. Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual ReasoningLLM reasoning → Spatial and embodied reasoning +1
  49. AIMER: Calibration-Free Task-Agnostic MoE Expert PruningMixture-of-experts → MoE large language models
  50. EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  51. T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-WorldMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  52. Do Vision Language Models Understand Human Engagement in Games?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  53. Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  54. CyberJustice Tutor: An Agentic AI Framework for Cybersecurity Learning via Think-Plan-Act Reasoning and Pedagogical ScaffoldingLLM reasoning → Reasoning for agents, planning and code +1
  55. MedQ-UNI: Toward Unified Medical Image Quality Assessment and Restoration via Vision-Language ModelingMultimodal LLMs / vision-language models → Medical vision-language models
  56. AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action ModelsWorld models → Embodied and robot world models +2
  57. AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware MambaState-space sequence models (S4, Mamba) → Speech and audio SSMs
  58. Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  59. AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning ArchitectureLLM reasoning → Reasoning benchmarks and evaluation
  60. Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM SystemsLLM safety and security → Prompt injection and agent security
  61. AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI AgentsLLM agents and tool use → GUI and mobile agents
  62. Adaptive Decoding via Test-Time Policy Learning for Self-Improving GenerationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  63. Multimodal Task Interference: A Benchmark and Analysis of History-Target Mismatch in Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  64. Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?LLM reasoning → Clinical and biomedical applications +1
  65. TARo: Token-level Adaptive Routing for LLM Test-time AlignmentLLM reasoning → Test-time compute and efficient thinking +1
  66. TopoChunker: Topology-Aware Agentic Document Chunking FrameworkRetrieval-augmented generation → Multimodal RAG +1
  67. Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian OptimizationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  68. FlowMS: Flow Matching for De Novo Structure Elucidation from Mass SpectraDiffusion models → Flow matching, time series and science
  69. RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approachDeep reinforcement learning methods → RL theory and sample complexity
  70. From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  71. PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  72. Mapping Recent Shifts in Digital Art via Conference Discourse: AI, XR, the Metaverse, and Blockchain/NFTs (2021-2025)
  73. From Seeing it to Experiencing it: Interactive Evaluation of Intersectional Voice Bias in Human-AI Speech Interaction
  74. Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub
  75. From Understanding to Creation: A Prerequisite-Free AI Literacy Course with Technical Depth Across Majors
  76. ML-Based Real-Time Downlink Performance Prediction in Standalone 5G NR Using Smartphones
  77. Hardware Utilization and Inference Performance of Edge Object Detection Under Fault Injection
  78. Adoption and Effectiveness of AI-Based Anomaly Detection for Cross Provider Health Data Exchange
  79. HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
  80. Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements
  81. A reconfigurable smart camera implementation for jet flames characterization based on an optimized segmentation model
  82. Dynamic Mask Enhanced Intelligent Multi-UAV Deployment for Urban Vehicular Networks
  83. A Multi-Modal Dataset for Ground Reaction Force Estimation Using Consumer Wearable Sensors
  84. Interpretable liquid crystal phase classification via two-by-two ordinal patterns
  85. Brain-inspired AI for Edge Intelligence: a systematic review
  86. Stress Classification from ECG Signals Using Vision Transformer
  87. The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
  88. Ca2+ transient detection and segmentation with the Astronomically motivated algorithm for Background Estimation And Transient Segmentation (Astro-BEATS)
  89. GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis
  90. Which Workloads Belong in Orbit? A Workload-First Framework for Orbital Data Centers Using Semantic Abstraction
  91. Bypassing Document Ingestion: An MCP Approach to Financial Q&A
  92. Rolling-Origin Validation Reverses Model Rankings in Multi-Step PM10 Forecasting: XGBoost, SARIMA, and Persistence
  93. GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems
  94. Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception
  95. EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control
  96. The Global-Local loop: what is missing in bridging the gap between geospatial data from numerous communities?
  97. Voice Privacy from an Attribute-based Perspective
  98. Transformer-Based Predictive Maintenance for Risk-Aware Instrument Calibration
  99. MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
  100. LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
  101. dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
  102. SurfaceXR: Fusing Smartwatch IMUs and Egocentric Hand Pose for Seamless Surface Interactions
  103. Depictions of Depression in Generative AI Video Models: A Preliminary Study of OpenAI's Sora 2
  104. Recognising BSL Fingerspelling in Continuous Signing Sequences
  105. Inducing Sustained Creativity and Diversity in Large Language Models
  106. ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models
  107. FedAgain: A Trust-Based and Robust Federated Learning Strategy for an Automated Kidney Stone Identification in Ureteroscopy
  108. Linear Social Choice with Few Queries: A Moment-Based Approach
  109. Beyond the Desk: Barriers and Future Opportunities for AI to Assist Scientists in Embodied Physical Tasks
  110. Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
  111. Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering
  112. ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
  113. VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification
  114. Any-Subgroup Equivariant Networks via Symmetry Breaking
  115. Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids
  116. Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
  117. Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3
  118. Hyperagents
  119. GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models
  120. In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
  121. Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas
  122. TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
  123. LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray
  124. Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphs
  125. When both Grounding and not Grounding are Bad -- A Partially Grounded Encoding of Planning into SAT (Extended Version)
  126. Vocabulary shapes cross-lingual variation of word-order learnability in language models
  127. Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs
  128. Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents
  129. Scalable Prompt Routing via Fine-Grained Latent Task Discovery
  130. Bridging Conformal Prediction and Scenario Optimization: Discarded Constraints and Modular Risk Allocation
  131. TuLaBM: Tumor-Biased Latent Bridge Matching for Contrast-Enhanced MRI Synthesis
  132. Factored Levenberg-Marquardt for Diffeomorphic Image Registration: An efficient optimizer for FireANTs
  133. AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis
  134. A Novel Solution for Zero-Day Attack Detection in IDS using Self-Attention and Jensen-Shannon Divergence in WGAN-GP
  135. A Mathematical Theory of Understanding
  136. Anatomical Heterogeneity in Transformer Language Models
  137. Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons
  138. Spectral Tempering for Embedding Compression in Dense Passage Retrieval
  139. DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training
  140. POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
  141. Matryoshka Gaussian Splatting
  142. MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
  143. NavTrust: Benchmarking Trustworthiness for Embodied Navigation
  144. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
  145. Under One Sun: Multi-Object Generative Perception of Materials and Illumination
  146. EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
  147. F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
  148. Online Learning and Equilibrium Computation with Ranking Feedback
  149. LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
  150. DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
  151. R-equivalence on Cubic Surfaces I: Existing Cases with Non-Trivial Universal Equivalence
  152. Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
  153. Robustness, Cost, and Attack-Surface Concentration in Phishing Detection
  154. Extending SSMs with the Exponentially Weighted Signature
  155. How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
  156. Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
  157. Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment
  158. ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis
  159. Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees
  160. cuGenOpt: A GPU-Accelerated General-Purpose Metaheuristic Framework for Combinatorial Optimization
  161. PPI is the Difference Estimator: Recognizing the Survey Sampling Roots of Prediction-Powered Inference
  162. VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models
  163. Optimal Splitting of Language Models from Mixtures to Specialized Domains
  164. Fast and Effective Computation of Generalized Symmetric Matrix Factorization
  165. Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
  166. UGID: Unified Graph Isomorphism for Debiasing Large Language Models
  167. SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data
  168. Hierarchical Latent Structure Learning through Online Inference
  169. CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
  170. Numerical Considerations for the Construction of Karhunen-Lo`eve Expansions
  171. FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning
  172. Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
  173. Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models
  174. A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes
  175. Multi-Modal Building Change Detection for Large-Scale Small Changes: Benchmark and Baseline
  176. DROID-SLAM in the Wild
  177. CAMO: A Conditional Neural Solver for the Multi-objective Multiple Traveling Salesman Problem
  178. Communication-Efficient and Robust Multi-Modal Federated Learning via Latent-Space Consensus
  179. Large Language Models provide support for the parallelogram theory of analogy
  180. Hardness of High-Dimensional Linear Classification
  181. Adaptive Nonlinear Data Assimilation through P-Spline Triangular Measure Transport
  182. Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding
  183. SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation
  184. Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation
  185. Man and machine: artificial intelligence and judicial decision making
  186. Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
  187. When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
  188. FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal
  189. Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference
  190. Behavioral Fingerprints for LLM Endpoint Stability and Identity
  191. GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness
  192. AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
  193. Unleashing the Power of Simplicity: A Minimalist Strategy for State-of-the-Art Fingerprint Enhancement
  194. RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation
  195. Regret Bounds for Competitive Resource Allocation with Endogenous Costs
  196. Evaluating Game Difficulty in Tetris Block Puzzle
  197. Unmasking Algorithmic Bias in Predictive Policing: A GAN-Based Simulation Framework with Multi-City Temporal Analysis
  198. Revisiting OmniAnomaly for Anomaly Detection: performance metrics and comparison with PCA-based models
  199. Book your room in the Turing Hotel! A symmetric and distributed Turing Test with multiple AIs and humans
  200. PRIOR: Perceptive Learning for Humanoid Locomotion with Reference Gait Priors
  201. Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction
  202. Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
  203. Teleological Inference in Structural Causal Models via Intentional Interventions
  204. BVSIMC: Bayesian Variable Selection-Guided Inductive Matrix Completion for Improved and Interpretable Drug Discovery
  205. Balancing Performance and Fairness in Explainable AI for Anomaly Detection in Distributed Power Plants Monitoring
  206. A conceptual framework for ideology in online discourse beyond the left and right
  207. VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
  208. Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning
  209. Kernel Single-Index Bandits: Estimation, Inference, and Learning
  210. An Optimised Greedy-Weighted Ensemble Framework for Financial Loan Default Prediction
  211. Improving moment tensor solutions under Earth structure uncertainty with simulation-based inference
  212. Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching
  213. GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting
  214. Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs
  215. Ventriloquist LLMs: Linear Alignment of Late-Stage Representations
  216. Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method
  217. From Accuracy to Readiness: Metrics and Benchmarks for Human-AI Decision-Making
  218. PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment
  219. Authority-Level Priors: An Under-Specified Constraint in Hierarchical Predictive Processing
  220. Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography
  221. A Human-in/on-the-Loop Framework for Accessible Text Generation
  222. Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo
  223. Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs
  224. Through the Looking-Glass: AI-Mediated Video Communication Reduces Interpersonal Trust and Confidence in Judgments
  225. Conflict-Based Search for Multi Agent Path Finding with Asynchronous Actions
  226. Data-driven construction of machine-learning-based interatomic potentials for gas-surface scattering dynamics: the case of NO on graphite
  227. Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
  228. BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding
  229. Towards Interpretable Foundation Models for Retinal Fundus Images
  230. A Model Ensemble-Based Post-Processing Framework for Fairness-Aware Prediction
  231. Model Order Reduction of Cerebrovascular Hemodynamics Using POD_Galerkin and Reservoir Computing_based Approach
  232. Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging
  233. Agent Control Protocol: Admission Control for Agent Actions
  234. Student views in AI Ethics and Social Impact
  235. Structure of Basic Human Values in Russian Social Media
  236. Seasoning Generative Models for a Generalization Aftertaste
  237. Can LLM generate interesting mathematical research problems?
  238. dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
  239. Signals of Success and Struggle: Early Prediction and Physiological Signatures of Human Performance across Task Complexity
  240. VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
  241. Rethinking Uncertainty Quantification and Entanglement in Image Segmentation
  242. Proceedings of the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind
  243. Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
  244. SRRM: Improving Recursive Transport Surrogates in the Small-Discrepancy Regime
  245. SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction
  246. Automatic Configuration of LLM Post-Training Pipelines
  247. Enhancing the Parameterization of Reservoir Properties for Data Assimilation Using Deep VAE-GAN
  248. Implicit Grading Bias in Large Language Models: How Writing Style Affects Automated Assessment Across Math, Programming, and Essay Tasks
  249. ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation
  250. NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and Statistical Physics
  251. Dual-Model Prediction of Affective Engagement and Vocal Attractiveness from Speaker Expressiveness in Video Learning
  252. WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification
  253. Automatic detection of Gen-AI texts: A comparative framework of neural models
  254. Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
  255. EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation
  256. Holter-to-Sleep: AI-Enabled Repurposing of Single-Lead ECG for Sleep Phenotyping
  257. Accurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism
  258. From ex(p) to poly: Gaussian Splatting with Polynomial Kernels
  259. A mathematical framework for time-delay reservoir computing analysis
  260. Off-Policy Learning with Limited Supply
  261. OCP: Orthogonal Constrained Projection for Sparse Scaling in Industrial Commodity Recommendation
  262. STEP: Scientific Time-Series Encoder Pretraining via Cross-Domain Distillation
  263. Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defend
  264. Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models
  265. Cognitive Amplification vs Cognitive Delegation in Human-AI Systems: A Metric Framework
  266. MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation
  267. Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixels
  268. Multimodal Model for Computational Pathology:Representation Learning and Image Compression
  269. Enhancing Multi-Corpus Training in SSL-Based Anti-Spoofing Models: Domain-Invariant Feature Extraction
  270. Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation
  271. Beyond String Matching: Semantic Evaluation of PDF Table Extraction
  272. Click-to-Ask: An AI Live Streaming Assistant with Offline Copywriting and Online Interactive QA
  273. Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection
  274. MeInTime: Bridging Age Gap in Identity-Preserving Face Restoration
  275. Evaluating Model-Free Policy Optimization in Masked-Action Environments via an Exact Blackjack Oracle
  276. A Comparative Empirical Study of Catastrophic Forgetting Mitigation in Sequential Task Adaptation for Continual Natural Language Processing Systems
  277. A Theoretical Comparison of No-U-Turn Sampler Variants: Necessary and Sufficient Convergence Conditions and Mixing Time Analysis under Gaussian Targets
  278. OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
  279. SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
  280. An Onto-Relational-Sophic Framework for Governing Synthetic Minds
  281. GEAR: Geography-knowledge Enhanced Analog Recognition Framework in Extreme Environments
  282. GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?
  283. REST: Receding Horizon Explorative Steiner Tree for Zero-Shot Object-Goal Navigation
  284. OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
  285. Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset
  286. Cyber-Resilient Digital Twins: Discriminating Attacks for Safe Critical Infrastructure Control
  287. DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units
  288. Cross-Modal Rationale Transfer for Explainable Humanitarian Classification on Social Media
  289. AutORAN: LLM-driven Natural Language Programming for Agile xApp Development
  290. SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
  291. myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition
  292. Elastic Weight Consolidation Done Right for Continual Learning
  293. Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors
  294. A Novel FACS-Aligned Anatomical Text Description Paradigm for Fine-Grained Facial Behavior Synthesis
  295. Color image restoration based on nonlocal saturation-value similarity
  296. HAViT: Historical Attention Vision Transformer
  297. Breaking Hard Isomorphism Benchmarks with DRESS
  298. WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network
  299. ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs
  300. MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning
  301. Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation
  302. UEPS: Robust and Efficient MRI Reconstruction
  303. CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization
  304. Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks
  305. Transformers Learn Robust In-Context Regression under Distributional Uncertainty
  306. Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
  307. End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration
  308. Learning Decision-Sufficient Representations for Linear Optimization
  309. SINDy-KANs: Sparse identification of non-linear dynamics through Kolmogorov-Arnold networks
  310. HEP Statistical Inference for UAV Fault Detection: CLs, LRT, and SBI Applied to Blade Damage
  311. SCISSR: Scribble-Conditioned Interactive Surgical Segmentation and Refinement
  312. Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
  313. GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems
  314. iSatCR: Graph-Empowered Joint Onboard Computing and Routing for LEO Data Delivery
  315. Data-efficient pre-training by scaling synthetic megadocs
  316. When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making
  317. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
  318. On the Peril of (Even a Little) Nonstationarity in Satisficing Regret Minimization
  319. OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
  320. Foundations and Architectures of Artificial Intelligence for Motor Insurance
  321. From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions
  322. HOMEY: Heuristic Object Masking with Enhanced YOLO for Property Insurance Risk Detection
  323. NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data
  324. FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
  325. TexEditor: Structure-Preserving Text-Driven Texture Editing
  326. Precise Performance of Linear Denoisers in the Proportional Regime
  327. The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
  328. WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
  329. GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
  330. Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
  331. Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
  332. Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images
  333. HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships
  334. Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching
  335. Seeking Universal Shot Language Understanding Solutions
  336. SODIUM: From Open Web Data to Queryable Databases
  337. UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
  338. SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation
  339. MLOW: Interpretable Low-Rank Frequency Magnitude Decomposition of Multiple Effects for Time Series Forecasting
  340. Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits
  341. R&D: Balancing Reliability and Diversity in Synthetic Data Augmentation for Semantic Segmentation
  342. Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression
  343. SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
  344. The Impact of Corporate AI Washing on Farmers' Digital Financial Behavior Response -- An Analysis from the Perspective of Digital Financial Exclusion
  345. From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
  346. Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration
  347. The Spillover Effects of Peer AI Rinsing on Corporate Green Innovation
  348. Statistical Testing Framework for Clustering Pipelines by Selective Inference
  349. Multi-Domain Empirical Bayes for Linearly-Mixed Causal Representations
  350. Inst4DGS: Instance-Decomposed 4D Gaussian Splatting with Multi-Video Label Permutation Learning
  351. Pixel-Accurate Epipolar Guided Matching
  352. Computational and Statistical Hardness of Calibration Distance
  353. AutoScreen-FW: An LLM-based Framework for Resume Screening
  354. An SO(3)-equivariant reciprocal-space neural potential for long-range interactions
  355. Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
  356. Mathematical Foundations of Deep Learning
  357. Evolutionarily Stable Stackelberg Equilibrium
  358. To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
  359. PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching