mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 10 Mar 2026

492 papers

  1. ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency ScenariosEfficient LLM inference and serving → Speculative decoding
  2. BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI ModelsDiffusion models → Image generation, text-to-image and editing
  3. Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  4. C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment AnalysisLLM reasoning → Audio-language model reasoning
  5. Finding and Reactivating Post-Trained LLMs' Hidden Safety MechanismsLLM reasoning → Reasoning for agents, planning and code
  6. Interview-Informed Generative Agents for Product Discovery: A Validation StudyLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. Operationalizing Perceptions of Agent Gender: Foundations and GuidelinesLLM agents and tool use → Social simulation and multi-agent debate
  8. LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News DetectionLLM reasoning → Multimodal reasoning +1
  9. Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG SystemsRetrieval-augmented generation → Privacy and security of RAG
  10. Geometry-Aware Semantic Reasoning for Training Free Video Anomaly DetectionLLM reasoning → Chain-of-thought reasoning for driving
  11. Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA ChainLLM reasoning → Reasoning for agents, planning and code +1
  12. SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich DisassemblyVision-language-action models → Generalist VLA models and benchmarks +1
  13. CR-Bench: Evaluating the Real-World Utility of AI Code Review AgentsLLM agents and tool use → Software engineering coding agents
  14. DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool UseLLM agents and tool use → Tool learning and function calling
  15. Context Before Code: An Experience Report on Vibe Coding in PracticeRetrieval-augmented generation → RAG for code
  16. Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play FrameworkDiffusion models → Diffusion foundations and sampling
  17. Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHFLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  18. SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI EnvironmentsLLM agents and tool use → Software engineering coding agents
  19. From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL FinetuningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. Improving TabPFN's Synthetic Data Generation by Integrating Causal StructureSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  21. GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  22. DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development PracticeLLM agents and tool use → Software engineering coding agents
  23. GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  24. Rethinking the Harmonic Loss via Non-Euclidean Distance LayersLLM reasoning → Multimodal reasoning
  25. A Diffusion Analysis of Policy Gradient for Stochastic BanditsDeep reinforcement learning methods → RL theory and sample complexity
  26. Sabi'a-4 Technical ReportLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Delta-K: Boosting Multi-Instance Generation via Cross-Attention AugmentationDiffusion models → Image generation, text-to-image and editing
  28. Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action SpacesDeep reinforcement learning methods → RL theory and sample complexity
  29. MCP-in-SoS: Risk assessment framework for open-source MCP serversLLM agents and tool use → Agent threats, guardrails and governance
  30. Video-Based Reward Modeling for Computer-Use AgentsLLM agents and tool use → GUI and mobile agents +1
  31. Calibration-Reasoning Framework for Descriptive Speech Quality AssessmentLLM reasoning → Audio-language model reasoning
  32. OpenClaw-RL: Train Any Agent Simply by TalkingLLM agents and tool use → Reinforcement learning for LLM agents
  33. Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance
  34. Cross-Hand Latent Representation for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
  35. Reason and Verify: A Framework for Faithful Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  36. Agentic Control Center for Data Product OptimizationLLM agents and tool use → Web, search, and research agents
  37. AR-VLA: True Autoregressive Action Expert for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  38. CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVRLLM reasoning → Reinforcement learning for reasoning
  39. Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  40. Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation GenerationDiffusion models → Flow matching, time series and science
  41. Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local ExecutorsLLM agents and tool use → Agent threats, guardrails and governance
  42. Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task InterferenceLLM reasoning → Reasoning for agents, planning and code +2
  43. KernelSkill: A Multi-Agent Framework for GPU Kernel OptimizationLLM agents and tool use → Software engineering coding agents
  44. Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language ModelsLLM safety and security → Jailbreaking +1
  45. Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation ModelsMechanistic interpretability → Interpreting time-series and weather models
  46. Improving Search Agent with One Line of CodeLLM agents and tool use → Reinforcement learning for LLM agents
  47. ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  48. From Data Statistics to Feature Geometry: How Correlations Shape SuperpositionMechanistic interpretability → Sparse autoencoder training and evaluation
  49. ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-CompareEfficient LLM inference and serving → Fast autoregressive visual generation
  50. Think Before You Lie: How Reasoning Leads to HonestyLLM reasoning → Prompting and chain-of-thought reasoning
  51. When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-CriticDeep reinforcement learning methods → RL theory and sample complexity
  52. Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality ImputationDiffusion models → Medical imaging and segmentation
  53. MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent SystemsLLM agents and tool use → Medical and scientific domain agents
  54. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  55. Overview of the TREC 2025 Retrieval Augmented Generation (RAG) TrackRetrieval-augmented generation → RAG pipeline design and evaluation
  56. Influencing LLM Multi-Agent Dialogue via Policy-Parameterized PromptsLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and EditingLLM reasoning → Multimodal reasoning
  58. The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization RevocationLLM agents and tool use → Agent threats, guardrails and governance
  59. RecThinker: An Agentic Framework for Tool-Augmented Reasoning in RecommendationLLM reasoning → LLM reasoning for recommendation +1
  60. Chow-Liu Ordering for Long-Context Reasoning in Chain-of-AgentsLLM reasoning → Reasoning for agents, planning and code +1
  61. Prompt-Driven Color Accessibility Evaluation in Diffusion-based Image Generation ModelsDiffusion models → Image generation, text-to-image and editing
  62. VLM-Loc: Localization in Point Cloud Maps via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  63. One-Eval: An Agentic System for Automated and Traceable LLM EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  64. ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware InterpolationDiffusion models → 3D, point cloud and scene generation
  65. Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  66. Quantifying the Necessity of Chain of Thought through Opaque Serial DepthLLM reasoning → Prompting and chain-of-thought reasoning
  67. World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation ModelsLLM reasoning → Spatial and embodied reasoning
  68. Ego: Embedding-Guided Personalization of Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  69. Long-Run Conditional Value-at-Risk Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  70. EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon ReasoningLLM reasoning → Spatial and embodied reasoning +1
  71. RbtAct: Rebuttal as Supervision for Actionable Review Feedback GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  72. FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video GenerationDiffusion models → Video generation
  73. AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive AgentsLLM agents and tool use → Agent memory systems
  74. OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden ConsequencesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  75. Evaluation of LLMs in retrieving food and nutritional context for RAG systemsRetrieval-augmented generation → Time series and agricultural RAG
  76. ActiveUltraFeedback: Efficient Preference Data Generation using Active LearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  77. EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming LanguagesLLM reasoning → Reasoning for agents, planning and code
  78. When to Lock Attention: Training-Free KV Control in Video DiffusionDiffusion models → Video generation
  79. MM-tau-p2: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control SettingsLLM agents and tool use → Social simulation and multi-agent debate
  80. PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt EvolutionLLM agents and tool use → Agent memory systems
  81. Grounding Synthetic Data Generation With Vision and Language ModelsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  82. Decoder-Free Distillation for Quantized Image RestorationKnowledge distillation → General knowledge distillation methods
  83. Preparing Students for AI-Driven Agile Development: A Project-Based AI Engineering CurriculumLLM agents and tool use → Software engineering coding agents
  84. BinaryAttention: One-Bit QK-Attention for Vision and Diffusion TransformersDiffusion models → Video generation
  85. SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation DistillationDiffusion models → Diffusion and flow policies for robotics
  86. More than the Sum: Panorama-Language Models for Adverse Omni-ScenesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  87. GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  88. ALARM: Audio-Language Alignment for Reasoning ModelsLLM reasoning → Audio-language model reasoning
  89. GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process SupervisionLLM reasoning → Spatial and embodied reasoning +1
  90. NS-VLA: Towards Neuro-Symbolic Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  91. Towards Unified Multimodal Interleaved Generation via Group Relative Policy OptimizationLLM reasoning → Multimodal reasoning +1
  92. Dynamic Multimodal Expression Generation for LLM-Driven Pedagogical Agents: From User Experience PerspectiveLLM agents and tool use → Educational agents and math problem solving
  93. Efficiently Aligning Draft Models via Parameter- and Data-Efficient AdaptationEfficient LLM inference and serving → Speculative decoding
  94. Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation BenchmarksVision-language-action models → Reasoning and chain-of-thought in VLA
  95. Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal ReasoningLLM reasoning → Chain-of-thought reasoning for driving +1
  96. A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech RestorationDiffusion models → Audio, speech and music
  97. Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance NavigationLLM reasoning → Spatial and embodied reasoning
  98. Guided Prompt Evolution for Vision-Language Models AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  99. Streaming Autoregressive Video Generation via Diagonal DistillationDiffusion models → Video generation
  100. StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
All 492
  1. Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-DiversityMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  2. OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial TasksLLM reasoning → Spatial and embodied reasoning +1
  3. EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning DistillationVision-language-action models → VLA for autonomous driving +2
  4. ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  5. Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts TransformersMixture-of-experts → Expert routing strategies
  6. AI Act Evaluation Benchmark: An Open, Transparent, and Reproducible Evaluation Dataset for NLP and RAG SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  7. Impact of Markov Decision Process Design on Sim-to-Real Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  8. From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution DistillationDiffusion models → Diffusion and flow policies for robotics
  9. Reviving ConvNeXt for Efficient Convolutional Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  10. LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric ValidationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  11. Reward Prediction with Factorized World StatesLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  12. SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action SpaceOffline RL and imitation learning from data → Offline RL algorithms
  13. The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AIRetrieval-augmented generation → RAG pipeline design and evaluation
  14. Robust Regularized Policy Iteration under Transition UncertaintyOffline RL and imitation learning from data → Offline RL algorithms +1
  15. TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  16. Beyond Scaling: Assessing Strategic Reasoning and Rapid Decision-Making Capability of LLMs in Zero-sum EnvironmentsLLM reasoning → Reasoning for agents, planning and code
  17. Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  18. OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  19. Curveball Steering: The Right Direction To Steer Isn't Always LinearMechanistic interpretability → Activation steering methods
  20. IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic FrameworkLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  21. CORAL: Scalable Multi-Task Robot Learning via LoRA ExpertsVision-language-action models → Reinforcement learning and post-training
  22. TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QALLM reasoning → Reasoning for agents, planning and code +1
  23. See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic ManipulationVision-language-action models → Failure recovery and robustness
  24. ToolRosella: Translating Code Repositories into Standardized Tools for Scientific AgentsLLM agents and tool use → Software engineering coding agents
  25. Logos: An evolvable reasoning engine for rational molecular designLLM reasoning → Clinical and biomedical applications
  26. ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View HypergraphLLM reasoning → Spatial and embodied reasoning
  27. Social-R1: Towards Human-like Social Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  28. Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  29. RAE-NWM: Navigation World Model in Dense Visual Representation SpaceWorld models → World models for navigation +1
  30. MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for RoboticsDeep reinforcement learning methods → RL for games and combinatorial optimization
  31. Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational AwarenessSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  32. EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question AnsweringRetrieval-augmented generation → Generation and context integration +1
  33. Beyond Test-Time Memory: State-Space Optimal Control for LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  34. SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language ModelsEfficient LLM inference and serving → Early exit and edge inference
  35. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero DataLLM reasoning → Multimodal reasoning +2
  36. Emotion is Not Just a Label: Latent Emotional Factors in LLM ProcessingLLM reasoning → Audio-language model reasoning
  37. Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented AgentsRetrieval-augmented generation → Agentic RAG, agents and memory
  38. The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational AwarenessLLM reasoning → Reasoning benchmarks and evaluation
  39. Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-BackRetrieval-augmented generation → Agentic RAG, agents and memory
  40. DEO: Training-Free Direct Embedding Optimization for Negation-Aware RetrievalRetrieval-augmented generation → Generation and context integration
  41. Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  42. Point Cloud as a Foreign Language for Multi-modal Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  43. Progressive Split Mamba: Effective State Space Modelling for Image RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
  44. SPAN-Nav: Generalized Spatial Awareness for Versatile Vision-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. RubiCap: Rubric-Guided Reinforcement Learning for Dense Image CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  46. Real-Time Trust Verification for Safe Agentic Actions using TrustBenchLLM agents and tool use → Agent threats, guardrails and governance
  47. DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question AnsweringLLM agents and tool use → Web, search, and research agents
  48. RTFDNet: Fusion-Decoupling for Robust RGB-T SegmentationKnowledge distillation → Detection and dense prediction distillation
  49. Agentic AI as a Network Control-Plane Intelligence Layer for Federated Learning over 6GLLM agents and tool use → Agentic AI for wireless networks
  50. Rotation Equivariant Mamba for Vision TasksState-space sequence models (S4, Mamba) → Vision Mamba backbones
  51. AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber OperationsLLM agents and tool use → Agent threats, guardrails and governance
  52. QUSR: Quality-Aware and Uncertainty-Guided Image Super-Resolution Diffusion ModelDiffusion models → Inverse problems and image restoration
  53. DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous ManipulationVision-language-action models → Human-video and latent-action pretraining
  54. Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  55. VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTsMultimodal LLMs / vision-language models → Medical vision-language models
  56. MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive OrchestrationMultimodal LLMs / vision-language models → Medical vision-language models
  57. Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  58. Chain of Event-Centric Causal Thought for Physically Plausible Video GenerationLLM reasoning → Multimodal reasoning
  59. Overcoming Valid Action Suppression in Unmasked Policy Gradient AlgorithmsDeep reinforcement learning methods → Deep RL algorithms and representations
  60. Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open ChallengesWorld models → World models for autonomous driving +2
  61. GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
  62. M2Diff: Multi-Modality Multi-Task Enhanced Diffusion Model for MRI-Guided Low-Dose PET EnhancementDiffusion models → Medical imaging and segmentation
  63. Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  64. EPOCH: An Agentic Protocol for Multi-Round System OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  65. FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource IsolationEfficient LLM inference and serving → Serving systems and request scheduling
  66. Time, Identity and Consciousness in Language Model AgentsLLM agents and tool use → Social simulation and multi-agent debate
  67. Uncertainty, Vagueness, and Ambiguity in Human-Robot Interaction: Why Conceptualization Matters
  68. Facial-Expression-Aware Prompting for Empathetic LLM Tutoring
  69. A Comparative Study on the Impact of Traditional Learning and Interactive Learning on Students' Academic Performance and Emotional Well-Being
  70. Beyond Passive Viewing: A Pilot Study of a Hybrid Learning Platform Augmenting Video Lectures with Conversational AI
  71. Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling
  72. Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity
  73. LLMs for Text-Based Exploration and Navigation Under Partial Observability
  74. From Scalars to Tensors: Declared Losses Recover Epistemic Distinctions That Neutrosophic Scalars Cannot Express
  75. Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent
  76. Algebraic Structure Discovery for Real World Combinatorial Optimisation Problems: A General Framework from Abstract Algebra to Quotient Space Learning
  77. Classifying Problem and Solution Framing in Congressional Social Media
  78. Semantic Shifts of Psychological Concepts in Scientific and Popular Media Discourse: A Distributional Semantics Analysis of Russian-Language Corpora
  79. Are they human? Detecting large language models by probing human memory constraints
  80. ASCAT: An Arabic Scientific Corpus and Benchmark for Advanced Translation Evaluation
  81. Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses
  82. Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager
  83. LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval
  84. Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System
  85. Stability of AI Governance Systems: A Coupled Dynamics Model of Public Trust and Social Disruptions
  86. Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding
  87. Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
  88. Automatic Analysis of Collaboration Through Human Conversational Data Resources: A Review
  89. A Visualization for Comparative Analysis of Regression Models
  90. Privacy and Safety Experiences and Concerns of U.S. Women Using Generative AI for Seeking Sexual and Reproductive Health Information
  91. HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
  92. Quantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake Detection
  93. Quantum Amplitude Estimation for Catastrophe Insurance Tail-Risk Pricing: Empirical Convergence and NISQ Noise Analysis
  94. OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners
  95. A Hierarchical End-of-Turn Model with Primary Speaker Segmentation for Real-Time Conversational AI
  96. Do Large Language Models Get Caught in Hofstadter-Mobius Loops?
  97. Deep Learning for BioImaging: What Are We Really Learning?
  98. A Computer-aided Framework for Detecting Osteosarcoma in Computed Tomography Scans
  99. InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization
  100. Ethical Fairness in Ubiquitous Health Sensing without Known Attributes
  101. Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
  102. VeriHGN: Heterogeneous Graph-Based Congestion Prediction for Chip Layout Verification
  103. OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
  104. TinyNav: End-to-End TinyML for Real-Time Autonomous Navigation on Microcontrollers
  105. From Phase Prediction to Phase Design: A ReAct Agent Framework for High-Entropy Alloy Discovery
  106. Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
  107. Exploring Collatz Dynamics with Human-LLM Collaboration
  108. VCR: Variance-Driven Channel Recalibration for Robust Low-Light Enhancement
  109. GSVD for Geometry-Grounded Dataset Comparison: An Alignment Angle Is All You Need
  110. Estimating Condition Number with Graph Neural Networks
  111. A Robust Deep Learning Framework for Bangla License Plate Recognition Using YOLO and Vision-Language OCR
  112. Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
  113. ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
  114. Joint Imaging-ROI Representation Learning via Cross-View Contrastive Alignment for Brain Disorder Classification
  115. Bayesian Hierarchical Models and the Maximum Entropy Principle
  116. Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing
  117. Learning from Radio using Variational Quantum RF Sensing
  118. One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning
  119. Why Does It Look There? Structured Explanations for Image Classification
  120. S-GRADES -- Studying Generalization of Student Response Assessments in Diverse Evaluative Settings
  121. OilSAM2: Memory-Augmented SAM2 for Scalable SAR Oil Spill Detection
  122. A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method
  123. Robotic Ultrasound Makes CBCT Alive
  124. Multilingual AI-Driven Password Strength Estimation with Similarity-Based Detection
  125. An Automated Radiomics Framework for Postoperative Survival Prediction in Colorectal Liver Metastases using Preoperative MRI
  126. SDSR: A Spectral Divide-and-Conquer Approach for Species Tree Reconstruction
  127. FusionNet: a frame interpolation network for 4D heart models
  128. ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard Translation
  129. Flexible Cutoff Learning: Optimizing Machine Learning Potentials After Training
  130. Variance-Corrected Multi-Asset Equity Simulation with Hybrid Hidden Markov Marginals
  131. Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
  132. ARCHE: Autoregressive Residual Compression with Hyperprior and Excitation
  133. Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem
  134. DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning
  135. ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
  136. Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
  137. A neural operator for predicting vibration frequency response curves from limited data
  138. Social Knowledge for Cross-Domain User Preference Modeling
  139. Lost in Backpropagation: The LM Head is a Gradient Bottleneck
  140. The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory
  141. Unbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering
  142. The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments
  143. HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
  144. 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
  145. Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
  146. Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
  147. Denoising the US Census: Succinct Block Hierarchical Regression
  148. Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts
  149. A Survey of Weight Space Learning: Understanding, Representation, and Generation
  150. ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
  151. Digging Deeper: Learning Multi-Level Concept Hierarchies
  152. Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning
  153. Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
  154. Stochastic Port-Hamiltonian Neural Networks: Universal Approximation with Passivity Guarantees
  155. TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning
  156. Marginals Before Conditionals
  157. Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation
  158. HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
  159. The Epistemic Support-Point Filter: Jaynesian Maximum Entropy Meets Popperian Falsification
  160. Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
  161. CREATE: Testing LLMs for Associative Creativity
  162. Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
  163. Emotional Modulation in Swarm Decision Dynamics
  164. BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
  165. From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding
  166. Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading
  167. On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
  168. Towards a Neural Debugger for Python
  169. The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
  170. No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space
  171. PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
  172. Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand
  173. SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG
  174. Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
  175. Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
  176. Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
  177. Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
  178. On the Structural Failure of Chamfer Distance in 3D Shape Optimization
  179. OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
  180. WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
  181. AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation
  182. Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
  183. MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
  184. LCA: Local Classifier Alignment for Continual Learning
  185. Benchmarking Political Persuasion Risks Across Frontier Large Language Models
  186. DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary
  187. Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning
  188. Do What I Say: A Spoken Prompt Dataset for Instruction-Following
  189. MissBench: Benchmarking Multimodal Affective Analysis under Imbalanced Missing Modalities
  190. N-gram-like Language Models Predict Naturalistic Reading Time Best
  191. CarbonBench: A Global Benchmark for Upscaling of Carbon Fluxes Using Zero-Shot Learning
  192. GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection
  193. A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks
  194. SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases
  195. A Unified Hierarchical Multi-Task Multi-Fidelity Framework for Data-Efficient Surrogate Modeling in Manufacturing
  196. CycleULM: A unified label-free deep learning framework for ultrasound localisation microscopy
  197. MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
  198. BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network Modeling
  199. Correction of Transformer-Based Models with Smoothing Pseudo-Projector
  200. RA-SSU: Towards Fine-Grained Audio-Visual Learning with Region-Aware Sound Source Understanding
  201. MITRA: An AI Assistant for Knowledge Retrieval in Physics Collaborations
  202. Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
  203. Information Theoretic Bayesian Optimization over the Probability Simplex
  204. Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning
  205. A Hybrid Quantum Circuit Born Machine Framework for Financial Volatility Forecasting: Quantum-Assisted Training and Classical Inference
  206. What is Missing? Explaining Neurons Activated by Absent Concepts
  207. EPIC-EuroParl-UdS: Information-Theoretic Perspectives on Translation and Interpreting
  208. First Estimation of Model Parameters for Neutrino-Induced Nucleon Knockout Using Simulation-Based Inference
  209. Global universality via discrete-time signatures
  210. Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
  211. PanoAffordanceNet: Towards Holistic Affordance Grounding in 360deg Indoor Environments
  212. LogoDiffuser: Training-Free Multilingual Logo Generation and Stylization via Letter-Aware Attention Control
  213. Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAG
  214. LAP: A Language-Aware Planning Model For Procedure Planning In Instructional Videos
  215. Upper Generalization Bounds for Neural Oscillators
  216. ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial Scenarios
  217. Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments
  218. M2-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera Inputs
  219. FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video Analysis
  220. A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing System
  221. GSStream: 3D Gaussian Splatting based Volumetric Scene Streaming System
  222. Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
  223. MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
  224. ProGS: Towards Progressive Coding for 3D Gaussian Splatting
  225. TriFusion-SR: Joint Tri-Modal Medical Image Fusion and SR
  226. Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning
  227. TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering
  228. DRIFT: Dual-Representation Inter-Fusion Transformer for Automated Driving Perception with 4D Radar Point Clouds
  229. Physics-informed neural operator for parametric phase-field modelling of interfacial degradation and microstructural evolution
  230. ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling
  231. AutoViVQA: A Large-Scale Automatically Constructed Dataset for Vietnamese Visual Question Answering
  232. Fusing Semantic, Lexical, and Domain Perspectives for Recipe Similarity Estimation
  233. Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health Records
  234. On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning
  235. Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture
  236. Murmurations: a case study in AI-assisted mathematics
  237. Logics-Parsing-Omni Technical Report
  238. GNNs for Time Series Anomaly Detection: An Open-Source Framework and a Critical Evaluation
  239. VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM
  240. DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
  241. No evaluation without fair representation : Impact of label and selection bias on the evaluation, performance and mitigation of classification models
  242. FreqCycle: A Multi-Scale Time-Frequency Analysis Method for Time Series Forecasting
  243. Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
  244. OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive Uncertainty
  245. MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
  246. Well Log-Guided Synthesis of Subsurface Images from Sparse Petrography Data Using cGANs
  247. Noise Models Impacts and Mitigation Strategies in Photonic Quantum Machine Learning
  248. Multi-DNN Inference of Sparse Models on Edge SoCs
  249. Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models
  250. X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting
  251. Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution
  252. Context Engineering: From Prompts to Corporate Multi-Agent Architecture
  253. Surgical Repair of Collapsed Attention Heads in ALiBi Transformers
  254. A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps
  255. ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis
  256. Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis
  257. MM-algorithms for traditional and convex NMF with Tweedie and Negative Binomial cost functions and empirical evaluation
  258. A Variational Latent Equilibrium for Learning in Neuronal Circuits
  259. Build, Borrow, or Just Fine-Tune? A Political Scientist's Guide to Choosing NLP Models
  260. Memorization capacity of deep ReLU neural networks characterized by width and depth
  261. Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
  262. Towards Understanding Adam Convergence on Highly Degenerate Polynomials
  263. Routing without Forgetting
  264. An Optimal Control Approach To Transformer Training
  265. a-TMFG: Scalable Triangulated Maximally Filtered Graphs via Approximate Nearest Neighbors
  266. Learning Bayesian and Markov Networks with an Unreliable Oracle
  267. Compiler-First State Space Duality and Portable O(1) Autoregressive Caching for Inference
  268. A comprehensive study of time-of-flight non-line-of-sight imaging
  269. Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
  270. Enhancing Debunking Effectiveness through LLM-based Personality Adaptation
  271. What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
  272. Association of Progressive PPFE and Mortality in Lung Cancer Screening Cohorts
  273. DCAU-Net: Differential Cross Attention and Channel-Spatial Feature Fusion for Medical Image Segmentation
  274. RESBev: Making BEV Perception More Robust
  275. You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases
  276. TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
  277. Modelling the Diachronic Emergence of Phoneme Frequency Distributions
  278. SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding
  279. Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection
  280. Vibe-Creation: The Epistemology of Human-AI Emergent Cognition
  281. Component-Aware Sketch-to-Image Generation Using Self-Attention Encoding and Coordinate-Preserving Fusion
  282. GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
  283. Telogenesis: Goal Is All U Need
  284. The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions
  285. TopoOR: A Unified Topological Scene Representation for the Operating Room
  286. An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
  287. Declarative Scenario-based Testing with RoadLogic
  288. CyberThreat-Eval: Can Large Language Models Automate Real-World Threat Research?
  289. A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation
  290. GIIM: Graph-based Learning of Inter- and Intra-view Dependencies for Multi-view Medical Image Diagnosis
  291. From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation
  292. Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs
  293. CERES: A Probabilistic Early Warning System for Acute Food Insecurity
  294. Class-Incremental Motion Forecasting
  295. MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updating
  296. CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
  297. Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health
  298. PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue
  299. Reconstructing Movement from Sparse Samples: Enhanced Spatio-Temporal Matching Strategies for Low-Frequency Data
  300. RiO-DETR: DETR for Real-time Oriented Object Detection
  301. YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
  302. ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts
  303. Physics-Informed Neural Engine Sound Modeling with Differentiable Pulse-Train Synthesis
  304. Training-Free Coverless Multi-Image Steganography with Access Control
  305. EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation
  306. SinGeo: Unlock Single Model's Potential for Robust Cross-View Geo-Localization
  307. MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification
  308. Quantifying and extending the coverage of spatial categorization data sets
  309. Flow Field Reconstruction via Voronoi-Enhanced Physics-Informed Neural Networks with End-to-End Sensor Placement Optimization
  310. From Representation to Clusters: A Contrastive Learning Approach for Attributed Hypergraph Clustering
  311. M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition
  312. Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification
  313. Democratising Clinical AI through Dataset Condensation for Classical Clinical Models
  314. SHANG++: Robust Stochastic Acceleration under Multiplicative Noise
  315. Interactive 3D visualization of surface roughness predictions in additive manufacturing: A data-driven framework
  316. TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection
  317. Robust Provably Secure Image Steganography via Latent Iterative Optimization
  318. Predictive Spectral Calibration for Source-Free Test-Time Regression
  319. TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control
  320. Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents
  321. SpaceSense-Bench: A Large-Scale Multi-Modal Benchmark for Spacecraft Perception and Pose Estimation
  322. NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors
  323. CLoE: Expert Consistency Learning for Robust Missing Modality Segmentation
  324. A Gaussian Comparison Theorem for Training Dynamics in Machine Learning
  325. Rescaling Confidence: What Scale Design Reveals About LLM Metacognition
  326. Diagnosing and Repairing Citation Failures in Generative Engine Optimization
  327. DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction
  328. Proxy-Guided Measurement Calibration
  329. Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking
  330. CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation
  331. Learning Convex Decomposition via Feature Fields
  332. From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
  333. Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
  334. On Regret Bounds of Thompson Sampling for Bayesian Optimization
  335. DendroNN: Dendrocentric Neural Networks for Energy-Efficient Classification of Event-Based Data
  336. Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos
  337. Multimodal Graph Representation Learning with Dynamic Information Pathways
  338. Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification
  339. Multi-model approach for autonomous driving: A comprehensive study on traffic sign-, vehicle- and lane detection and behavioral cloning
  340. Efficient Reasoning at Fixed Test-Time Cost via Length-Aware Attention Priors and Gain-Aware Training
  341. A Generative Sampler for distributions with possible discrete parameter based on Reversibility
  342. Bridging Object Detection and Segmentation with Polygon Detection Transformers
  343. When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
  344. BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off
  345. HelixTrack: Event-Based Tracking and RPM Estimation of Propeller-like Objects
  346. StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement
  347. How Contrastive Decoding Enhances Large Audio Language Models
  348. UniField: A Unified Field-Aware MRI Enhancement Framework
  349. Distributed Convolutional Neural Networks for Object Recognition
  350. Embodied Human Simulation for Quantitative Design and Analysis of Interactive Robotics
  351. TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomy
  352. PrivPRISM: Automatically Detecting Discrepancies Between Google Play Data Safety Declarations and Developer Privacy Policies
  353. Geometry-Aware Metric Learning for Cross-Lingual Few-Shot Sign Language Recognition on Static Hand Keypoints
  354. Abundant Intelligence and Deficient Demand: A Macro-Financial Stress Test of Rapid AI Adoption
  355. Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
  356. The Radio-Frequency Transformer for Signal Separation
  357. P2GNN: Two Prototype Sets to boost GNN Performance
  358. The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN
  359. DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
  360. Differentiable Stochastic Traffic Dynamics: Physics-Informed Generative Modelling in Transportation
  361. Reinforced Generation of Combinatorial Structures: Ramsey Numbers
  362. ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data
  363. Better Bounds for the Distributed Experts Problem
  364. GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
  365. POLISH'ing the Sky: Wide-Field and High-Dynamic Range Interferometric Image Reconstruction with Application to Strong Lens Discovery
  366. Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL
  367. Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety
  368. Deep Tabular Research via Continual Experience-Driven Execution
  369. Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning
  370. Transformer-Based Multi-Region Segmentation and Radiomic Analysis of HR-pQCT Imaging for Osteoporosis Classification
  371. Collective AI can amplify tiny perturbations into divergent decisions
  372. PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings
  373. Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities
  374. Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations
  375. Training-free Motion Factorization for Compositional Video Generation
  376. Probabilistic Hysteresis Factor Prediction for Electric Vehicle Batteries with Graphite Anodes Containing Silicon
  377. Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting
  378. SyncEdit: Rethinking Lip Synchronization as Editing with Audio-Driven Diffusion Models
  379. PPO-Based Hybrid Optimization for RIS-Assisted Semantic Vehicular Edge Computing
  380. Exclusive Self Attention
  381. A Text-Native Interface for Generative Video Authoring
  382. Intelligent Spatial Estimation for Fire Hazards in Engineering Sites: An Enhanced YOLOv8-Powered Proximity Analysis Framework
  383. Verifying Good Regulator Conditions for Hypergraph Observers: Natural Gradient Learning from Causal Invariance via Established Theorems
  384. Learning Adaptive LLM Decoding
  385. Dynamic Multi-period Experts for Online Time Series Forecasting
  386. Adaptive Active Learning for Online Reliability Prediction of Satellite Electronics
  387. Spectral-Structured Diffusion for Single-Image Rain Removal
  388. Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation
  389. From Days to Minutes: An Autonomous AI Agent Achieves Reliable Clinical Triage in Remote Patient Monitoring
  390. WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion
  391. SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding
  392. Two Teachers Better Than One: Hardware-Physics Co-Guided Distributed Scientific Machine Learning