mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 23 Sep 2025

440 papers

  1. Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents (Extended Revision: From Behavioral Architecture to Epistemic Accountability)LLM agents and tool use → General LLM agent frameworks and benchmarks
  2. GRPO++: Enhancing Dermatological Reasoning under Low Resource SettingsLLM reasoning → Clinical and biomedical applications +1
  3. Automated Extraction of Material Properties using LLM-based AI AgentsLLM agents and tool use → Medical and scientific domain agents
  4. Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based SupervisionSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  5. Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AIMechanistic interpretability → Probing deception, bias and beliefs
  6. GZSL-MoE: Apprentissage G'en'eralis'e Z'ero-Shot bas'e sur le M'elange d'Experts pour la Segmentation S'emantique de Nuages de Points 3DAppliqu'e `a un Jeu de Donn'ees d'Environnement de Collaboration Humain-RobotMixture-of-experts → Vision mixture-of-experts
  7. Metadata-Guided Adaptable Frequency Scaling across Heterogeneous Applications and DevicesDeep reinforcement learning methods → RL for energy, networks and operations
  8. SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse AutoencodersDiffusion models → Robustness, privacy and adversarial aspects +2
  9. Are We Scaling the Right Thing? A System Perspective on Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  10. AutoSpec: An Agentic Framework for Automatically Drafting Patent SpecificationLLM agents and tool use → Web, search, and research agents
  11. TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series GenerationDiffusion models → Flow matching, time series and science
  12. Mamba Modulation: On the Length Generalization of MambaState-space sequence models (S4, Mamba) → Core SSM architectures for language
  13. Advancing Speech Summarization in Multi-modal LLMs with Reinforcement LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Multimodal Language Models with Modality-Specific Experts for Financial Forecasting from Interleaved Sequences of Text and Time SeriesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  15. EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human DataOffline RL and imitation learning from data → Robot manipulation imitation learning
  16. SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  17. Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language ModelsMultimodal LLMs / vision-language models → Multimodal emotion understanding
  18. Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  19. Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot ActionLLM agents and tool use → Multimodal and embodied agents
  20. Retrieval Augmented Generation based context discovery for ASRRetrieval-augmented generation → Conversational and speech RAG
  21. Nano Bio-Agents (NBA): Small Language Model Agents for GenomicsLLM agents and tool use → Medical and scientific domain agents
  22. CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition SystemsLLM safety and security → Machine unlearning
  23. AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent SpaceWorld models → Latent dynamics models and model-based RL
  24. iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video ReasoningLLM reasoning → Chain-of-thought reasoning for driving
  25. DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred TransitionsWorld models → Latent dynamics models and model-based RL +1
  26. Semantic-Aware Fuzzing: An Empirical Framework for LLM-Guided, Reasoning-Driven Input MutationLLM reasoning → Reasoning for agents, planning and code
  27. Metriplectic Conditional Flow Matching for Dissipative DynamicsDiffusion models → Flow matching, time series and science
  28. Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft RobotDeep reinforcement learning methods → RL for robot locomotion and manipulation
  29. Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  30. STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured DatabasesLLM reasoning → Knowledge- and tool-augmented reasoning
  31. Frame-based Equivariant Diffusion Models for 3D Molecular GenerationDiffusion models → Flow matching, time series and science
  32. Estimating the Self-Consistency of LLMsLLM reasoning → Test-time compute and efficient thinking
  33. OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot NavigationVision-language-action models → Generalist VLA models and benchmarks
  34. Evaluation-Aware Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  35. Self-evolved Imitation Learning in Simulated WorldOffline RL and imitation learning from data → Imitation learning methods
  36. ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data AugmentationOffline RL and imitation learning from data → Robot manipulation imitation learning
  37. CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow MatchingDiffusion models → Flow matching, time series and science
  38. Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-DistillationDiffusion models → 3D, point cloud and scene generation
  39. What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoTLLM reasoning → Prompting and chain-of-thought reasoning
  40. A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion ModelsDiffusion models → Inverse problems and image restoration
  41. Policy Gradient Bounds in Multitask LQRDeep reinforcement learning methods → RL for games and combinatorial optimization
  42. Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab WorldLLM reasoning → Reasoning benchmarks and evaluation
  43. Reinforcement Learning on Pre-Training DataDeep reinforcement learning methods → RL training of language and agent models
  44. Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and GenerationDiffusion models → Image generation, text-to-image and editing
  45. AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  46. CompLLM: Compression for Long Context Q&AEfficient LLM inference and serving → Prompt and context compression
  47. PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model DistillationKnowledge distillation → Distillation for medical imaging
  48. Steering Multimodal Large Language Models Decoding for Context-Aware SafetyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  49. A Knowledge Graph and a Tripartite Evaluation Framework Make Retrieval-Augmented Generation Scalable and TransparentRetrieval-augmented generation → RAG pipeline design and evaluation
  50. Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  51. Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene DescriptionsLLM reasoning → Multimodal reasoning +1
  52. Agentic Reinforcement Learning with Implicit Step RewardsLLM agents and tool use → Reinforcement learning for LLM agents +1
  53. Reading Images Like Texts: Sequential Image Understanding in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  54. An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic ApplicationsLLM agents and tool use → Software engineering coding agents
  55. Soft Tokens, Hard TruthsLLM reasoning → Prompting and chain-of-thought reasoning
  56. Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation FunctionsDeep reinforcement learning methods → Deep RL algorithms and representations
  57. NeuCODEX: Edge-Cloud Co-Inference with Spike-Driven Compression and Dynamic Early-ExitEfficient LLM inference and serving → Early exit and edge inference
  58. Anecdoctoring: Automated Red-Teaming Across Language and PlaceLLM safety and security → Prompt injection and agent security
  59. On the Soundness and Consistency of LLM Agents for Executing Test Cases Written in Natural LanguageLLM agents and tool use → Software engineering coding agents
  60. PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence GenerationLLM reasoning → Reinforcement learning for reasoning +1
  61. A Fast Initialization Method for Neural Network Controllers: A Case Study of Image-based Visual Servoing Control for the multicopter InterceptionDeep reinforcement learning methods → RL theory and sample complexity
  62. Online Distributionally Robust LLM Alignment via Regression to Relative RewardLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  63. Investigating Traffic Accident Detection Using Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  64. Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question AnsweringLLM reasoning → Reinforcement learning for reasoning
  65. Training Flow Matching Models with Reliable Labels via Self-PurificationDiffusion models → Audio, speech and music
  66. World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic ManipulationWorld models → Embodied and robot world models +3
  67. ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  68. ManipForce: Force-Guided Policy Learning with Frequency-Aware Representation for Contact-Rich ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  69. Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box AttacksDiffusion models → Robustness, privacy and adversarial aspects
  70. Reduced-Order Model-Guided Reinforcement Learning for Demonstration-Free Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  71. Investigating Test-Time Scaling with Reranking for Machine TranslationLLM reasoning → Test-time compute and efficient thinking
  72. OmniBridge: Unified Multimodal Understanding, Generation, and Retrieval via Latent Space AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  73. Fully Learnable Neural Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
  74. Pure Vision Language Action (VLA) Models: A Comprehensive SurveyMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  75. Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained RewardsLLM reasoning → Multimodal reasoning +2
  76. VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary ReconstructionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  77. LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and DirectionsLLM agents and tool use → Medical and scientific domain agents
  78. Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical VariationsVision-language-action models → Safety and adversarial attacks
  79. One-shot Embroidery Customization via Contrastive LoRA ModulationDiffusion models → 3D, point cloud and scene generation
  80. Direct Preference Optimization for Speech Autoregressive Diffusion ModelsDiffusion models → Audio, speech and music
  81. LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic ModelsDiffusion models → 3D, point cloud and scene generation
  82. How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven PerspectiveLLM reasoning → Spatial and embodied reasoning
  83. Introducing LongCat-Flash-Thinking: A Technical ReportLLM reasoning → Reinforcement learning for reasoning +2
  84. On The Reproducibility Limitations of RAG SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  85. Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action GenerationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  86. Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User ProfilingLLM reasoning → Reinforcement learning for reasoning
  87. NGRPO: Negative-enhanced Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  88. MAPO: Mixed Advantage Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  89. Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool InteractionsLLM agents and tool use → Tool learning and function calling
  90. Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian IconographyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  91. Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA AdaptersDiffusion models → Image generation, text-to-image and editing
  92. On the Convergence of Policy Mirror Descent with Temporal Difference EvaluationDeep reinforcement learning methods → RL theory and sample complexity
  93. MAPEX: A Multi-Agent Pipeline for Keyphrase ExtractionLLM agents and tool use → Web, search, and research agents
  94. Towards Application Aligned Synthetic Surgical Image SynthesisDiffusion models → Medical imaging and segmentation
  95. The AGNTCY Agent Directory Service: Architecture and ImplementationLLM agents and tool use → Agent threats, guardrails and governance
  96. VGGT-DP: Generalizable Robot Control via Vision Foundation ModelsOffline RL and imitation learning from data → Robot manipulation imitation learning
  97. Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  98. FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score DistillationDiffusion models → 3D, point cloud and scene generation
  99. MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  100. Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
All 440
  1. Knowledge Transfer from Interaction LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk DetectionSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  3. Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and AlignmentLLM safety and security → Backdoor and data poisoning attacks
  4. MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer ServiceLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Autonomous Data Agents: A New Opportunity for Smart DataLLM agents and tool use → Web, search, and research agents
  6. MVT: Mask-Grounded Vision-Language Models for Taxonomy-Aligned Land-Cover TaggingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  7. An overview of neural architectures for self-supervised audio representation learning from masked spectrogramsState-space sequence models (S4, Mamba) → Speech and audio SSMs
  8. Query-Centric Diffusion Policy for Generalizable Robotic AssemblyDiffusion models → Diffusion and flow policies for robotics
  9. LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  10. 3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D SpaceDiffusion models → Diffusion and flow policies for robotics
  11. TERAG: Token-Efficient Graph-Based Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  12. Agentic AutoSurvey: Let LLMs Survey LLMsLLM agents and tool use → Web, search, and research agents
  13. SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real TransferDeep reinforcement learning methods → Safe and constrained RL
  14. Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into GenerationLLM reasoning → Multimodal reasoning
  15. A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps UsersLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  16. Prompt-Guided Dual Latent Steering for Inversion ProblemsDiffusion models → Inverse problems and image restoration
  17. Flow marching for a generative PDE foundation modelDiffusion models → Flow matching, time series and science
  18. SINGER: An Onboard Generalist Vision-Language Navigation Policy for DronesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  19. PIE: Perception and Interaction Enhanced End-to-End Motion Planning for Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture +1
  20. SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample FilteringDiffusion models → Audio, speech and music
  21. Training-Free Multi-Style Fusion Through Reference-Based Adaptive ModulationDiffusion models → Image generation, text-to-image and editing
  22. Growing with Your Embodied Agent: A Human-in-the-Loop Lifelong Code Generation Framework for Long-Horizon Manipulation SkillsLLM agents and tool use → Multimodal and embodied agents
  23. DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series GenerationDiffusion models → Flow matching, time series and science
  24. The Photographer Eye: Teaching Multimodal Large Language Models to Understand Image Aesthetics like PhotographersMultimodal LLMs / vision-language models → Image editing and quality assessment
  25. Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise DistillationLLM reasoning → Audio-language model reasoning +1
  26. Live-E2T: Real-time Threat Monitoring in Video via Deduplicated Event Reasoning and Chain-of-ThoughtLLM reasoning → Multimodal reasoning
  27. LLMZ+: Contextual Prompt Whitelist Principles for Agentic LLMsLLM agents and tool use → Agent threats, guardrails and governance +1
  28. Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-ExpertsMixture-of-experts → MoE theory and gating functions
  29. CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMsLLM reasoning → Reasoning benchmarks and evaluation
  30. No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTSLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  31. APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail GenerationDeep reinforcement learning methods → RL training of language and agent models
  32. Spatial Envelope MPC: High Performance Driving without a ReferenceEnd-to-end autonomous driving → Reinforcement learning for driving
  33. SimpleFold: Folding Proteins is Simpler than You ThinkDiffusion models → Flow matching, time series and science
  34. A Modality-Aware Cooperative Co-Evolutionary Framework for Multimodal Graph Neural Architecture Search
  35. Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis
  36. Silent Tokens, Loud Effects: Padding in LLMs
  37. Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation
  38. LLMRank: Understanding LLM Strengths for Model Routing
  39. Computational Social Linguistics for Telugu Cultural Preservation: Novel Algorithms for Chandassu Metrical Pattern Recognition
  40. Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
  41. Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models
  42. Geometric Structures and Patterns of Meaning: A PHATE Manifold Analysis of Chinese Character Embeddings
  43. Who is In Charge? Dissecting Role Conflicts in Instruction Following
  44. EEFSUVA: A New Mathematical Olympiad Benchmark
  45. Challenges and Solutions in Selecting Optimal Lossless Data Compression Algorithms
  46. Localizing Adversarial Attacks To Produces More Imperceptible Noise
  47. TUN3D: Towards Real-World Scene Understanding from Unposed Images
  48. Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
  49. ShipwreckFinder: A QGIS Tool for Shipwreck Detection in Multibeam Sonar Data
  50. Debugging Concept Bottleneck Models through Removal and Retraining
  51. Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal
  52. The LongiMam model for improved breast cancer risk prediction using longitudinal mammograms
  53. Toward a Realistic Encoding Model of Auditory Affective Understanding in the Brain
  54. Coreset selection based on Intra-class diversity
  55. Dynamic Multi-Target Fusion for Efficient Audio-Visual Navigation
  56. In silico Deep Learning Protocols for Label-Free Super-Resolution Microscopy: A Comparative Study of Network Architectures and SNR Dependence
  57. Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
  58. Sample completion, structured correlation, and Netflix problems
  59. SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
  60. Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
  61. Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
  62. Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling
  63. Centralized vs. Decentralized Security for Space AI Systems? A New Look
  64. Blueprints of Trust: AI System Cards for End to End Transparency and Governance
  65. The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind
  66. A Comparative Analysis of Ensemble-Based Machine Learning Approaches with Explainable AI for Multi-Class Intrusion Detection in Drone Networks
  67. Dynamicasome: a molecular dynamics-guided and AI-driven pathogenicity prediction catalogue for all genetic mutations
  68. Where 6G Stands Today: Evolution, Enablers, and Research Gaps
  69. The Impact of 2D Segmentation Backbones on Point Cloud Predictions Using 4D Radar
  70. Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Making
  71. Adaptive von Mises-Fisher Likelihood Loss for Supervised Deep Time Series Hashing
  72. Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG
  73. Evaluating Language Translation Models by Playing Telephone
  74. Graph-based Neural Space Weather Forecasting
  75. Improved Therapeutic Antibody Reformatting through Multimodal Machine Learning
  76. Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
  77. Learning Genetic Circuit Modules with Neural Networks: Full Version
  78. Knowledge Base-Aware Orchestration: A Dynamic, Privacy-Preserving Method for Multi-Agent Systems
  79. GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
  80. Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation
  81. Position: AI Evaluations Should be Grounded on a Theory of Capability
  82. Synthesizing Artifact Dataset for Pixel-level Detection
  83. Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models
  84. Reverse Engineering User Stories from Code using Large Language Models
  85. A Foundation Chemical Language Model for Comprehensive Fragment-Based Drug Discovery
  86. LLMs4All: A Review of Large Language Models Across Academic Disciplines
  87. MAGIC: Multi-task Gaussian process for joint imputation and classification in healthcare time series
  88. ExPe: Exact Positional Encodings for Generative Transformer Models with Extrapolating Capabilities
  89. Uncertainty in Semantic Language Modeling with PIXELS
  90. Stochastic Path Planning in Correlated Obstacle Fields
  91. Confidence Calibration in Large Language Model-Based Entity Matching
  92. Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks
  93. Do LLMs Encode Frame Semantics? Evidence from Frame Identification
  94. Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
  95. A Longitudinal Randomized Control Study of Companion Chatbot Use: Anthropomorphism and Its Mediating Role on Social Impacts
  96. The Heterogeneous Multi-Agent Challenge
  97. AIRwaves at CheckThat! 2025: Retrieving Scientific Sources for Implicit Claims on Social Media with Dual Encoders and Neural Re-Ranking
  98. Constraint-Reduced MILP with Local Outlier Factor Modeling for Plausible Counterfactual Explanations in Credit Approval
  99. Generative AI as a catalyst for democratic Innovation: Enhancing citizen engagement in participatory budgeting
  100. ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancement
  101. Chiseling: Powerful and Valid Subgroup Selection via Interactive Machine Learning
  102. Identifying and Addressing User-level Security Concerns in Smart Homes Using "Smaller" LLMs
  103. A Pipeline to Assess Merging Methods via Behavior and Internals
  104. Quantum Harmonic Analysis and the Structure in Data: Augmentation
  105. Transformer Modeling for Both Scalability and Performance in Multivariate Time Series
  106. THINNs: Thermodynamically Informed Neural Networks
  107. A More Realistic Evaluation of Cross-Frequency Transfer Learning and Foundation Forecasting Models
  108. The Indispensable Role of User Simulation in the Pursuit of AGI
  109. Anchored Langevin Algorithms
  110. The Platonic Universe: Do Foundation Models See the Same Sky?
  111. HUNT: High-Speed UAV Navigation and Tracking in Unstructured Environments via Instantaneous Relative Frames
  112. The Pareto Frontier of Resilient Jet Tagging
  113. Probabilistic Runtime Verification, Evaluation and Risk Assessment of Visual Deep Learning Systems
  114. Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
  115. EngravingGNN: A Hybrid Graph Neural Network for End-to-End Piano Score Engraving
  116. Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database
  117. Enhancing Credit Default Prediction Using Boruta Feature Selection and DBSCAN Algorithm with Different Resampling Techniques
  118. TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding
  119. Improving Outdoor Multi-cell Fingerprinting-based Positioning via Mobile Data Augmentation
  120. Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
  121. Overview of LifeCLEF Plant Identification task 2020
  122. SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs
  123. FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks
  124. Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG
  125. OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC
  126. Residual Off-Policy RL for Finetuning Behavior Cloning Policies
  127. VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
  128. Audio-Based Pedestrian Detection in the Presence of Vehicular Noise
  129. SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
  130. OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
  131. MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI
  132. DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture
  133. WolBanking77: Wolof Banking Speech Intent Classification Dataset
  134. SloPal: A 60-Million-Word Slovak Parliamentary Corpus with Aligned Speech and Fine-Tuned ASR Models
  135. Extracting Conceptual Spaces from LLMs Using Prototype Embeddings
  136. Discovering strategies for coastal resilience with AI-based prediction and optimization
  137. Moving by Looking: Towards Vision-Driven Avatar Motion Generation
  138. Graph-Radiomic Learning (GrRAiL) Descriptor to Characterize Imaging Heterogeneity in Confounding Tumor Pathologies
  139. Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps
  140. Recovering Wasserstein Distance Matrices from Few Measurements
  141. ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
  142. Linear Regression under Missing or Corrupted Coordinates
  143. Stability and Generalization of Adversarial Diffusion Training
  144. Study Design and Demystification of Physics Informed Neural Networks for Power Flow Simulation
  145. Finding My Voice: Generative Reconstruction of Disordered Speech for Automated Clinical Evaluation
  146. DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces
  147. MsFIN: Multi-scale Feature Interaction Network for Traffic Accident Anticipation
  148. Neighbor Embeddings Using Unbalanced Optimal Transport Metrics
  149. Systematic Comparative Analysis of Large Pretrained Language Models on Contextualized Medication Event Extraction
  150. Video Killed the Energy Budget: Characterizing the Latency and Power Regimes of Open Text-to-Video Models
  151. FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity
  152. HyKid: An Open MRI Dataset with Expert-Annotated Multi-Structure and Choroid Plexus in Pediatric Hydrocephalus
  153. Enabling Plant Phenotyping in Weedy Environments using Multi-Modal Imagery via Synthetic and Generated Training Data
  154. Parameter Space Analysis through Guided Visual Interpolations
  155. A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
  156. Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules
  157. The 1st Solution for MOSEv2 Challenge 2025: Long-term and Concept-aware Video Segmentation via SeC
  158. YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery
  159. YOLO-LAN: Precise Polyp Detection via Optimized Loss, Augmentations and Negatives
  160. RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions
  161. Measuring AI "Slop" in Text
  162. CayleyPy Growth: Efficient growth computations and hundreds of new conjectures on Cayley graphs (Brief version)
  163. Realizable Circuit Complexity: Embedding Computation in Space-Time
  164. LLMs as verification oracles for Solidity
  165. Generative Propaganda
  166. GSTM-HMU: Generative Spatio-Temporal Modeling for Human Mobility Understanding
  167. KAMERA: Enhancing Aerial Surveys of Ice-associated Seals in Arctic Environments
  168. Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering
  169. Analysis on distribution and clustering of weight
  170. FedFiTS: Fitness-Selected, Slotted Client Scheduling for Trustworthy Federated Learning in Healthcare AI
  171. LLM-based Vulnerability Discovery through the Lens of Code Metrics
  172. Track-On2: Enhancing Online Point Tracking with Memory
  173. Towards Practical Multi-label Causal Discovery in High-Dimensional Event Sequences via One-Shot Graph Aggregation
  174. Human-Annotated NER Dataset for the Kyrgyz Language
  175. Are most sentences unique? An empirical examination of Chomskyan claims
  176. FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation
  177. Algorithms for Adversarially Robust Deep Learning
  178. Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning
  179. Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning
  180. Digital Twins as Funhouse Mirrors: Five Key Distortions
  181. Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications
  182. Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
  183. Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference
  184. Diffusion Bridge Variational Inference for Deep Gaussian Processes
  185. Code Driven Planning with Domain-Adaptive Critic
  186. WaveletGaussian: Wavelet-domain Diffusion for Sparse-view 3D Gaussian Object Reconstruction
  187. Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training
  188. Towards Causal Representation Learning with Observable Sources as Auxiliaries
  189. A DyL-Unet framework based on dynamic learning for Temporally Consistent Echocardiographic Segmentation
  190. Charting a Decade of Computational Linguistics in Italy: The CLiC-it Corpus
  191. Improving Credit Card Fraud Detection through Transformer-Enhanced GAN Oversampling
  192. Landmarks, Monuments, and Beacons: Understanding Generative Calls to Action
  193. Clapping: Removing Per-sample Storage for Pipeline Parallel Distributed Optimization with Communication Compression
  194. Weakly Supervised Food Image Segmentation using Vision Transformers and Segment Anything Model
  195. Minimum Bisection Problem: Machine Learning-Based Penalty Parameter Tuning for Optimization on Quantum Annealers
  196. Bayesian Calibration and Model Assessment of Cell Migration Dynamics with Surrogate Model Integration
  197. Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization
  198. CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
  199. Learning From Simulators: A Theory of Simulation-Grounded Learning
  200. DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment
  201. Remaining Time Prediction in Outbound Warehouse Processes: A Case Study (Short Paper)
  202. From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system
  203. Category-Level Object Shape and Pose Estimation in Less Than a Millisecond
  204. Prompt-DAS: Annotation-Efficient Prompt Learning for Domain Adaptive Semantic Segmentation of Electron Microscopy Images
  205. Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding
  206. Central Limit Theorems for Asynchronous Averaged Q-Learning
  207. Lift What You Can: Green Online Learning with Heterogeneous Ensembles
  208. Generative data augmentation for biliary tract detection on intraoperative images
  209. Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting
  210. Towards Robust LiDAR Localization: Deep Learning-based Uncertainty Estimation
  211. Towards Privacy-Aware Bayesian Networks: A Credal Approach
  212. Quantum Random Synthetic Skyrmion Texture Generation, a Qiskit Simulation
  213. Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
  214. No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning
  215. Accurate and Efficient Prediction of Wi-Fi Link Quality Based on Machine Learning
  216. Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
  217. SynapFlow: A Modular Framework Towards Large-Scale Analysis of Dendritic Spines
  218. Audio-Driven Universal Gaussian Head Avatars
  219. Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset
  220. xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision
  221. Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation
  222. Moir'eNet: A Compact Dual-Domain Network for Image Demoir'eing
  223. Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks
  224. Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  225. Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass
  226. The AI Literacy Heptagon: A Structured Approach to AI Literacy in Higher Education
  227. DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring
  228. RS3DBench: A Comprehensive Benchmark for 3D Spatial Perception in Remote Sensing
  229. SmartWilds: Multimodal Wildlife Monitoring Dataset
  230. Exploring Heterophily in Graph-level Tasks
  231. Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model
  232. Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
  233. Diversity Boosts AI-Generated Text Detection
  234. When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
  235. Memory in Large Language Models: Mechanisms, Evaluation and Evolution
  236. Multi-Hierarchical Feature Detection for Large Language Model Generated Text
  237. Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning
  238. Are Smaller Open-Weight LLMs Closing the Gap to Proprietary Models for Biomedical Question Answering?
  239. Shared-Weights Extender and Gradient Voting for Neural Network Expansion
  240. ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
  241. Bounded PCTL Model Checking of Large Language Model Outputs
  242. DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation
  243. Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective
  244. Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
  245. Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models
  246. Training-Free Data Assimilation with GenCast
  247. Probabilistic Machine Learning for Uncertainty-Aware Diagnosis of Industrial Systems
  248. Surgical Video Understanding with Label Interpolation
  249. A Kernel Space-based Multidimensional Sparse Model for Dynamic PET Image Denoising
  250. Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
  251. Detection of security smells in IaC scripts through semantics-aware code and language processing
  252. Human-Interpretable Uncertainty Explanations for Point Cloud Registration
  253. Reconstruction of Optical Coherence Tomography Images from Wavelength-space Using Deep-learning
  254. Real-time Deer Detection and Warning in Connected Vehicles via Thermal Sensing and Deep Learning
  255. AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field
  256. Financial Risk Relation Identification through Dual-view Adaptation
  257. Experience Scaling: Post-Deployment Evolution For Large Language Models
  258. Diagonal Linear Networks and the Lasso Regularization Path
  259. DiSSECT: Structuring Transfer-Ready Medical Image Representations through Discrete Self-Supervision
  260. When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models
  261. Security smells in infrastructure as code: a taxonomy update beyond the seven sins
  262. Complexity of Activity Patterns in a Bio-Inspired Hopfield-Type Network in Different Topologies
  263. COLT: Enhancing Video Large Language Models with Continual Tool Usage
  264. Patch-based Memory Gate Model in Time Series Foundation Model
  265. False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
  266. Theory of periodic convolutional neural network
  267. TriFusion-AE: Language-Guided Depth and LiDAR Fusion for Robust Point Cloud Processing
  268. Consistency of Selection Strategies for Fraud Detection
  269. HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection
  270. LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR
  271. What Makes You Unique? Attribute Prompt Composition for Object Re-Identification
  272. A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications
  273. RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images
  274. Learning When to Restart: Nonstationary Newsvendor from Uncensored to Censored Demand
  275. Overview of LifeCLEF Plant Identification task 2019: diving into data deficient tropical countries
  276. Towards Rational Pesticide Design with Graph Machine Learning Models for Ecotoxicology
  277. AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping
  278. Overview of PlantCLEF 2021: cross-domain plant identification
  279. Lightweight Vision Transformer with Window and Spatial Attention for Food Image Classification
  280. Advances in Large Language Models for Medicine
  281. Implementation of airborne ML models with semantics preservation
  282. Scalable bayesian shadow tomography for quantum property estimation with set transformers
  283. NaviSense: A Multimodal Assistive Mobile application for Object Retrieval by Persons with Visual Impairment
  284. Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction
  285. Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering
  286. Online Learning for Optimizing AoI-Energy Tradeoff under Unknown Channel Statistics
  287. Subspace Clustering of Subspaces: Unifying Canonical Correlation Analysis and Subspace Clustering
  288. Do You Need Proprioceptive States in Visuomotor Policies?
  289. Zero-shot Monocular Metric Depth for Endoscopic Images
  290. Learning neuroimaging models from health system-scale data
  291. Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
  292. HyperAdapt: Simple High-Rank Adaptation
  293. BRAID: Input-Driven Nonlinear Dynamical Modeling of Neural-Behavioral Data
  294. The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving
  295. MLF-4DRCNet: Multi-Level Fusion with 4D Radar and Camera for 3D Object Detection in Autonomous Driving
  296. End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learning
  297. Reflect before Act: Proactive Error Correction in Language Models
  298. FlexSED: Towards Open-Vocabulary Sound Event Detection
  299. OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
  300. SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution
  301. VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation
  302. Enhancing Video Object Segmentation in TrackRAD Using XMem Memory Network
  303. UniECG: Understanding and Generating ECG in One Unified Model
  304. TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning
  305. Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity
  306. LCMF: Lightweight Cross-Modality Mambaformer for Embodied Robotics VQA
  307. The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
  308. Interaction Topological Transformer for Multiscale Learning in Porous Materials
  309. HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modeling
  310. Explore the Reinforcement Learning for the LLM based ASR and TTS system
  311. Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia
  312. Event-guided 3D Gaussian Splatting for Dynamic Human and Scene Reconstruction
  313. Solving Math Word Problems Using Estimation Verification and Equation Generation
  314. CPCLDETECTOR: Knowledge Enhancement and Alignment Selection for Chinese Patronizing and Condescending Language Detection
  315. SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes
  316. Efficient Breast and Ovarian Cancer Classification via ViT-Based Preprocessing and Transfer Learning
  317. Global Minimizers of Sigmoid Contrastive Loss
  318. HadaSmileNet: Hadamard fusion of handcrafted and deep-learning features for enhancing facial emotion recognition of genuine smiles
  319. SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models
  320. GeoRemover: Removing Objects and Their Causal Visual Artifacts
  321. Trace Is In Sentences: Unbiased Lightweight ChatGPT-Generated Text Detector
  322. Re-uploading quantum data: a universal function approximator for quantum inputs
  323. Reverse-Complement Consistency for DNA Language Models
  324. FERA: A Pose-Based Framework for Rule-Grounded Multimedia Decision Support with a Foil Fencing Case Study
  325. Automatic coherence-driven inference on arguments
  326. Coherence-driven inference for cybersecurity
  327. A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition
  328. Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data
  329. Hyperbolic Coarse-to-Fine Few-Shot Class-Incremental Learning
  330. Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment
  331. BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
  332. Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models
  333. Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction
  334. Enhanced Survival Trees
  335. MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation
  336. Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
  337. Estimating Heterogeneous Causal Effect on Networks via Orthogonal Learning
  338. Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints
  339. Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems
  340. Machine learning approach to single-shot multiparameter estimation for the non-linear Schr"odinger equation