mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 11 Jun 2025

411 papers

  1. Can LLMs Reason About Trust?: A Pilot StudyLLM reasoning → Reasoning benchmarks and evaluation
  2. Integrating Universal Generative AI Platforms in Educational Labs to Foster Critical Thinking and Digital LiteracyLLM reasoning → Reasoning benchmarks and evaluation
  3. MVGBench: Comprehensive Benchmark for Multi-view Generation ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  4. Reinforcement learning fine-tuning of language model for instruction following and math reasoningLLM reasoning → Reinforcement learning for reasoning +1
  5. Bench to the Future: A Pastcasting Benchmark for Forecasting AgentsLLM agents and tool use → Financial trading and forecasting agents
  6. Debunk and Infer: Multimodal Fake News Detection via Diffusion-Generated Evidence and LLM ReasoningLLM reasoning → Multimodal reasoning
  7. VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented GenerationLLM reasoning → Multimodal reasoning +2
  8. ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment FrameworkSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  9. SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-RefineLLM reasoning → Reasoning for agents, planning and code
  10. CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error ScenariosLLM agents and tool use → Tool learning and function calling
  11. Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained ReflectionLLM reasoning → Clinical and biomedical applications
  12. Meta-Learning and Synthetic Data for Automated Pretraining and FinetuningSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  13. Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language ReasoningLLM reasoning → Clinical and biomedical applications
  14. Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree SearchMultimodal LLMs / vision-language models → Video understanding with MLLMs
  15. ADAgent: LLM Agent for Alzheimer's Disease Analysis with Collaborative CoordinatorLLM agents and tool use → Medical and scientific domain agents
  16. AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human AnimationDiffusion models → Video generation +1
  17. Autonomous Computer Vision Development with Agentic AILLM agents and tool use → Medical and scientific domain agents
  18. Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning MethodsLLM safety and security → Machine unlearning
  19. LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology GenerationMechanistic interpretability → Circuits and mechanistic analysis
  20. Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationDiffusion models → Medical imaging and segmentation
  21. Leveraging Clinical Text and Class Conditioning for 3D Prostate MRI GenerationDiffusion models → Medical imaging and segmentation
  22. ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves RecognitionDiffusion models → Image generation, text-to-image and editing +1
  23. TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style GamesLLM reasoning → Reasoning for agents, planning and code
  24. Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video RetrievalMultimodal LLMs / vision-language models → Video understanding with MLLMs
  25. Scalable Non-Equivariant 3D Molecule Generation via Rotational AlignmentDiffusion models → Flow matching, time series and science
  26. Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative ModelsDiffusion models → Diffusion foundations and sampling
  27. AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat AttributionRetrieval-augmented generation → Privacy and security of RAG +1
  28. SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE ScoreDiffusion models → Image generation, text-to-image and editing
  29. A Navigation Framework Utilizing Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  30. Beyond Jailbreaking: Auditing Contextual Privacy in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  31. Wasserstein Barycenter Soft Actor-CriticDeep reinforcement learning methods → RL theory and sample complexity
  32. One Patient, Many Contexts: Scaling Medical AI with Contextual IntelligenceMultimodal LLMs / vision-language models → Medical vision-language models
  33. Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flowsDeep reinforcement learning methods → RL with diffusion and flow models
  34. RoCA: Robust Cross-Domain End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  35. Diffusion prior as a direct regularization term for FWIDiffusion models → Flow matching, time series and science
  36. Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNNDeep reinforcement learning methods → Deep RL algorithms and representations
  37. Self-Predictive Representations for Combinatorial Generalization in Behavioral CloningOffline RL and imitation learning from data → Imitation learning methods
  38. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMsLLM reasoning → Multimodal reasoning
  39. ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question AnsweringLLM reasoning → Multimodal reasoning
  40. NnD: Diffusion-based Generation of Physically-Nonnegative ObjectsDiffusion models → 3D, point cloud and scene generation
  41. EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation +1
  42. Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific InformationLLM reasoning → Reasoning for agents, planning and code +1
  43. VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  44. LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-TuningDiffusion models → Video generation
  45. Patient-Specific Deep Reinforcement Learning for Automatic Replanning in Head-and-Neck Cancer Proton TherapyDeep reinforcement learning methods → RL for clinical treatment and surgery
  46. Pareto Optimal Code GenerationLLM reasoning → Reasoning for agents, planning and code
  47. TaskCraft: Automated Generation of Agentic TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  49. GenBreak: Red Teaming Text-to-Image Generators Using Large Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  50. From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content MonitoringLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  51. Text-Aware Image Restoration with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  52. A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video PairsLLM reasoning → Multimodal reasoning
  53. V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and PlanningWorld models → Embodied and robot world models
  54. ReSim: Reliable World Simulation for Autonomous DrivingWorld models → World models for autonomous driving +1
  55. Resa: Transparent Reasoning Models via SAEsLLM reasoning → Reasoning benchmarks and evaluation +1
  56. Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual DrawingLLM reasoning → Spatial and embodied reasoning +1
  57. Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal EndoscopyLLM reasoning → Clinical and biomedical applications
  58. LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection ChallengeLLM safety and security → Prompt injection and agent security
  59. Canonical Latent Representations in Conditional Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  60. Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingLLM reasoning → Reasoning benchmarks and evaluation
  61. CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video ModelsLLM reasoning → Multimodal reasoning
  62. VerIF: Verification Engineering for Reinforcement Learning in Instruction FollowingDeep reinforcement learning methods → RL training of language and agent models
  63. SAFE: Multitask Failure Detection for Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  64. LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  65. HadaNorm: Diffusion Transformer Quantization through Mean-Centered TransformationsDiffusion models → Diffusion foundations and sampling
  66. From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  67. Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine UnlearningLLM safety and security → Machine unlearning
  68. "What are my options?": Explaining RL Agents with Diverse Near-Optimal Alternatives (Extended)Deep reinforcement learning methods → Deep RL algorithms and representations
  69. The Emergence of Abstract Thought in Large Language Models Beyond Any LanguageLLM reasoning → Reasoning benchmarks and evaluation
  70. Probabilistic distances-based hallucination detection in LLMs with RAGRetrieval-augmented generation → Hallucination detection in RAG
  71. 3D-Aware Vision-Language Models Fine-Tuning with Geometric DistillationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  72. UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow MatchingDiffusion models → Audio, speech and music
  73. Causal Sufficiency and Necessity Improves Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  74. OctoNav: Towards Generalist Embodied NavigationLLM reasoning → Spatial and embodied reasoning
  75. A Deep Generative Model for the Simulation of Discrete Karst NetworksDiffusion models → Flow matching, time series and science
  76. CoRT: Code-integrated Reasoning within ThinkingLLM reasoning → Mathematical reasoning
  77. DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward SupervisionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  78. Automatic Treatment Planning using Reinforcement Learning for High-dose-rate Prostate BrachytherapyDeep reinforcement learning methods → RL for clinical treatment and surgery
  79. Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning ProtocolsLLM safety and security → Membership inference attacks
  80. Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +2
  81. ComfyUI-R1: Exploring Reasoning Models for Workflow GenerationLLM reasoning → Reasoning for agents, planning and code
  82. Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI EraLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML MonitoringLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  85. Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image PerturbationLLM reasoning → Multimodal reasoning +1
  86. Patterns for a New Generation: AI and AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  87. Adding simple structure at inference improves Vision-Language CompositionalityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  88. Bridging Continuous-time LQR and Reinforcement Learning via Gradient Flow of the Bellman ErrorDeep reinforcement learning methods → RL for games and combinatorial optimization
  89. Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal BoundsDiffusion models → Diffusion foundations and sampling
  90. Benchmarking Gaslighting Negation Attacks Against Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  91. VideoMat: Extracting PBR Materials from Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  92. Multi-level Value Alignment in Agentic AI Systems: Survey and PerspectivesLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  93. Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
  94. DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation LearningDiffusion models → Diffusion foundations and sampling
  95. FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  96. SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-ShotState-space sequence models (S4, Mamba) → Core SSM architectures for language
  97. Effective Red-Teaming of Policy-Adherent AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  98. MOORL: A Framework for Integrating Offline-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  99. From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model SynergiesLLM reasoning → Knowledge- and tool-augmented reasoning
  100. TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
All 411
  1. Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban ScenesLLM reasoning → Multimodal reasoning +1
  2. KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge GraphsRetrieval-augmented generation → RAG pipeline design and evaluation
  3. AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial PatchesDiffusion models → Robustness, privacy and adversarial aspects
  4. Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  5. Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  6. ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical ReasoningLLM reasoning → Clinical and biomedical applications +1
  7. Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental DesignLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  8. A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  9. Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse PlanningDiffusion models → Diffusion and flow policies for robotics
  10. Marrying Autoregressive Transformer and Diffusion with Multi-Reference AutoregressionDiffusion models → Image generation, text-to-image and editing
  11. Towards Bridging the Reward-Generation Gap in Direct Alignment AlgorithmsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  12. LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-JudgeLLM safety and security → Safety alignment, refusal and guardrails
  13. GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts ArchitectureMixture-of-experts → MoE large language models
  14. A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. Time-Unified Diffusion Policy with Action Discrimination for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  16. A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI AutonomyLLM agents and tool use → General LLM agent frameworks and benchmarks
  17. Noise Conditional Variational Score DistillationDiffusion models → Diffusion foundations and sampling
  18. Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  19. Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation ModelsLLM reasoning → Reasoning for agents, planning and code
  20. Revisiting Diffusion Models: From Generative Pre-training to One-Step GenerationDiffusion models → Diffusion foundations and sampling
  21. LPO: Towards Accurate GUI Agent Interaction via Location Preference OptimizationLLM agents and tool use → GUI and mobile agents +1
  22. Anomaly Detection and Generation with Diffusion Models: A SurveyDiffusion models → Flow matching, time series and science
  23. SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill BlendingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment ErasingDiffusion models → Robustness, privacy and adversarial aspects
  25. DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety PromptMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  26. DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-ExpertsMixture-of-experts → MoE large language models
  27. ErrorEraser: Unlearning Data Bias for Improved Continual LearningLLM safety and security → Machine unlearning
  28. RePO: Replay-Enhanced Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  29. Know What You Don't Know: Uncertainty Calibration of Process Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  30. Multi-Agent Language Models: Advancing Cooperation, Coordination, and AdaptationLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. Towards Efficient and Effective Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  32. Workflow-Based Evaluation of Music Generation Systems
  33. Active Learning for Forecasting Severity among Patients with Post Acute Sequelae of SARS-CoV-2
  34. Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
  35. Features-based embedding or Feature-grounding
  36. Latent Factorization of Tensors with Threshold Distance Weighted Loss for Traffic Data Estimation
  37. From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
  38. Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search
  39. GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations
  40. Efficient Multilingual ASR Finetuning via LoRA Language Experts
  41. HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration
  42. AI shares emotion with humans across languages and cultures
  43. ICE-ID: A Novel Historical Census Dataset for Longitudinal Identity Resolution
  44. The NordDRG AI Benchmark for Large Language Models
  45. Analysis of Anonymous User Interaction Relationships and Prediction of Advertising Feedback Based on Graph Neural Network
  46. Enhancing Bagging Ensemble Regression with Data Integration for Time Series-Based Diabetes Prediction
  47. ScholarSearch: Benchmarking Scholar Searching Ability of LLMs
  48. Enhancing Traffic Accident Classifications: Application of NLP Methods for City Safety
  49. Continuously Updating Digital Twins using Large Language Models
  50. ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour
  51. Towards a general-purpose foundation model for fMRI analysis
  52. Evaluating BiLSTM and CNN+GRU Approaches for Human Activity Recognition Using WiFi CSI Data
  53. Synthetic Geology: Structural Geology Meets Deep Learning
  54. Vector Representations of Vessel Trees
  55. VIBE: Can a VLM Read the Room?
  56. Brain-wide interpolation and conditioning of gene expression in the human brain using Implicit Neural Representations
  57. Digitization of Document and Information Extraction using OCR
  58. SLRNet: A Real-Time LSTM-Based Sign Language Recognition System
  59. QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
  60. HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data
  61. Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
  62. LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs
  63. 3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
  64. HQFNN: A Compact Quantum-Fuzzy Neural Network for Accurate Image Classification
  65. On the development of an AI performance and behavioural measures for teaching and classroom management
  66. FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation
  67. ToxSyn-PT: A Synthetic Fine-Grained Dataset of Minority-Targeted Toxic Language in Portuguese
  68. A new type of federated clustering: A non-model-sharing approach
  69. DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
  70. Classifying Unreliable Narrators with Large Language Models
  71. California Crop Yield Benchmark: Combining Satellite Image, Climate, Evapotranspiration, and Soil Data Layers for County-Level Yield Forecasting of Over 70 Crops
  72. Genre Controlled Music Generation via Activation Steering
  73. Cross-Learning Between ECG and PCG: Exploring Common and Exclusive Characteristics of Bimodal Electromechanical Cardiac Waveforms
  74. AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
  75. Code Roulette: How Prompt Variability Affects LLM Code Generation
  76. DynaSubVAE: Adaptive Subgrouping for Scalable and Robust OOD Detection
  77. Exploring Topological and Localization Phenomena in SSH Chains under Generalized AAH Modulation: A Computational Approach
  78. Towards Responsible AI: Advances in Safety, Fairness, and Accountability of Autonomous Systems
  79. Improving Oral Cancer Outcomes Through Machine Learning and Dimensionality Reduction
  80. Optimizing Genetic Algorithms with Multilayer Perceptron Networks for Enhancing TinyFace Recognition
  81. Improving Personalized Search with Regularized Low-Rank Parameter Updates
  82. A Comparative Study of Machine Learning Techniques for Early Prediction of Diabetes
  83. Correlation vs causation in Alzheimer's disease: an interpretability-driven study
  84. Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency
  85. Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context
  86. Momentum Multi-Marginal Schr"odinger Bridge Matching
  87. The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset
  88. Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective
  89. Probabilistic Variational Contrastive Learning
  90. Measuring Corporate Human Capital Disclosures: Lexicon, Data, Code, and Research Opportunities
  91. Analyzing Emotions in Bangla Social Media Comments Using Machine Learning and LIME
  92. When Large Language Models are Reliable for Judging Empathic Communication
  93. Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors
  94. Physiological-model-based neural network for modeling the metabolic-heart rate relationship during physical activities
  95. Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective
  96. Survival Analysis as Imprecise Classification with Trainable Kernels
  97. Unsupervised Elicitation of Language Models
  98. Statistical Guarantees for Offline Domain Randomization
  99. A Conjecture on a Fundamental Trade-Off between Certainty and Scope in Symbolic and Generative AI
  100. Meet Me at the Arm: The Cooperative Multi-Armed Bandits Problem with Shareable Arms
  101. GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environments
  102. Deteccc~ao da Psor'iase Utilizando Vis~ao Computacional: Uma Abordagem Comparativa Entre CNNs e Vision Transformers
  103. A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild
  104. AI5GTest: AI-Driven Specification-Aware Automated Testing and Validation of 5G O-RAN Components
  105. One For All: LLM-based Heterogeneous Mission Planning in Precision Agriculture
  106. Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach
  107. Fundamental Limits of Learning High-dimensional Simplices in Noisy Regimes
  108. Estimating the Joint Probability of Scenario Parameters with Gaussian Mixture Copula Models
  109. When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs
  110. Unsupervised Deep Clustering of MNIST with Triplet-Enhanced Convolutional Autoencoders
  111. Leveraging LLMs for Mission Planning in Precision Agriculture
  112. Efficient kernelized bandit algorithms via exploration distributions
  113. Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection
  114. DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding
  115. A quantum semantic framework for natural language processing
  116. Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
  117. Online Discovery of Simulation Models for Evolving Business Processes (Extended Version)
  118. Improving the performance of optical inverse design of multilayer thin films using CNN-LSTM tandem neural networks
  119. Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
  120. DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos
  121. PlayerOne: Egocentric World Simulator
  122. eFlesh: Highly customizable Magnetic Touch Sensing using Cut-Cell Microstructures
  123. Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
  124. Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
  125. Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation
  126. Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
  127. EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits
  128. InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
  129. Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
  130. AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
  131. Efficient Part-level 3D Object Generation via Dual Volume Packing
  132. How Do People Revise Inconsistent Beliefs? Examining Belief Revision in Humans with User Studies
  133. When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
  134. Vectorized Region Based Brush Strokes for Artistic Rendering
  135. Almost-Optimal Local-Search Methods for Sparse Tensor PCA
  136. Vision Generalist Model: A Survey
  137. Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos
  138. UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
  139. Sampling Theory for Super-Resolution with Implicit Neural Representations
  140. The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
  141. Fluoroscopic Shape and Pose Tracking of Catheters with Custom Radiopaque Markers
  142. Course Project Report: Comparing MCMC and Variational Inference for Bayesian Probabilistic Matrix Factorization on the MovieLens Dataset
  143. Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
  144. MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images
  145. Aspect-Based Opinion Summarization with Argumentation Schemes
  146. Only-Style: Stylistic Consistency in Image Generation without Content Leakage
  147. PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
  148. CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects
  149. A look at adversarial attacks on radio waveforms from discrete latent space
  150. EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
  151. Causal Climate Emulation with Bayesian Filtering
  152. Learning single-index models via harmonic decomposition
  153. The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
  154. Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation
  155. Stakeholder Participation for Responsible AI Development: Disconnects Between Guidance and Current Practice
  156. Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
  157. Machine Learning-Based Classification of Oils Using Dielectric Properties and Microwave Resonant Sensing
  158. Guided Graph Compression for Quantum Graph Neural Networks
  159. Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets
  160. IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
  161. Dataset of News Articles with Provenance Metadata for Media Relevance Assessment
  162. Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition
  163. DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction
  164. MMME: A Spontaneous Multi-Modal Micro-Expression Dataset Enabling Visual-Physiological Fusion
  165. Error-Guided Pose Augmentation: Enhancing Rehabilitation Exercise Assessment through Targeted Data Generation
  166. EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection
  167. A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity
  168. Superstudent intelligence in thermodynamics
  169. Identifiability Challenges in Sparse Linear Ordinary Differential Equations
  170. Metritocracy: Representative Metrics for Lite Benchmarks
  171. Generalizing Supervised Contrastive learning: A Projection Perspective
  172. Regularizing Learnable Feature Extraction for Automatic Speech Recognition
  173. Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?
  174. Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction
  175. A theoretical framework for self-supervised contrastive learning for continuous dependent data
  176. Accurate and efficient zero-shot 6D pose estimation with frozen foundation models
  177. Q-SAM2: Accurate Quantization for Segment Anything Model 2
  178. On the Similarities of Embeddings in Contrastive Learning
  179. Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space
  180. Cross-Channel Unlabeled Sensing over a Union of Signal Subspaces
  181. Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning
  182. Learning to Optimize Package Picking for Large-Scale, Real-World Robot Induction
  183. Alice and the Caterpillar: A more descriptive null model for assessing data mining results
  184. Large Language Models for Combinatorial Optimization of Design Structure Matrix
  185. Hierarchical Image Matching for UAV Absolute Visual Localization via Semantic and Structural Constraints
  186. Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets
  187. Towards Multimodal Graph Large Language Model
  188. MPFNet: A Multi-Prior Fusion Network with a Progressive Training Strategy for Micro-Expression Recognition
  189. AtmosMJ: Revisiting Gating Mechanism for AI Weather Forecasting Beyond the Year Scale
  190. Empirical and computer-aided robustness analysis of long-step and accelerated methods in smooth convex optimization
  191. The Four Color Theorem for Cell Instance Segmentation
  192. Non-Contact Health Monitoring During Daily Personal Care Routines
  193. Auto-Compressing Networks
  194. Training-Free Voice Conversion with Factorized Optimal Transport
  195. Fine-Tuning Large Audio-Language Models with LoRA for Precise Temporal Localization of Prolonged Exposure Therapy Elements
  196. ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search
  197. CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settings
  198. Towards Practical Alzheimer's Disease Diagnosis: A Lightweight and Interpretable Spiking Neural Model
  199. Knockoffs Inference under Privacy Constraints
  200. Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models
  201. Wasserstein Hypergraph Neural Network
  202. Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning
  203. Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Data
  204. Query-Level Uncertainty in Large Language Models
  205. CINeMA: Conditional Implicit Neural Multi-Modal Atlas for a Spatio-Temporal Representation of the Perinatal Brain
  206. PD2GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting
  207. Empirical Quantification of Spurious Correlations in Malware Detection
  208. A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma
  209. SyncFed: Time-Aware Federated Learning through Explicit Timestamping and Synchronization
  210. Intent Factored Generation: Unleashing the Diversity in Your Language Model
  211. Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
  212. DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
  213. HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
  214. Scaling Laws for Uncertainty in Deep Learning
  215. Real-Time Network Traffic Forecasting with Missing Data: A Generative Model Approach
  216. Using Sign Language Production as Data Augmentation to enhance Sign Language Translation
  217. Modeling Probabilistic Reduction using Information Theory and Naive Discriminative Learning
  218. Evasion Attacks Against Bayesian Predictive Models
  219. HSENet: Hybrid Spatial Encoding Network for 3D Medical Vision-Language Understanding
  220. In-Context Bias Propagation in LLM-Based Tabular Data Generation
  221. Benchmarking Debiasing Methods for LLM-based Parameter Estimates
  222. ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting
  223. GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
  224. Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
  225. Accelerating Large-Scale Regularized High-Order Tensor Recovery
  226. Beyond Overconfidence: Foundation Models Redefine Calibration in Deep Neural Networks
  227. Memorization in Language Models through the Lens of Intrinsic Dimension
  228. SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields
  229. Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language
  230. Gender Bias in English-to-Greek Machine Translation
  231. MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions
  232. GLD-Road:A global-local decoding road network extraction model for remote sensing images
  233. Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments
  234. Tightly-Coupled LiDAR-IMU-Leg Odometry with Online Learned Leg Kinematics Incorporating Foot Tactile Information
  235. STOAT: Spatial-Temporal Probabilistic Causal Inference Network
  236. 3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection
  237. Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
  238. Neural Functions for Learning Periodic Signal
  239. You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
  240. How attention simplifies mental representations for planning
  241. HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
  242. LLM-Powered CPI Prediction Inference with Online Text Time Series
  243. A Survey on the Role of Artificial Intelligence and Machine Learning in 6G-V2X Applications
  244. Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals
  245. TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
  246. Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
  247. EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization
  248. Bridging Online Behavior and Clinical Insight: A Longitudinal LLM-based Study of Suicidality on YouTube Reveals Novel Digital Markers
  249. DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
  250. BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio Generation
  251. Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
  252. TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation
  253. On a few pitfalls in KL divergence gradient estimation for RL
  254. WakeupUrban: Unsupervised Semantic Segmentation of Mid-20th century Urban Landscapes with Satellite Imagery
  255. Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
  256. Optimizing Cooperative Multi-Object Tracking using Graph Signal Processing
  257. Open-Set Domain Generalization through Spectral-Spatial Uncertainty Disentanglement for Hyperspectral Image Classification
  258. Abstraction-Based Proof Production in Formal Verification of Neural Networks
  259. NDCG-Consistent Softmax Approximation with Accelerated Convergence
  260. Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform
  261. Safe Screening Rules for Group SLOPE
  262. UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs
  263. OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
  264. Harmonizing and Merging Source Models for CLIP-based Domain Generalization
  265. TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
  266. Attention-Bayesian Hybrid Approach to Modular Multiple Particle Tracking
  267. Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
  268. When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
  269. Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training
  270. A Novel Lightweight Transformer with Edge-Aware Fusion for Remote Sensing Image Captioning
  271. Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
  272. Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings
  273. ODG: Occupancy Prediction Using Dual Gaussians
  274. PGDA-KGQA: A Prompt-Guided Generative Framework with Multiple Data Augmentation Strategies for Knowledge Graph Question Answering
  275. Synthetic Human Action Video Data Generation with Pose Transfer
  276. Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
  277. Scoop-and-Toss: Dynamic Object Collection for Quadrupedal Systems
  278. SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation
  279. A theoretical basis for model collapse in recursive training
  280. Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
  281. Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames
  282. SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
  283. A Hierarchical Probabilistic Framework for Incremental Knowledge Tracing in Classroom Settings
  284. Comparing human and LLM politeness strategies in free production
  285. Beyond Nash Equilibrium: Bounded Rationality of LLMs and humans in Strategic Decision-making
  286. ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
  287. Bipedal Balance Control with Whole-body Musculoskeletal Standing and Falling Simulations
  288. Binary classification for perceived quality of headlines and links on worldwide news websites, 2018-2024
  289. UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images
  290. CoLMbo: Speaker Language Model for Descriptive Profiling
  291. Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history
  292. ScaleLSD: Scalable Deep Line Segment Detection Streamlined
  293. COGENT: A Curriculum-oriented Framework for Generating Grade-appropriate Educational Content
  294. "I Said Things I Needed to Hear Myself": Peer Support as an Emotional, Organisational, and Sociotechnical Practice in Singapore
  295. Taming SQL Complexity: LLM-Based Equivalence Evaluation for Text-to-SQL
  296. A new approach for image segmentation based on diffeomorphic registration and gradient fields
  297. "Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
  298. Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
  299. DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
  300. Adversarial Surrogate Risk Bounds for Binary Classification
  301. An Effective End-to-End Solution for Multimodal Action Recognition
  302. Ming-Omni: A Unified Multimodal Model for Perception and Generation
  303. CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation
  304. Latent Multi-Head Attention for Small Language Models
  305. Intelligent System of Emergent Knowledge: A Coordination Fabric for Billions of Minds
  306. InstructPro: Natural Language Guided Ligand-Binding Protein Design
  307. MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning
  308. On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
  309. Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
  310. Surrogate models to optimize plasma assisted atomic layer deposition in high aspect ratio features
  311. What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?