mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 14 Aug 2025

343 papers

  1. 3D latent diffusion models for parameterizing and history matching multiscenario facies systemsDiffusion models → Flow matching, time series and science
  2. Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent CollaborationLLM agents and tool use → Web, search, and research agents
  3. Vocabulary Expansion of Large Language Models via Kullback-Leibler-Based Self-DistillationKnowledge distillation → Knowledge distillation for LLMs
  4. REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache CompressionLLM reasoning → Test-time compute and efficient thinking +1
  5. ALAS: Autonomous Learning Agent for Self-Updating Language ModelsLLM agents and tool use → Web, search, and research agents
  6. ReportBench: Evaluating Deep Research Agents via Academic Survey TasksLLM agents and tool use → Web, search, and research agents
  7. MAC: A Live Benchmark for Multimodal Large Language Models in Scientific UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  8. Physics-Informed Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
  9. MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing AgentsLLM agents and tool use → Multimodal and embodied agents
  10. Towards Reliable Multi-Agent Systems for Marketing Applications via Reflection, Memory, and PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Diffusion is a code repair operator and generatorDiffusion models → Discrete and text diffusion
  12. HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message PassingDiffusion models → 3D, point cloud and scene generation
  13. Utilizing Vision-Language Models as Action Models for Intent Recognition and AssistanceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  15. Hell or High Water: Evaluating Agentic Recovery from External FailuresLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. Can Multi-modal (reasoning) LLMs detect document manipulation?LLM reasoning → Multimodal reasoning +1
  17. CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse PreventionLLM reasoning → Reinforcement learning for reasoning
  18. Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
  19. SproutBench: A Benchmark for Safe and Ethical Large Language Models for YouthLLM safety and security → Safety alignment, refusal and guardrails
  20. 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  21. Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time ScalingLLM reasoning → Diffusion reasoning and test-time scaling +1
  22. Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  23. MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AILLM agents and tool use → Agent threats, guardrails and governance +1
  24. BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale PretrainingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  25. Failures to Surface Harmful Contents in Video Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
  26. Not There Yet: Evaluating Vision Language Models in Simulating the Visual Perception of People with Low VisionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  27. Retro-Expert: Collaborative Reasoning for Interpretable RetrosynthesisLLM reasoning → Clinical and biomedical applications
  28. A Study of Commonsense Reasoning over Visual Object PropertiesLLM reasoning → Multimodal reasoning
  29. Empowering Multimodal LLMs with External Tools: A Comprehensive SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  30. Searching for Privacy Risks in LLM Agents via SimulationLLM agents and tool use → Agent threats, guardrails and governance
  31. A Survey on Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  32. SSRL: Self-Search Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
  33. TLE-Based A2C Agent for Terrestrial Coverage Orbital Path PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
  34. Performance of GPT-5 in Brain Tumor MRI ReasoningLLM reasoning → Clinical and biomedical applications
  35. Hierarchical Fine-grained Preference Optimization for Physically Plausible Video GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  36. Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and ReasoningLLM reasoning → Clinical and biomedical applications
  37. UI-Venus Technical Report: Building High-performance UI Agents with RFTLLM agents and tool use → GUI and mobile agents
  38. Object Fidelity Diffusion for Remote Sensing Image GenerationDiffusion models → Inverse problems and image restoration
  39. Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion PriorDiffusion models → Inverse problems and image restoration
  40. The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language InferenceLLM reasoning → Clinical and biomedical applications
  41. BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video GenerationDiffusion models → Video generation
  42. AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video SequencesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  43. From Diagnosis to Improvement: Probing Spatio-Physical Reasoning in Vision Language ModelsWorld models → World models for language agents +2
  44. Modeling Human Responses to Multimodal AI ContentLLM agents and tool use → Social simulation and multi-agent debate
  45. FROGENT: An End-to-End Full-process Drug Design Multi-Agent SystemLLM agents and tool use → Medical and scientific domain agents
  46. Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  47. Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized PlanningDeep reinforcement learning methods → Deep RL algorithms and representations
  48. Agentic Design Review SystemLLM agents and tool use → Multimodal and embodied agents
  49. Thinking Inside the Mask: In-Place Prompting in Diffusion LLMsLLM reasoning → Prompting and chain-of-thought reasoning +1
  50. EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  51. NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at ScaleDiffusion models → Image generation, text-to-image and editing
  52. CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  53. Novel View Synthesis using DDIM InversionDiffusion models → 3D, point cloud and scene generation
  54. MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal ControlDiffusion models → Diffusion foundations and sampling
  55. IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context LearningLLM reasoning → Chain-of-thought reasoning for driving
  56. Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset GenerationDiffusion models → Image generation, text-to-image and editing +1
  57. AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  58. SemPT: Semantic Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  59. ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario SimulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  60. Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  61. Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language ModelsMechanistic interpretability → Activation steering methods
  62. HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMsLLM reasoning → Multimodal reasoning +1
  63. Towards Agentic AI for Multimodal-Guided Video Object SegmentationLLM agents and tool use → Multimodal and embodied agents
  64. SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  65. Retrieval-Augmented Prompt for OOD DetectionRetrieval-augmented generation → Privacy and security of RAG
  66. eDIF: A European Deep Inference Fabric for Remote Interpretability of LLMMechanistic interpretability → Knowledge and representations inside LLMs
  67. When Language Overrules: Revealing Text Dominance in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  68. PSScreen: Partially Supervised Multiple Retinal Disease ScreeningKnowledge distillation → Distillation for medical imaging
  69. Stabilizing Long-term Multi-turn Reinforcement Learning with Gated RewardsDeep reinforcement learning methods → RL training of language and agent models
  70. Projected Coupled Diffusion for Test-Time Constrained Joint GenerationDiffusion models → Diffusion foundations and sampling
  71. Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  72. Reasoning in Computer Vision: Taxonomy, Models, Tasks, and MethodologiesLLM reasoning → Multimodal reasoning +1
  73. Nonlocal Monte Carlo via Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  74. KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory SelectionDiffusion models → Diffusion and flow policies for robotics
  75. PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray ReasoningLLM reasoning → Clinical and biomedical applications +1
  76. TweezeEdit: Consistent and Efficient Image Editing with Path RegularizationDiffusion models → Image generation, text-to-image and editing
  77. A Unified Multi-Agent Framework for Universal Multimodal Understanding and GenerationDiffusion models → Image generation, text-to-image and editing +1
  78. Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive ArchitecturesWorld models → Latent predictive world models
  79. Trajectory-aware Shifted State Space Models for Online Video Super-ResolutionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  80. DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant RationalesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  81. We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical ReasoningLLM reasoning → Multimodal reasoning +1
  82. SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making TasksSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  83. STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving ScenesLLM reasoning → Chain-of-thought reasoning for driving +2
  84. NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  85. ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  86. CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation ModelVision-language-action models → Generalist VLA models and benchmarks
  87. Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  88. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text GenerationLLM safety and security → Jailbreaking +1
  89. PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  90. XQuant: Breaking the Memory Wall for LLM Inference with KV Cache RematerializationEfficient LLM inference and serving → KV cache quantization
  91. LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical RetrievalRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  92. Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful PromptsLLM reasoning → Reasoning for agents, planning and code +1
  93. Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  94. Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  95. eMamba: Efficient Acceleration Framework for Mamba Models in Edge ComputingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  96. Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired EvaluationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  97. What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup PuzzlesLLM reasoning → Reasoning benchmarks and evaluation
  98. Making Qwen3 Think in Korean with Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  99. A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question AnsweringDeep reinforcement learning methods → RL training of language and agent models
  100. ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot PerceiverVision-language-action models → Generalist VLA models and benchmarks
All 343
  1. Integrating Reinforcement Learning with Visual Generative Models: Foundations and AdvancesDeep reinforcement learning methods → RL with diffusion and flow models
  2. A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated LearningLLM safety and security → Federated unlearning and poisoning
  3. Cross-view Generalized Diffusion Model for Sparse-view CT ReconstructionDiffusion models → Medical imaging and segmentation
  4. ReviewRL: Towards Automated Scientific Review with RLDeep reinforcement learning methods → RL training of language and agent models
  5. Promoting Efficient Reasoning with Verifiable Stepwise RewardLLM reasoning → Test-time compute and efficient thinking
  6. JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in RoboticsLLM reasoning → Spatial and embodied reasoning +1
  7. Why Cannot Large Language Models Ever Make True Correct Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
  8. MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMsLLM reasoning → Hallucination detection and mitigation +1
  9. Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer ModelsLLM safety and security → Backdoor and data poisoning attacks
  10. cuAPO: A CUDA-based Parallelization of Artificial Protozoa Optimizer
  11. A Unified Theory of Language
  12. Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection
  13. The GPT-4o Shock Emotional Attachment to AI Models and Its Impact on Regulatory Acceptance: A Cross-Cultural Analysis of the Immediate Transition from GPT-4o to GPT-5
  14. RAST: A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
  15. STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction over Human Trajectory Data
  16. Uplifted Attackers, Human Defenders: The Cyber Offense-Defense Balance for Trailing-Edge Organizations
  17. Logical Expressivity and Explanations for Monotonic GNNs with Scoring Functions
  18. DLLMQuant: Quantizing Diffusion-based Large Language Models
  19. Systematic FAIRness Assessment of Open Voice Biomarker Datasets for Mental Health and Neurodegenerative Diseases
  20. Colon Polyps Detection from Colonoscopy Images Using Deep Learning
  21. "Not in My Backyard": LLMs Uncover Online and Offline Social Biases Against Homelessness
  22. BERT-VQA: Visual Question Answering on Plots
  23. Are AI Machines Making Humans Obsolete?
  24. Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2)
  25. Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs
  26. Enhancing GraphQL Security by Detecting Malicious Queries Using Large Language Models, Sentence Transformers, and Convolutional Neural Networks
  27. Code Vulnerability Detection Across Different Programming Languages with AI Models
  28. Navigating the New Landscape: A Conceptual Model for Project-Based Assessment (PBA) in the Age of GenAI
  29. Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity
  30. +VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking
  31. Tabularis Formatus: Predictive Formatting for Tables
  32. PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
  33. UWB-PostureGuard: A Privacy-Preserving RF Sensing System for Continuous Ergonomic Sitting Posture Monitoring
  34. Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees
  35. Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
  36. Predictive Multimodal Modeling of Diagnoses and Treatments in EHR
  37. Compressive Meta-Learning
  38. Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation
  39. A learning-driven automatic planning framework for proton PBS treatments of H&N cancers
  40. A Feasibility Experiment on the Application of Predictive Coding to Instant Messaging Corpora
  41. Abundance-Aware Set Transformer for Microbiome Sample Embedding
  42. LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters
  43. Your Recourse, My Loss? Algorithmic Recourse under Shared Constraints
  44. Functional Analysis of Variance for Association Studies
  45. Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs
  46. Data-Driven Abdominal Phenotypes of Type 2 Diabetes in Lean, Overweight, and Obese Cohorts
  47. Human-in-the-Loop Systems for Adaptive Learning Using Generative AI
  48. BIPOLAR: Polarization-based granular framework for LLM bias evaluation
  49. Counterfactual Survival Q-learning via Buckley-James Boosting, with Applications to ACTG 175 and CALGB 8923
  50. Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
  51. SHLIME: Foiling adversarial attacks fooling SHAP and LIME
  52. AI That Helps Us Help Each Other: A Proactive System for Scaffolding Mentor-Novice Collaboration in Entrepreneurship Coaching
  53. Conditional Independence Estimates for the Generalized Nonparanormal
  54. Learning with Confidence
  55. Note on Selection Bias in Observational Estimates of Algorithmic Progress
  56. MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation
  57. Risk-Based Prognostics and Health Management
  58. Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
  59. Quantization vs Pruning: Insights from the Strong Lottery Ticket Hypothesis
  60. Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
  61. Deep Learning-Based Automated Segmentation of Uterine Myomas
  62. Grounding Rule-Based Argumentation Using Datalog
  63. Rule2Text: A Framework for Generating and Evaluating Natural Language Explanations of Knowledge Graph Rules
  64. Multi-fidelity batch Bayesian optimization for bioprocess development across scales
  65. EVCtrl: Efficient Control Adapter for Visual Generation
  66. CSNR and JMIM Based Spectral Band Selection for Reducing Metamerism in Urban Driving
  67. UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools
  68. Quantum Visual Fields with Neural Amplitude Encoding
  69. A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
  70. Puppeteer: Rig and Animate Your 3D Models
  71. Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning
  72. ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
  73. MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
  74. STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
  75. Conic Formulations of Transport Metrics for Unbalanced Measure Networks and Hypernetworks
  76. Empirical Investigation into Configuring Echo State Networks for Representative Benchmark Problem Domains
  77. ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
  78. An Iterative Algorithm for Differentially Private k-PCA with Adaptive Noise
  79. Medico 2025: Visual Question Answering for Gastrointestinal Imaging
  80. TexVerse: A Universe of 3D Objects with High-Resolution Textures
  81. Efficiently Verifiable Proofs of Data Attribution
  82. From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
  83. From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals
  84. Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
  85. Generalizable Federated Learning using Client Adaptive Focal Modulation
  86. Reinforced Language Models for Sequential Decision Making
  87. MAGIC: Learning from Visibility Asymmetry for Unsupervised Stereo Matching
  88. SoK: Data Minimization in Machine Learning
  89. A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
  90. Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations
  91. Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures
  92. Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops
  93. Comparison of Data Reduction Criteria for Online Gaussian Processes
  94. Parity Cross-Resonance: A Multiqubit Gate
  95. Who Benefits from AI Explanations? Towards Accessible and Interpretable Systems
  96. Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee
  97. The SET Perceptual Factors Framework: Towards Assured Perception for Autonomous Systems
  98. When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images
  99. Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
  100. VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
  101. Cooperative Face Liveness Detection from Optical Flow
  102. Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detection
  103. Insights from the Algonauts 2025 Winners
  104. Dimension-Free Bounds for Generalized First-Order Methods via Gaussian Coupling
  105. Estimating Covariance for Global Minimum Variance Portfolio: A Decision-Focused Learning Approach
  106. IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data
  107. Memorisation and forgetting in a learning Hopfield neural network: bifurcation mechanisms, attractors and basins
  108. Natively Trainable Sparse Attention for Hierarchical Point Cloud Datasets
  109. An Efficient Model-Driven Groupwise Approach for Atlas Construction
  110. Forgery Guided Learning Strategy with Dual Perception Network for Deepfake Cross-domain Detection
  111. Axis-level Symmetry Detection with Group-Equivariant Representation
  112. Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
  113. APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squares
  114. Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
  115. Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
  116. Symmetry-Constrained Multi-Scale Physics-Informed Neural Networks for Graphene Electronic Band Structure Prediction
  117. ViewBridge:Revisiting Cross-View Localization from Image Matching
  118. Electromagnetic Simulations of Antennas on GPUs for Machine Learning Applications
  119. Lightweight CNNs for Embedded SAR Ship Target Detection and Classification
  120. Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios
  121. GenOM: Ontology Matching with Description Generation and Large Language Model
  122. REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations
  123. Learning from Natural Language Feedback for Personalized Question Answering
  124. Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
  125. Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages
  126. Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping
  127. HyperTea: A Hypergraph-based Temporal Enhancement and Alignment Network for Moving Infrared Small Target Detection
  128. Advancing Autonomous Incident Response: Leveraging LLMs and Cyber Threat Intelligence
  129. STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
  130. Deep Learning in Classical and Quantum Physics
  131. Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking
  132. Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
  133. Geospatial Diffusion for Land Cover Imperviousness Change Forecasting
  134. SPHENIC: Topology-Aware Multi-View Clustering for Spatial Transcriptomics
  135. Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
  136. Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
  137. A Guide to Bayesian Optimization in Bioprocess Engineering
  138. Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
  139. Increasing the Utility of Synthetic Images through Chamfer Guidance
  140. Nonlinear filtering based on density approximation and deep BSDE prediction
  141. Energy-Based Models for Predicting Mutational Effects on Proteins
  142. Beyond Random Sampling: Instance Quality-Based Data Partitioning via Item Response Theory
  143. FIND-Net -- Fourier-Integrated Network with Dictionary Kernels for Metal Artifact Reduction
  144. Fourier-Guided Attention Upsampling for Image Super-Resolution
  145. DIVA-VQA: Detecting Inter-frame Variations in UGC Video Quality
  146. Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
  147. Oops!... They Stole it Again: Attacks on Split Learning
  148. On Spectral Properties of Gradient-based Explanation Methods
  149. FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
  150. Self-Supervised Temporal Super-Resolution of Energy Data using Generative Adversarial Transformer
  151. GNN-based Unified Deep Learning
  152. EvTurb: Event Camera Guided Turbulence Removal
  153. Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot
  154. Multi-Receptive Field Ensemble with Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detection
  155. HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
  156. Reproducible Physiological Features in Affective Computing: A Preliminary Analysis on Arousal Modeling
  157. Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform
  158. PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks
  159. A Differentiable Framework for Full and Phaseless Data Inversion Using Neural Implicit Contrast-Source Representation
  160. AR Surgical Navigation with Surface Tracing: Comparing In-Situ Visualization with Tool-Tracking Guidance for Neurosurgical Applications
  161. Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Images
  162. Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation
  163. Improving Value-based Process Verifier via Low-Cost Variance Reduction
  164. Mitigating Exponential Mixed Frequency Growth through Frequency Selection
  165. Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
  166. EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba
  167. Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT Modules
  168. A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
  169. Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting
  170. Advances in Logic-Based Entity Resolution: Enhancing ASPEN with Local Merges and Optimality Criteria
  171. Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model
  172. Contrastive ECOC: Learning Output Codes for Adversarial Defense
  173. On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
  174. SEQ-GPT: LLM-assisted Spatial Query via Example
  175. When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
  176. Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
  177. Confounding is a Pervasive Problem in Real World Recommender Systems
  178. EDAPT: Towards Calibration-Free BCIs with Continual Online Adaptation
  179. STAMP: Multi-pattern Attention-aware Multiple Instance Learning for STAS Diagnosis in Multi-center Histopathology Images
  180. GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generation
  181. Enhanced Sparse Point Cloud Data Processing for Privacy-aware Human Action Recognition
  182. FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs
  183. SingleStrip: learning skull-stripping from a single labeled example
  184. X-Node: Self-Explanation is All We Need
  185. Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching
  186. Multi-Label Plant Species Prediction with Metadata-Enhanced Multi-Head Vision Transformers
  187. RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations
  188. From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
  189. SkeySpot: Automating Service Key Detection for Digital Electrical Layout Plans in the Construction Industry
  190. BKP: An R Package for Beta Kernel Process Modeling
  191. DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations
  192. Alternating Approach-Putt Models for Multi-Stage Speech Enhancement
  193. Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
  194. CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation
  195. MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance
  196. Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
  197. HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation
  198. MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion
  199. Evaluating LLMs on Chinese Idiom Translation
  200. MCP2OSC: Parametric Control by Natural Language
  201. SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection
  202. Dataset Construction for Training LLM to Learn Analog Circuit Knowledge
  203. A Unified Evaluation Framework for Multi-Annotator Tendency Learning
  204. Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noise
  205. Clicks Versus Conversion: Choosing a Recommender's Training Objective in E-Commerce
  206. Improving Generative Cross-lingual Aspect-Based Sentiment Analysis with Constrained Decoding
  207. Large Language Models for Summarizing Czech Historical Documents and Beyond
  208. Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
  209. AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging
  210. Improving OCR for Historical Texts of Multiple Languages
  211. Cross-Prompt Encoder for Low-Performing Languages
  212. Glo-UMF: A Unified Multi-model Framework for Automated Morphometry of Glomerular Ultrastructural Characterization
  213. Semantic Communication with Distribution Learning through Sequential Observations
  214. FlexP-SFT: A Flexible Aggregation-Free Framework for On-Device Personalized Split Federated Fine-Tuning of LLMs
  215. A Hierarchical IDS for Zero-Day Attack Detection in Internet of Medical Things Networks
  216. Welfare-Centric Clustering
  217. Multi-Agent Trust Region Policy Optimisation: A Joint Constraint Approach
  218. Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models
  219. Online selective conformal inference: adaptive scores, convergence rates and optimality
  220. Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech
  221. Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
  222. From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis
  223. From Pixel to Mask: A Survey of Out-of-Distribution Segmentation
  224. Efficient Image Denoising Using Global and Local Circulant Representation
  225. Yet another algorithmic bias: A Discursive Analysis of Large Language Models Reinforcing Dominant Discourses on Gender and Race
  226. Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuning
  227. SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
  228. InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild
  229. Inductive Bias Extraction and Matching for LLM Prompts
  230. A Mutual-Structure Weighted Sub-Pixel Multimodal Optical Remote Sensing Image Matching Method
  231. Uncertainty-Aware Prediction of Parkinson's Disease Medication Needs: A Two-Stage Conformal Prediction Approach
  232. The Conditional Regret-Capacity Theorem for Batch Universal Prediction
  233. VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation
  234. High Fidelity Text to Image Generation with Contrastive Alignment and Structural Guidance
  235. Pose-Robust Calibration Strategy for Point-of-Gaze Estimation on Mobile Phones
  236. DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy
  237. Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
  238. Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets
  239. Federated Anomaly Detection for Multi-Tenant Cloud Platforms with Personalized Modeling
  240. Multi-Agent Reinforcement Learning for Adaptive Resource Orchestration in Cloud-Native Clusters
  241. Facilitating Longitudinal Interaction Studies of AI Systems
  242. Convergence Analysis of Max-Min Exponential Neural Network Operators in Orlicz Space
  243. A Computational Approach to Analyzing Language Change and Variation in the Constructed Language Toki Pona