mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 12 Mar 2025

383 papers

  1. Chain of Draft for Software Engineering: Challenges in Applying Concise Reasoning to Code TasksLLM reasoning → Reasoning for agents, planning and code
  2. MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product QuantizationEfficient LLM inference and serving → KV cache quantization
  3. HaploVL: A Single-Transformer Baseline for Multi-Modal UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. A Survey of Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. Enhanced Continual Learning of Vision-Language Models with Model FusionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  6. Error Analyses of Auto-Regressive Video Diffusion Models: A Unified FrameworkDiffusion models → Video generation
  7. ClaimTrust: Propagation Trust Scoring for RAG SystemsRetrieval-augmented generation → Privacy and security of RAG
  8. TA-V2A: Textually Assisted Video-to-Audio GenerationDiffusion models → Audio, speech and music
  9. Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question EvaluationLLM reasoning → Multimodal reasoning
  10. Learning to Contextualize Web Pages for Enhanced Decision Making by LLM AgentsLLM agents and tool use → Web, search, and research agents
  11. Context-guided Responsible Data Augmentation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  12. Conversational Gold: Evaluating Personalized Conversational Search System using Gold NuggetsRetrieval-augmented generation → Conversational and speech RAG
  13. Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  14. On the Limitations of Vision-Language Models in Understanding Image TransformsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  15. SE(3)-Equivariant Robot Learning and Control: A Tutorial SurveyOffline RL and imitation learning from data → Robot manipulation imitation learning
  16. ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot NavigationLLM reasoning → Spatial and embodied reasoning +1
  17. Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided RetrievalLLM reasoning → Test-time compute and efficient thinking
  18. Fine-tuning Vision Language Models with Graph-based Knowledge for Explainable Medical Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  19. Constrained Discrete DiffusionDiffusion models → Discrete and text diffusion
  20. AgentDAM: Privacy Leakage Evaluation for Autonomous Web AgentsLLM agents and tool use → Agent threats, guardrails and governance
  21. Multi-Agent LLM Actor-Critic Framework for Social Robot NavigationLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. Solving Bayesian inverse problems with diffusion priors and off-policy RLDiffusion models → Inverse problems and image restoration +1
  23. The Pitfalls of Imitation Learning when Actions are ContinuousOffline RL and imitation learning from data → Imitation learning methods
  24. MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based BatchingMixture-of-experts → Efficient MoE training and inference systems +1
  25. Accelerating Diffusion Sampling via Exploiting Local Transition CoherenceDiffusion models → Diffusion foundations and sampling
  26. Probabilistic Reasoning with LLMs for k-anonymity EstimationLLM reasoning → Reasoning for agents, planning and code
  27. Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  28. Optimisation of the Accelerator Control by Reinforcement Learning: A Simulation-Based ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  29. A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM NetworksDeep reinforcement learning methods → Adversarial robustness and RL in finance
  30. A Survey on Trustworthy LLM Agents: Threats and CountermeasuresLLM agents and tool use → Agent threats, guardrails and governance
  31. SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency DistillationDiffusion models → Image generation, text-to-image and editing
  32. Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine HesitancyLLM agents and tool use → Social simulation and multi-agent debate
  33. Edge AI-Powered Real-Time Decision-Making for Autonomous Vehicles in Adverse Weather ConditionsEnd-to-end autonomous driving → VLMs for autonomous driving
  34. RewardSDS: Aligning Score Distillation via Reward-Weighted SamplingDiffusion models → 3D, point cloud and scene generation +1
  35. MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemRetrieval-augmented generation → Multimodal RAG
  36. PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff DropDiffusion models → Video generation
  37. SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action AlignmentEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  38. Minimax Optimality of the Probability Flow ODE for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  39. Block Diffusion: Interpolating Between Autoregressive and Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  40. Plan-and-Act: Improving Planning of Agents for Long-Horizon TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  42. TPDiff: Temporal Pyramid Video Diffusion ModelDiffusion models → Video generation
  43. Strategyproof Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  44. StructDiff: Structure-aware Diffusion Model for 3D Fine-grained Medical Image SynthesisDiffusion models → Medical imaging and segmentation
  45. SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityMechanistic interpretability → SAE features and their applications
  46. CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing GamesVision-language-action models → Generalist VLA models and benchmarks
  47. PairVDN - Pair-wise Decomposed Value FunctionsDeep reinforcement learning methods → Deep RL algorithms and representations
  48. Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  49. CM-Diff: A Single Generative Network for Bidirectional Cross-Modality Translation Diffusion Model Between Infrared and Visible ImagesDiffusion models → Image generation, text-to-image and editing
  50. Reinforcement Learning is all You NeedLLM reasoning → Reinforcement learning for reasoning +1
  51. ViM-VQ: Efficient Post-Training Vector Quantization for Visual MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  52. Double-Stage Feature-Level Clustering-Based Mixture of Experts FrameworkMixture-of-experts → Vision mixture-of-experts
  53. ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +1
  54. DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution PredictionDiffusion models → Diffusion foundations and sampling
  55. Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and PlanningLLM reasoning → Clinical and biomedical applications +1
  56. Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  57. Astrea: A MOE-based Visual Understanding Model with Progressive AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  58. Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from TranslationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  59. Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent SpaceDiffusion models → Diffusion foundations and sampling
  60. Mitigating Membership Inference Vulnerability in Personalized Federated LearningLLM safety and security → Federated unlearning and poisoning
  61. Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  62. Context-aware Constrained Reinforcement Learning Based Energy-Efficient Power Scheduling for Non-stationary XR Data TrafficDeep reinforcement learning methods → RL for energy, networks and operations
  63. Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical SystemsDeep reinforcement learning methods → Safe and constrained RL
  64. VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic CarriersMultimodal LLMs / vision-language models → Video understanding with MLLMs
  65. Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrityLLM safety and security → Membership inference attacks
  66. GIGP: A Global Information Interacting and Geometric Priors Focusing Framework for Semi-supervised Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  67. MOAT: Evaluating LMMs for Capability Integration and Instruction GroundingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  68. Unified Dense Prediction of Video DiffusionDiffusion models → Video generation
  69. Group-robust Machine UnlearningLLM safety and security → Machine unlearning
  70. A Survey on Enhancing Causal Reasoning Ability of Large Language ModelsLLM reasoning → Causal reasoning in LLMs
  71. xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge DistillationKnowledge distillation → Multimodal distillation
  72. Steering No-Regret Agents in MFGs under Model UncertaintyDeep reinforcement learning methods → RL for games and combinatorial optimization
  73. Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  74. Detecting and Preventing Data Poisoning Attacks on AI ModelsLLM safety and security → Backdoor and data poisoning attacks
  75. UniCombine: Unified Multi-Conditional Combination with Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  76. Rule-Guided Reinforcement Learning Policy Evaluation and ImprovementDeep reinforcement learning methods → Interpretable and logic-guided RL
  77. COLA: A Scalable Multi-Agent Framework For Windows UI Task AutomationLLM agents and tool use → GUI and mobile agents
  78. Large-scale Regional Traffic Signal Control Based on Single-Agent Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  79. Considering Length Diversity in Retrieval-Augmented SummarizationRetrieval-augmented generation → RAG pipeline design and evaluation
  80. Bayesian Test-Time Adaptation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  81. NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow TransformersDiffusion models → Diffusion foundations and sampling
  82. In-Context Defense in Computer Agents: An Empirical StudyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  83. Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation DatasetsDiffusion models → Medical imaging and segmentation
  84. Rethinking Prompt-based Debiasing in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  85. Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent SpaceWorld models → World models for autonomous driving +1
  86. Why LLMs Cannot Think and How to Fix ItLLM reasoning → Reasoning benchmarks and evaluation
  87. MarineGym: A High-Performance Reinforcement Learning Platform for Underwater RoboticsDeep reinforcement learning methods → RL for robot navigation and UAV control
  88. FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPOLLM reasoning → Multimodal reasoning
  89. Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News DetectionLLM reasoning → Hallucination detection and mitigation
  90. Reangle-A-Video: 4D Video Generation as Video-to-Video TranslationDiffusion models → 3D, point cloud and scene generation
  91. Memory-enhanced Retrieval Augmentation for Long Video UnderstandingRetrieval-augmented generation → Multimodal RAG
  92. Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?Diffusion models → Image generation, text-to-image and editing
  93. GRU: Mitigating the Trade-off between Unlearning and Retention for LLMsLLM safety and security → Machine unlearning
  94. Backdooring CLIP through Concept ConfusionLLM safety and security → Backdoor and data poisoning attacks
  95. Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear SystemsOffline RL and imitation learning from data → Inverse reinforcement learning +1
  96. LocAgent: Graph-Guided LLM Agents for Code LocalizationLLM agents and tool use → Software engineering coding agents
  97. Theoretical Guarantees for High Order Trajectory Refinement in Generative FlowsDiffusion models → Flow matching, time series and science
  98. Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial StatesLLM safety and security → Jailbreaking
  99. ManeuverGPT Agentic Control for Safe Autonomous Stunt ManeuversLLM agents and tool use → Multimodal and embodied agents
  100. Adaptive Temperature Based on Logits Correlation in Knowledge DistillationKnowledge distillation → General knowledge distillation methods
All 383
  1. DAST: Difficulty-Aware Self-Training on Large Language ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  2. Aligning to What? Limits to RLHF Based AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  3. Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration InterfaceOffline RL and imitation learning from data → Robot manipulation imitation learning
  4. Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data CatalogsRetrieval-augmented generation → RAG pipeline design and evaluation
  5. Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for QuadrupedsKnowledge distillation → Multimodal distillation +1
  6. Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  7. Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior AttacksLLM safety and security → Jailbreaking
  8. Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future DirectionsLLM agents and tool use → Web, search, and research agents
  9. Bridging Pattern-Aware Complexity with NP-Hard Optimization: A Unifying Framework and Empirical Study
  10. You Only Train Once: A Flexible Training Framework for Code Vulnerability Detection Driven by Vul-Vector
  11. PharMolixFM: All-Atom Foundation Models for Molecular Modeling and Generation
  12. Neuro-Informed Adaptive Learning (NIAL) Algorithm: A Hybrid Deep Learning Approach for ECG Signal Classification
  13. Mapping fMRI Signal and Image Stimuli in an Artificial Neural Network Latent Space: Bringing Artificial and Natural Minds Together
  14. Intanify AI Platform: Embedded AI for Automated IP Audit and Due Diligence
  15. AIDetection: A Generative AI Detection Tool for Educators Using Syntactic Matching of Common ASCII Characters As Potential 'AI Traces' Within Users' Internet Browser
  16. SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models
  17. Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey
  18. Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
  19. Leveraging Knowledge Graphs and LLMs for Context-Aware Messaging
  20. Revisiting the Predictability of Performative, Social Events
  21. Privacy-Preserved Automated Scoring using Federated Learning for Educational Research
  22. ConjointNet: Enhancing Conjoint Analysis for Preference Prediction with Representation Learning
  23. Conformal Prediction and Human Decision Making
  24. Refining Filter Global Feature Weighting for Fully-Unsupervised Clustering
  25. Physical knowledge improves prediction of EM Fields
  26. LLM-Guided Indoor Navigation with Multimodal Map Understanding
  27. Exploration of Hepatitis B Virus Infection Dynamics through Physics-Informed Deep Learning Approach
  28. CALLM: Understanding Cancer Survivors' Emotions and Intervention Opportunities via Mobile Diaries and Context-Aware Language Models
  29. SciFi-Benchmark: Leveraging Science Fiction To Improve Robot Behavior
  30. LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation
  31. Video Individual Counting for Moving Drones
  32. Test-Time Discovery via Hashing Memory
  33. Ordered Semantically Diverse Sampling for Textual Data
  34. Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion
  35. Neighboring Autoregressive Modeling for Efficient Visual Generation
  36. Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks
  37. Medical Large Language Model Benchmarks Should Prioritize Construct Validity
  38. Knowledge Consultation for Semi-Supervised Semantic Segmentation
  39. Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark
  40. Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models
  41. CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding
  42. Proceedings of the ISCA/ITG Workshop on Diversity in Large Speech and Language Models
  43. Quantization for OpenAI's Whisper Models: A Comparative Analysis
  44. A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives
  45. AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions
  46. A Rule Based Solution to Co-reference Resolution in Clinical Text
  47. What's In Your Field? Mapping Scientific Research with Knowledge Graphs and Large Language Models
  48. Tracking the Best Expert Privately
  49. On the contraction properties of Sinkhorn semigroups
  50. QuickDraw: Fast Visualization, Analysis and Active Learning for Medical Image Segmentation
  51. CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation
  52. FDCT: Frequency-Aware Decomposition and Cross-Modal Token-Alignment for Multi-Sensor Target Classification
  53. LuciBot: Automated Robot Policy Learning from Generated Videos
  54. Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations
  55. EquiPy: Sequential Fairness using Optimal Transport in Python
  56. Foundation X: Integrating Classification, Localization, and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis
  57. An Asymmetric Independence Model for Causal Discovery on Path Spaces
  58. Media and responsible AI governance: a game-theoretic and LLM analysis
  59. Who Are You Behind the Screen? Implicit MBTI and Gender Detection Using Artificial Intelligence
  60. TabNSA: Native Sparse Attention for Efficient Tabular Data Learning
  61. Training Human-Robot Teams by Improving Transparency Through a Virtual Spectator Interface
  62. Predicting Tropical Cyclone Track Forecast Errors using a Probabilistic Neural Network
  63. A Comprehensive Review on Understanding the Decentralized and Collaborative Approach in Machine Learning
  64. Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation
  65. Resolution Invariant Autoencoder
  66. Isolated Channel Vision Transformers: From Single-Channel Pretraining to Multi-Channel Finetuning
  67. Generative AI for Named Entity Recognition in Low-Resource Language Nepali
  68. Temporal Difference Flows
  69. A practical guide to machine learning interatomic potentials -- Status and future
  70. How good are deep learning methods for automated road safety analysis using video data? An experimental study
  71. Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models
  72. Evaluating the Impact of Synthetic Data on Object Detection Tasks in Autonomous Driving
  73. Batch List-Decodable Linear Regression via Higher Moments
  74. Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
  75. SeqSAM: Autoregressive Multiple Hypothesis Prediction for Medical Image Segmentation using SAM
  76. Minimal Time Series Transformer
  77. Bidirectional Learned Facial Animation Codec for Low Bitrate Talking Head Videos
  78. Designing Graph Convolutional Neural Networks for Discrete Choice with Network Effects
  79. Learning richness modulates equality reasoning in neural networks
  80. Real-Time Risky Fault-Chain Search using Time-Varying Graph RNNs
  81. Efficient Multi-Task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment
  82. Cover Learning for Large-Scale Topology Representation
  83. BiasConnect: Investigating Bias Interactions in Text-to-Image Models
  84. Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
  85. A PyTorch-Enabled Tool for Synthetic Event Camera Data Generation and Algorithm Development
  86. SASNet: Spatially-Adaptive Sinusoidal Networks for INRs
  87. A Siamese Network to Detect If Two Iris Images Are Monozygotic
  88. Review GIDE -- Restaurant Review Gastrointestinal Illness Detection and Extraction with Large Language Models
  89. Unveiling Hidden Pivotal Players with GoalNet: A GNN-Based Soccer Player Evaluation System
  90. Enhancing Adversarial Example Detection Through Model Explanation
  91. I2V3D: Controllable image-to-video generation with 3D guidance
  92. Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving
  93. How Feasible is Augmenting Fake Nodes with Learnable Features as a Counter-strategy against Link Stealing Attacks?
  94. Finding the Muses: Identifying Coresets through Loss Trajectories
  95. Towards Causal Model-Based Policy Optimization
  96. Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
  97. Revisiting semi-supervised learning in the era of foundation models
  98. Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey
  99. DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
  100. CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
  101. Towards Hardware Supported Domain Generalization in DNN-Based Edge Computing Devices for Health Monitoring
  102. Power Spectrum Signatures of Graphs
  103. Edge AI for Real-time Fetal Assessment in Rural Guatemala
  104. Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Users
  105. T'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
  106. LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics
  107. Bags of Projected Nearest Neighbours: Competitors to Random Forests?
  108. Technical and Legal Aspects of Federated Learning in Bioinformatics: Applications, Challenges and Opportunities
  109. Inductive Spatio-Temporal Kriging with Physics-Guided Increment Training Strategy for Air Quality Inference
  110. Global Position Aware Group Choreography using Large Language Model
  111. FedMSGL: A Self-Expressive Hypergraph Based Federated Multi-View Learning
  112. Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k
  113. Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
  114. How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation
  115. Parsing the Language of Expression: Enhancing Symbolic Regression with Domain-Aware Symbolic Priors
  116. BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
  117. Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matching
  118. Auspex: Building Threat Modeling Tradecraft into an Artificial Intelligence-based Copilot
  119. Cost-Optimal Grouped-Query Attention for Long-Context Modeling
  120. Manify: A Python Library for Learning Non-Euclidean Representations
  121. Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μP Parametrization
  122. Interlaced R2D2 DNN Series for Scalable Non-Cartesian MRI with Sensitivity Self-calibration
  123. Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis
  124. A Planning Compilation to Reason about Goal Achievement at Planning Time
  125. PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
  126. Neural Network-Based Change Point Detection for Large-Scale Time-Evolving Data
  127. Differentially Private Equilibrium Finding in Polymatrix Games
  128. GenHPE: Generative Counterfactuals for 3D Human Pose Estimation with Radio Frequency Signals
  129. Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging
  130. Large Language Models for Multi-Facility Location Mechanism Design
  131. Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer
  132. RESTRAIN: Reinforcement Learning-Based Secure Framework for Trigger-Action IoT Environment
  133. TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues
  134. MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
  135. Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment
  136. Federated Smoothing ADMM for Localization
  137. Robust Multimodal Survival Prediction with the Latent Differentiation Conditional Variational AutoEncoder
  138. Representation Retrieval Learning for Heterogeneous Data Integration
  139. Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection
  140. Learning Cascade Ranking as One Network
  141. Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
  142. A Novel Approach for Intrinsic Dimension Estimation
  143. Learning Spatially Adaptive ℓ1-Norms Weights for Convolutional Synthesis Regularization
  144. BAMBI: Developing Baby Language Models for Italian
  145. Neural reservoir control of a soft bio-hybrid arm
  146. Hybrid Rendering for Multimodal Autonomous Driving: Merging Neural and Physics-Based Simulation
  147. SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
  148. Explicit Learning and the LLM in Machine Translation
  149. How Well Does Your Tabular Generator Learn the Structure of Tabular Data?
  150. Fast computation of the TGOSPA metric for multiple target tracking via unbalanced optimal transport
  151. Online Language Splatting
  152. SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation
  153. PromptMap: An Alternative Interaction Style for AI-Based Image Generation
  154. CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection
  155. Language-Enhanced Representation Learning for Single-Cell Transcriptomics
  156. Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter
  157. Efficient dynamic modal load reconstruction using physics-informed Gaussian processes based on frequency-sparse Fourier basis functions
  158. Towards Generating Automatic Anaphora Annotations
  159. OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment
  160. Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
  161. Monte Carlo Diffusion for Generalizable Learning-Based RANSAC
  162. AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation
  163. Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation
  164. Got Compute, but No Data: Lessons From Post-training a Finnish LLM
  165. Multi-Agent Image Restoration
  166. VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
  167. ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
  168. Precoder Learning by Leveraging Unitary Equivariance Property
  169. Close-up-GS: Enhancing Close-Up View Synthesis in 3D Gaussian Splatting with Progressive Self-Training
  170. Adjusted Count Quantification Learning on Graphs
  171. Revisiting Agnostic Boosting
  172. Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
  173. Pig behavior dataset and Spatial-temporal perception and enhancement networks based on the attention mechanism for pig behavior recognition
  174. Revisiting Medical Image Retrieval via Knowledge Consolidation
  175. PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens
  176. Post-interactive Multimodal Trajectory Prediction for Autonomous Driving
  177. Towards Graph Foundation Models: A Transferability Perspective
  178. Deep Learning for Climate Action: Computer Vision Analysis of Visual Narratives on X
  179. RetSTA: An LLM-Based Approach for Standardizing Clinical Fundus Image Reports
  180. Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach
  181. Fully-Synthetic Training for Visual Quality Inspection in Automotive Production
  182. Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
  183. GASPACHO: Gaussian Splatting for Controllable Humans and Objects
  184. An Evaluation of LLMs for Detecting Harmful Computing Terms
  185. Investigating User Perspectives on Differentially Private Text Privatization
  186. Online multidimensional dictionary learning
  187. Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness
  188. NVP-HRI: Zero Shot Natural Voice and Posture-based Human-Robot Interaction via Large Language Model
  189. CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
  190. SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstruction
  191. Energy Optimized Piecewise Polynomial Approximation Utilizing Modern Machine Learning Optimizers
  192. DAVE: Diagnostic benchmark for Audio Visual Evaluation
  193. 2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos
  194. ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning
  195. Revealing the Implicit Noise-based Imprint of Generative Models
  196. Terrier: A Deep Learning Repeat Classifier
  197. Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions
  198. Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
  199. IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond
  200. Better Together: Unified Motion Capture and 3D Avatar Reconstruction
  201. Unmask It! AI-Generated Product Review Detection in Dravidian Languages
  202. Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoising
  203. Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption
  204. DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
  205. Single-Qudit Quantum Neural Networks for Multiclass Classification
  206. Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering
  207. A Global Dataset Mapping the AI Innovation from Academic Research to Industrial Patents
  208. SCOPE-DTI: Semi-Inductive Dataset Construction and Framework Optimization for Practical Usability Enhancement in Deep Learning-Based Drug Target Interaction Prediction
  209. How To Make Your Cell Tracker Say "I dunno!"
  210. GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation
  211. Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions
  212. LREF: A Novel LLM-based Relevance Framework for E-commerce
  213. N2C2: Nearest Neighbor Enhanced Confidence Calibration for Cross-Lingual In-Context Learning
  214. Evaluating the Generalizability of LLMs in Automated Program Repair
  215. Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients
  216. Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model
  217. Token Weighting for Long-Range Language Modeling
  218. Time-EAPCR: A Deep Learning-Based Novel Approach for Anomaly Detection Applied to the Environmental Field
  219. GENEOnet: Statistical analysis supporting explainability and trustworthiness
  220. Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting
  221. Addressing pitfalls in implicit unobserved confounding synthesis using explicit block hierarchical ancestral sampling
  222. Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates
  223. Learning Appearance and Motion Cues for Panoptic Tracking
  224. Polygonizing Roof Segments from High-Resolution Aerial Images Using Yolov8-Based Edge Detection
  225. Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework
  226. Incomplete Multi-view Clustering via Diffusion Contrastive Generation
  227. Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs
  228. Dynamic Feature Selection from Variable Feature Sets Using Features of Features
  229. Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs
  230. Effective Feature Selection for Predicting Spreading Factor with ML in Large LoRaWAN-based Mobile IoT Networks
  231. AI-Driven Decision Support in Oncology: Evaluating Data Readiness for Skin Cancer Treatment
  232. WonderVerse: Extendable 3D Scene Generation with Video Generative Models
  233. Unreflected Use of Tabular Data Repositories Can Undermine Research Quality
  234. SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video
  235. Generative Frame Sampler for Long Video Understanding
  236. Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharing
  237. Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
  238. Clustering by Nonparametric Smoothing
  239. Investigation of Frame Differences as Motion Cues for Video Object Segmentation
  240. MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration
  241. Reference-free Human-Object Interaction Editing
  242. Specification languages for computational laws versus basic legal principles
  243. FlexiReg: Flexible Urban Region Representation Learning
  244. AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
  245. On the Internal Representations of Graph Metanetworks
  246. Drift-Aware Federated Learning: A Causal Perspective
  247. Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge
  248. Constraint-Guided Learning of Data-driven Health Indicator Models: An Application on the Pronostia Bearing Dataset
  249. Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery
  250. VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformation
  251. The Shape of Attraction in UMAP: Exploring the Embedding Forces in Dimensionality Reduction
  252. Tacchi 2.0: A Low Computational Cost and Comprehensive Dynamic Contact Simulator for Vision-based Tactile Sensors
  253. Causal-Ex: Causal Graph-based Micro and Macro Expression Spotting
  254. Self-Consistent Equation-guided Neural Networks for Censored Time-to-Event Data
  255. Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation
  256. Multi-Modal Foundation Models for Computational Pathology: A Survey
  257. Differentiable Folding for Nearest Neighbor Model Optimization
  258. Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment
  259. Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information
  260. Implicit Contrastive Representation Learning with Guided Stop-gradient
  261. Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction
  262. Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data
  263. Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
  264. Discovering Influential Neuron Path in Vision Transformers
  265. Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction
  266. RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification
  267. Teaching LLMs How to Learn with Contextual Fine-Tuning
  268. Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs
  269. Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning
  270. Natural Humanoid Robot Locomotion with Generative Motion Prior
  271. Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal
  272. Word2winners at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
  273. Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement
  274. KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
  275. From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches
  276. DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation
  277. I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
  278. TetraGrip: Sensor-Driven Multi-Suction Reactive Object Manipulation in Cluttered Scenes
  279. Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection
  280. Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning
  281. Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection
  282. Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks
  283. Evaluation of state-of-the-art deep learning models in the segmentation of the heart ventricles in parasternal short-axis echocardiograms