mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 11 Mar 2025

455 papers

  1. The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  2. Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  3. Balancing SoC in Battery Cells using Safe Action PerturbationsDeep reinforcement learning methods → RL for energy, networks and operations
  4. Understanding the Quality-Diversity Trade-off in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  5. LinEAS: End-to-end Learning of Activation Steering with a Distributional LossMechanistic interpretability → Activation steering methods
  6. A Survey on Knowledge-Oriented Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  7. Identity Preserving Latent Diffusion for Brain Aging ModelingDiffusion models → Medical imaging and segmentation
  8. Adaptive Anomaly Recovery for Telemanipulation: A Diffusion Model Approach to Vision-Based TrackingDiffusion models → Diffusion and flow policies for robotics
  9. CASteer: Cross-Attention Steering for Controllable Concept ErasureDiffusion models → Robustness, privacy and adversarial aspects
  10. Multiplayer Information Asymmetric Contextual BanditsDeep reinforcement learning methods → RL theory and sample complexity
  11. Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  12. Beam Selection in ISAC using Contextual Bandit with Multi-modal Transformer and Transfer LearningDeep reinforcement learning methods → RL for energy, networks and operations
  13. Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative ModelDeep reinforcement learning methods → RL theory and sample complexity
  14. Backtracking for SafetyLLM safety and security → Safety alignment, refusal and guardrails
  15. Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  16. PlainQAFact: Retrieval-augmented Factual Consistency Evaluation Metric for Biomedical Plain Language SummarizationRetrieval-augmented generation → Medical and biomedical RAG
  17. SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  18. Imitation Learning of Correlated Policies in Stackelberg GamesOffline RL and imitation learning from data → Imitation learning methods
  19. LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  20. Meta-Reinforcement Learning with Discrete World Models for Adaptive Load BalancingWorld models → Latent dynamics models and model-based RL +1
  21. Zero-Shot Action Generalization with Limited ObservationsDeep reinforcement learning methods → Deep RL algorithms and representations
  22. SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory PredictionsDiffusion models → Diffusion and flow policies for robotics
  23. Combining Local Symmetry Exploitation and Reinforcement Learning for Optimised Probabilistic Inference -- A Work In ProgressDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. Towards Interpretable Protein Structure Prediction with Sparse AutoencodersMechanistic interpretability → Interpreting biomedical and science models
  25. Neurosymbolic Decision TreesLLM reasoning → Reasoning benchmarks and evaluation
  26. Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
  27. Oasis: One Image is All You Need for Multimodal Instruction Data SynthesisMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  28. Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  29. Preserving Product Fidelity in Large Scale Image Recontextualization with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  30. Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy ReuseDeep reinforcement learning methods → RL for autonomous driving and traffic
  31. QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video ComprehensionEfficient LLM inference and serving → Visual token pruning in multimodal models
  32. Chain-of-Thought Reasoning In The Wild Is Not Always FaithfulLLM reasoning → Prompting and chain-of-thought reasoning
  33. OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal InpaintingDiffusion models → 3D, point cloud and scene generation
  34. Language-Depth Navigated Thermal and Visible Image FusionDiffusion models → 3D, point cloud and scene generation
  35. SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and ConstraintsLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. REGEN: Learning Compact Video Embedding with (Re-)Generative DecoderDiffusion models → Video generation
  37. MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh AttentionDiffusion models → 3D, point cloud and scene generation
  38. MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal InputDiffusion models → 3D, point cloud and scene generation
  39. Rethinking Diffusion Model in High DimensionDiffusion models → Diffusion foundations and sampling
  40. How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?LLM safety and security → Machine unlearning
  41. LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  42. HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single DecoderEnd-to-end autonomous driving → End-to-end system architecture
  43. Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled SamplingDiffusion models → Video generation
  44. HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  45. RAG-Adapter: A Plug-and-Play RAG-enhanced Framework for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  46. Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank AdaptationDiffusion models → Image generation, text-to-image and editing
  47. DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking ProcessLLM reasoning → Knowledge- and tool-augmented reasoning
  48. MoE-Loco: Mixture of Experts for Multitask LocomotionMixture-of-experts → MoE in reinforcement learning and robotics
  49. ComicsPAP: understanding comic strips by picking the correct panelMultimodal LLMs / vision-language models → Image editing and quality assessment
  50. Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  51. Reasoning and Sampling-Augmented MCQ Difficulty Prediction via LLMsLLM reasoning → Reasoning benchmarks and evaluation
  52. TLA: Tactile-Language-Action Model for Contact-Rich ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  53. End-to-End PET Image Reconstruction via a Posterior-Mean Diffusion ModelDiffusion models → Medical imaging and segmentation
  54. Mellow: a small audio language model for reasoningLLM reasoning → Audio-language model reasoning
  55. Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidationLLM reasoning → Clinical and biomedical applications
  56. GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent TrainingLLM reasoning → Multimodal reasoning +1
  57. LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task PlanningLLM reasoning → Spatial and embodied reasoning
  58. MMRL: Multi-Modal Representation Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  59. PhysVLM: Enabling Visual Language Models to Understand Robotic Physical ReachabilityMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  60. Soft Actor-Critic-based Control Barrier Adaptation for Robust Autonomous Navigation in Unknown EnvironmentsDeep reinforcement learning methods → Safe and constrained RL
  61. Accelerating MoE Model Inference with Expert ShardingMixture-of-experts → Efficient MoE training and inference systems
  62. FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression FrameworkEfficient LLM inference and serving → KV cache optimization
  63. Controlling Latent Diffusion Using Latent CLIPDiffusion models → Diffusion foundations and sampling
  64. Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  65. Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive SensingDiffusion models → Inverse problems and image restoration
  66. AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion ModelsDiffusion models → Video generation
  67. TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference SystemsEfficient LLM inference and serving → Serving systems and request scheduling
  68. Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political InformationLLM safety and security → Safety alignment, refusal and guardrails
  69. OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval LearningRetrieval-augmented generation → RAG pipeline design and evaluation
  70. DyArtbank: Diverse Artistic Style Transfer via Pre-trained Stable Diffusion and Dynamic Style Prompt ArtbankDiffusion models → Image generation, text-to-image and editing
  71. V-Max: A Reinforcement Learning Framework for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  72. Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  73. Debiased Prompt Tuning in Vision-Language Model without AnnotationsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  74. LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series StructuresDeep reinforcement learning methods → RL for robot locomotion and manipulation
  75. Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image SynthesisDiffusion models → Medical imaging and segmentation
  76. Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  77. Diffusion Transformer Meets Random Masks: An Advanced PET Reconstruction FrameworkDiffusion models → Medical imaging and segmentation
  78. Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  79. MINT-Demo: Membership Inference Test DemonstratorLLM safety and security → Membership inference attacks
  80. KiteRunner: Language-Driven Cooperative Local-Global Navigation Policy with UAV Mapping in Outdoor EnvironmentsLLM reasoning → Spatial and embodied reasoning
  81. Evaluating Interpretable Reinforcement Learning by Distilling Policies into ProgramsDeep reinforcement learning methods → Interpretable and logic-guided RL
  82. Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving ScenariosWorld models → World models for autonomous driving
  83. Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic FrameworkLLM reasoning → Multimodal reasoning +2
  84. RFLAV: Rolling Flow matching for infinite Audio Video generationDiffusion models → Audio, speech and music
  85. General-Purpose Aerial Intelligent Agents Empowered by Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
  86. Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  87. Preference-Based Alignment of Discrete Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  88. OminiControl2: Efficient Conditioning for Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  89. Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph PolicyDeep reinforcement learning methods → RL for robot navigation and UAV control
  90. SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  91. Aligning Text to Image in Diffusion Models is Easier Than You ThinkDiffusion models → Image generation, text-to-image and editing +1
  92. HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied AgentsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  93. Modeling Variants of Prompts for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  94. EgoBlind: Towards Egocentric Visual Assistance for the BlindMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  95. MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion PriorDiffusion models → 3D, point cloud and scene generation
  96. Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  97. DeepRAG: Building a Custom Hindi Embedding Model for Retrieval Augmented Generation from ScratchRetrieval-augmented generation → RAG pipeline design and evaluation
  98. Route Sparse Autoencoder to Interpret Large Language ModelsMechanistic interpretability → SAE features and their applications
  99. A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
  100. Dialogue Injection Attack: Jailbreaking LLMs through Context ManipulationLLM safety and security → Jailbreaking
All 455
  1. Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
  2. ProtTeX: Structure-In-Context Reasoning and Editing of Proteins with Large Language ModelsLLM reasoning → Clinical and biomedical applications
  3. Privacy-Enhancing Paradigms within Federated Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  4. Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case StudyLLM reasoning → Spatial and embodied reasoning
  5. FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive FeedbackEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  6. U-StyDiT: Ultra-high Quality Artistic Style Transfer Using Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  7. Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT MethodMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  8. FlowDPS: Flow-Driven Posterior Sampling for Inverse ProblemsDiffusion models → Flow matching, time series and science
  9. Toward Stable World Models: Measuring and Addressing World Instability in Generative EnvironmentsWorld models → Video-generation world models and simulators
  10. Convergence Dynamics and Stabilization Strategies of Co-Evolving Generative ModelsSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  11. ACE: Concept Editing in Diffusion Models without Performance DegradationDiffusion models → Robustness, privacy and adversarial aspects
  12. Seeing Beyond Haze: Generative Nighttime Image DehazingDiffusion models → Inverse problems and image restoration
  13. STGDPM:Vessel Trajectory Prediction with Spatio-Temporal Graph Diffusion Probabilistic ModelDiffusion models → Diffusion and flow policies for robotics
  14. Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning GuidelinesLLM reasoning → LLM reasoning for recommendation
  15. LongProLIP: A Probabilistic Vision-Language Model with Long Context TextMultimodal LLMs / vision-language models → Video understanding with MLLMs
  16. Structural and Statistical Texture Knowledge Distillation and Learning for SegmentationKnowledge distillation → Detection and dense prediction distillation
  17. Generalized Kullback-Leibler Divergence LossKnowledge distillation → General knowledge distillation methods
  18. Group Preference Alignment: Customized LLM Response Generation from In-Situ ConversationsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  19. HOFAR: High-Order Augmentation of Flow Autoregressive TransformersDiffusion models → Diffusion foundations and sampling
  20. Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation LearningOffline RL and imitation learning from data → Real-world robot offline RL
  21. Computational bottlenecks for denoising diffusionsDiffusion models → Diffusion foundations and sampling
  22. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue AgentsLLM agents and tool use → Agent memory systems
  23. Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  24. A Three-Dimensional Pursuit-Evasion Game Based on Fuzzy Actor-Critic Learning AlgorithmDeep reinforcement learning methods → RL for robot navigation and UAV control
  25. MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +1
  26. CDI3D: Cross-guided Dense-view Interpolation for 3D ReconstructionDiffusion models → 3D, point cloud and scene generation
  27. Provable Zero-Shot Generalization in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  28. TRACE: Your Diffusion Model is Secretly an Instance Edge DetectorDiffusion models → Medical imaging and segmentation
  29. EFPC: Towards Efficient and Flexible Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
  30. LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim VerificationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  31. A Theory of Learning with Autoregressive Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  32. Perturbation Analysis of Singular Values in Concatenated Matrices
  33. Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation
  34. From Occurrence to Consequence: A Comprehensive Data-driven Analysis of Building Fire Risk
  35. Neural Learning Rules from Associative Networks Theory
  36. Stakeholder Perspectives on Whether and How Social Robots Can Support Mediation and Advocacy for Higher Education Students with Disabilities
  37. Llms, Virtual Users, and Bias: Predicting Any Survey Question Without Human Data
  38. Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking
  39. Acceptance or Rejection of Lots while Minimizing and Controlling Type I and Type II Errors
  40. Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition
  41. Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
  42. Is Limited Participant Diversity Impeding EEG-based Machine Learning?
  43. Finger-to-Chest Style Transfer-assisted Deep Learning Method For Photoplethysmogram Waveform Restoration with Timing Preservation
  44. TransECG: Leveraging Transformers for Explainable ECG Re-identification Risk Analysis
  45. Generalization of Video-Based Heart Rate Estimation Methods To Low Illumination and Elevated Heart Rates
  46. MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation
  47. VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation
  48. Open-World Skill Discovery from Unsegmented Demonstrations
  49. VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
  50. FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting
  51. Certainly Bot Or Not? Trustworthy Social Bot Detection via Robust Multi-Modal Neural Processes
  52. Learning second-order TVD flux limiters using differentiable solvers
  53. Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
  54. Explainable Quantum Machine Learning for Multispectral Images Segmentation: Case Study
  55. Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
  56. An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR
  57. Data-driven Nonlinear Modal Analysis with Physics-constrained Deep Learning: Numerical and Experimental Study
  58. FP3: A 3D Foundation Policy for Robotic Manipulation
  59. KAN-Mixers: a new deep learning architecture for image classification
  60. Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing
  61. PromptGAR: Flexible Promptive Group Activity Recognition
  62. Acoustic Neural 3D Reconstruction Under Pose Drift
  63. HessianForge: Scalable LiDAR reconstruction with Physics-Informed Neural Representation and Smoothness Energy Constraints
  64. The Detection of Saccadic Eye Movements and Per-Eye Comparisons using Virtual Reality Eye Tracking Devices
  65. Enhancing Large Language Models for Hardware Verification: A Novel SystemVerilog Assertion Dataset
  66. Revisiting Frank-Wolfe for Structured Nonconvex Optimization
  67. Multilevel Generative Samplers for Investigating Critical Phenomena
  68. Robust Unsupervised Fault Diagnosis For High-Dimensional Nonlinear Noisy Data
  69. Reconstruct Anything Model: a lightweight general model for computational imaging
  70. Interpreting the Repeated Token Phenomenon in Large Language Models
  71. From Models To Experiments: Shallow Recurrent Decoder Networks on the DYNASTY Experimental Facility
  72. Towards Efficient Parametric State Estimation in Circulating Fuel Reactors with Shallow Recurrent Decoder Networks
  73. A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimation
  74. Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms
  75. EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
  76. Comprehensive Benchmarking of Machine Learning Methods for Risk Prediction Modelling from Large-Scale Survival Data: A UK Biobank Study
  77. Smoothing ADMM for Non-convex and Non-smooth Hierarchical Federated Learning
  78. Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs
  79. Learning Pareto manifolds in high dimensions: How can regularization help?
  80. Keypoint Semantic Integration for Improved Feature Matching in Outdoor Agricultural Environments
  81. Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs
  82. PUMA: Learning a Mutation-Aware Vocabulary of Protein Units
  83. Seal Your Backdoor with Variational Defense
  84. ResBench: Benchmarking LLM-Generated FPGA Designs with Resource Awareness
  85. Residual Learning and Filtering Networks for End-to-End Lossless Video Compression
  86. Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
  87. Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining
  88. ESNLIR: A Spanish Multi-Genre Dataset with Causal Relationships
  89. Augmented Reality-based Guidance with Deformable Registration in Head and Neck Tumor Resection
  90. Enhanced Estimation Techniques for Certified Radii in Randomized Smoothing
  91. Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction
  92. Robust Multi-Objective Controlled Decoding of Large Language Models
  93. Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes
  94. QUIET-SR: Quantum Image Enhancement Transformer for Single Image Super-Resolution
  95. Automatic welding detection by an intelligent tool pipe inspection
  96. Frequency selection for the diagnostic characterization of human brain tumours
  97. Large Neighborhood Search and Bitmask Dynamic Programming for Wireless Mobile Charging Electric Vehicle Routing Problems in Medical Transportation
  98. Exposing Product Bias in LLM Investment Recommendation
  99. Source-free domain adaptation based on label reliability for cross-domain bearing fault diagnosis
  100. Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms
  101. Neural Network for Blind Unmixing: a novel MatrixConv Unmixing (MCU) Approach
  102. HeGMN: Heterogeneous Graph Matching Network for Learning Graph Similarity
  103. Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model
  104. A Bi-channel Aided Stitching of Atomic Force Microscopy Images
  105. Zero-to-One IDV: A Conceptual Model for AI-Powered Identity Verification
  106. Quantifying Circadian Desynchrony in ICU Patients and Its Association with Delirium
  107. FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methods
  108. Training Plug-n-Play Knowledge Modules with Deep Context Distillation
  109. SIMAC: A Semantic-Driven Integrated Multimodal Sensing And Communication Framework
  110. The Algorithmic State Architecture (ASA): An Integrated Framework for AI-Enabled Government
  111. OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
  112. "Principal Components" Enable A New Language of Images
  113. Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
  114. CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Driving
  115. Self-Taught Self-Correction for Small Language Models
  116. GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
  117. Understanding and Mitigating Distribution Shifts For Machine Learning Force Fields
  118. Keypoint Detection and Description for Raw Bayer Images
  119. SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
  120. Generating Robot Constitutions & Benchmarks for Semantic Safety
  121. Exploring the Word Sense Disambiguation Capabilities of Large Language Models
  122. Task-Oriented Co-Design of Communication, Computing, and Control for Edge-Enabled Industrial Cyber-Physical Systems
  123. Extra Clients at No Extra Cost: Overcome Data Heterogeneity in Federated Learning with Filter Decomposition
  124. Exploiting Instruction-Following Retrievers for Malicious Information Retrieval
  125. Coefficient-to-Basis Network: A Fine-Tunable Operator Learning Framework for Inverse Problems with Adaptive Discretizations and Theoretical Guarantees
  126. Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
  127. GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection
  128. YuE: Scaling Open Foundation Models for Long-Form Music Generation
  129. Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning
  130. SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
  131. Hierarchical autoregressive neural networks in three-dimensional statistical system
  132. Vision Transformer for Intracranial Hemorrhage Classification in CT Scans Using an Entropy-Aware Fuzzy Integral Strategy for Adaptive Scan-Level Decision Fusion
  133. A Grid Cell-Inspired Structured Vector Algebra for Cognitive Maps
  134. EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments
  135. CellStyle: Improved Zero-Shot Cell Segmentation via Style Transfer
  136. LiSu: A Dataset and Method for LiDAR Surface Normal Estimation
  137. NSF-SciFy: Mining the NSF Awards Database for Scientific Claims
  138. X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction
  139. PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
  140. Integration of nested cross-validation, automated hyperparameter optimization, high-performance computing to reduce and quantify the variance of test performance estimation of deep learning models
  141. BiasEdit: Debiasing Stereotyped Language Models via Model Editing
  142. MsaMIL-Net: An End-to-End Multi-Scale Aware Multiple Instance Learning Network for Efficient Whole Slide Image Classification
  143. Comparing Next-Day Wildfire Predictability of MODIS and VIIRS Satellite Data
  144. Sparsity-Induced Global Matrix Autoregressive Model with Auxiliary Network Data
  145. When Discourse Stalls: Moving Past Five Semantic Stopsigns about Generative AI in Design Research
  146. An Analysis of Safety Guarantees in Multi-Task Bayesian Optimization
  147. Transferring Extreme Subword Style Using Ngram Model-Based Logit Scaling
  148. GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas
  149. Deformable Linear Object Surface Placement Using Elastica Planning and Local Shape Control
  150. CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering
  151. ChromaFormer: A Scalable and Accurate Transformer Architecture for Land Cover Classification
  152. ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems
  153. Visual Attention Graph
  154. SignRep: Enhancing Self-Supervised Sign Representations
  155. Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency
  156. High-Quality 3D Head Reconstruction from Any Single Portrait Image
  157. Segmentation-Guided CT Synthesis with Pixel-Wise Conformal Uncertainty Bounds
  158. SAS: Segment Any 3D Scene with Integrated 2D Priors
  159. PCGS: Progressive Compression of 3D Gaussian Splatting
  160. External Knowledge Injection for CLIP-Based Class-Incremental Learning
  161. A Generative-AI Modeling Framework for Explainable Decision Support in Complex Geosteering Scenarios
  162. Referring to Any Person
  163. ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews
  164. CFNet: Optimizing Remote Sensing Change Detection through Content-Aware Enhancement
  165. The Space Between: On Folding, Symmetries and Sampling
  166. Learning to Match Unpaired Data with Minimum Entropy Coupling
  167. SuperCap: Multi-resolution Superpixel-based Image Captioning
  168. Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models
  169. A Triple-Inertial Accelerated Alternating Optimization Method for Deep Learning Training
  170. Test-Time 3D Occupancy Prediction
  171. Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum
  172. GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields
  173. A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling
  174. NullFace: Training-Free Localized Face Anonymization
  175. Data Driven Decision Making with Time Series and Spatio-temporal Data
  176. Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility
  177. TrackOcc: Camera-based 4D Panoptic Occupancy Tracking
  178. A Data Aggregation Visualization System supported by Processing-in-Memory
  179. Status and Future Prospects of the Standardization Framework Industry 4.0: A European Perspective
  180. Stick to Facts: Towards Fidelity-oriented Product Description Generation
  181. MinGRU-Based Encoder for Turbo Autoencoder Frameworks
  182. ICPR 2024 Competition on Rider Intention Prediction
  183. Accelerated Distributed Optimization with Compression and Error Feedback
  184. JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data
  185. Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
  186. Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview
  187. A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Media
  188. Uncertainty Quantification for Multi-fidelity Simulations
  189. WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images
  190. (θl, θu)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces
  191. Recognition-Synergistic Scene Text Editing
  192. Prototype-Based Multiple Instance Learning for Gigapixel Whole Slide Image Classification
  193. Twinner: Shining Light on Digital Twins in a Few Snaps
  194. InfluenceNet: AI Models for Banzhaf and Shapley Value Prediction
  195. JurisTCU: A Brazilian Portuguese Information Retrieval Dataset with Query Relevance Judgments
  196. Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens
  197. nnInteractive: Redefining 3D Promptable Segmentation
  198. Density Ratio-based Proxy Causal Learning Without Density Ratios
  199. Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking
  200. Embodied Crowd Counting
  201. Parametric Point Cloud Completion for Polygonal Surface Reconstruction
  202. 3D Medical Imaging Segmentation on Non-Contrast CT
  203. Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis
  204. Mitigating Ambiguities in 3D Classification with Gaussian Splatting
  205. Design and Implementation of FourCropNet: A CNN-Based System for Efficient Multi-Crop Disease Detection and Management
  206. DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
  207. Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields
  208. Prompt2LVideos: Exploring Prompts for Understanding Long-Form Multimodal Videos
  209. 1LoRA: Summation Compression for Very Low-Rank Adaptation
  210. MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting
  211. Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation
  212. Prototype-based Heterogeneous Federated Learning for Blade Icing Detection in Wind Turbines with Class Imbalanced Data
  213. Towards Scalable and Cross-Lingual Specialist Language Models for Oncology
  214. i-WiViG: Interpretable Window Vision GNN
  215. Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
  216. Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach
  217. ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals
  218. Energy Scale Degradation in Sparse Quantum Solvers: A Barrier to Quantum Utility
  219. Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study
  220. Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution
  221. A systematic literature review of unsupervised learning algorithms for anomalous traffic detection based on flows
  222. Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral
  223. SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation
  224. PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net
  225. Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
  226. LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
  227. HERO: Human Reaction Generation from Videos
  228. Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
  229. Massively Parallel Expectation Maximization For Approximate Posteriors
  230. DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
  231. MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection
  232. Dynamic DBSCAN with Euler Tour Sequences
  233. ExMAG: Learning of Maximally Ancestral Graphs
  234. Tangentially Aligned Integrated Gradients for User-Friendly Explanations
  235. EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification
  236. How good is PAC-Bayes at explaining generalisation?
  237. Investigating Execution-Aware Language Models for Code Optimization
  238. A Grey-box Text Attack Framework using Explainable AI
  239. HRAvatar: High-Quality and Relightable Gaussian Head Avatar
  240. CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning
  241. S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction
  242. Explaining Human Preferences via Metrics for Structured 3D Reconstruction
  243. Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?
  244. OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
  245. A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
  246. Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models
  247. Automating Violence Detection and Categorization from Ancient Texts
  248. RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware
  249. Physics-based AI methodology for Material Parameter Extraction from Optical Data
  250. Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation
  251. Towards All-in-One Medical Image Re-Identification
  252. CQVPR: Landmark-aware Contextual Queries for Visual Place Recognition
  253. TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement
  254. Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming
  255. Multimodal Generation of Animatable 3D Human Models with AvatarForge
  256. XAI4Extremes: An interpretable machine learning framework for understanding extreme-weather precursors under climate change
  257. OASIS: Order-Augmented Strategy for Improved Code Search
  258. Concept-Driven Deep Learning for Enhanced Protein-Specific Molecular Generation
  259. Mimicking How Humans Interpret Out-of-Context Sentences Through Controlled Toxicity Decoding
  260. Towards Large-scale Chemical Reaction Image Parsing via a Multimodal Large Language Model
  261. Domain Adaptation and Entanglement: an Optimal Transport Perspective
  262. S2A: A Unified Framework for Parameter and Memory Efficient Transfer Learning
  263. WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation
  264. Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding
  265. Few-Shot Class-Incremental Model Attribution Using Learnable Representation From CLIP-ViT Features
  266. FilmComposer: LLM-Driven Music Production for Silent Film Clips
  267. Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking
  268. A Framework for Reducing the Complexity of Geometric Vision Problems and its Application to Two-View Triangulation with Approximation Bounds
  269. Scaling Probabilistic Circuits via Data Partitioning
  270. HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
  271. ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting
  272. MGHanD: Multi-modal Guidance for authentic Hand Diffusion
  273. Large Scale Multi-Task Bayesian Optimization with Large Language Models
  274. AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
  275. UniF2ace: A Unified Fine-grained Face Understanding and Generation Model
  276. MaRI: Material Retrieval Integration across Domains
  277. Functional Unit: A New Perspective on Materials Science Research Paradigms
  278. Median Consensus Embedding for Dimensionality Reduction
  279. AI-native Memory 2.0: Second Me
  280. Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning
  281. Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
  282. Locally Private Nonparametric Contextual Multi-armed Bandits
  283. Evidential Uncertainty Probes for Graph Neural Networks
  284. MegaSR: Mining Customized Semantics and Expressive Guidance for Real-World Image Super-Resolution
  285. Denoising via Repainting: an image denoising method using layer wise medical image repainting
  286. MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction
  287. SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection
  288. Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions
  289. PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
  290. Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation
  291. Degradation Self-Supervised Learning for Lithium-ion Battery Health Diagnostics
  292. Advancing Sentiment Analysis: A Novel LSTM Framework with Multi-head Attention
  293. Trend-Aware Supervision: On Learning Invariance for Semi-Supervised Facial Action Unit Intensity Estimation
  294. MuCoS: Efficient Drug Target Discovery via Multi Context Aware Sampling in Knowledge Graphs
  295. GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
  296. Simulating Automotive Radar with Lidar and Camera Inputs
  297. Context-aware Biases for Length Extrapolation
  298. Continual Learning for Multiple Modalities
  299. ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation
  300. Symbolic Neural Ordinary Differential Equations
  301. Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
  302. DDO-IN: Dual Domains Optimization for Implicit Neural Network to Eliminate Motion Artifact in Magnetic Resonance Imaging
  303. Beyond Deepfake vs Real: Facial Deepfake Detection in the Open-Set Paradigm
  304. SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models
  305. Adapting Large Language Models for Parameter-Efficient Log Anomaly Detection
  306. LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data
  307. Accurate INT8 Training Through Dynamic Block-Level Fallback
  308. ObjectMover: Generative Object Movement with Video Prior
  309. Empirical Error Estimates for Graph Sparsification
  310. Learning to Search Effective Example Sequences for In-Context Learning
  311. Deep Perceptual Enhancement for Medical Image Analysis
  312. Dynamic PET Image Reconstruction via Non-negative INR Factorization
  313. AdaSCALE: Adaptive Scaling for OOD Detection
  314. Partial differential equation system for binarization of degraded document images
  315. SGNetPose+: Stepwise Goal-Driven Networks with Pose Information for Trajectory Prediction in Autonomous Driving
  316. GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals
  317. Exploring Bias in over 100 Text-to-Image Generative Models
  318. SKALD: Learning-Based Shot Assembly for Coherent Multi-Shot Video Creation
  319. A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects
  320. Injecting Imbalance Sensitivity for Multi-Task Learning
  321. Multiplayer Information Asymmetric Bandits in Metric Spaces
  322. Predicting and Understanding College Student Mental Health with Interpretable Machine Learning
  323. Efficient Dataset Distillation through Low-Rank Space Sampling
  324. SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic
  325. Almost Linear Time Consistent Mode Estimation and Quick Shift Clustering
  326. A Neural Symbolic Model for Space Physics
  327. LLM-Powered Knowledge Graphs for Enterprise Intelligence and Analytics
  328. Efficient and Accurate Estimation of Lipschitz Constants for Hybrid Quantum-Classical Decision Models
  329. Boundary Prompting: Elastic Urban Region Representation via Graph-based Spatial Tokenization
  330. Enhancing Multilingual Language Models for Code-Switched Input Data
  331. Regulatory DNA sequence Design with Reinforcement Learning
  332. Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning
  333. Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
  334. Boundary Regression for Leitmotif Detection in Music Audio
  335. Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approach
  336. 7ABAW-Compound Expression Recognition via Curriculum Learning
  337. LabelCoRank: Revolutionizing Long Tail Multi-Label Classification with Co-Occurrence Reranking
  338. Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification
  339. Hierarchical Contact-Rich Trajectory Optimization for Multi-Modal Manipulation using Tight Convex Relaxations
  340. Discriminative versus Generative Approaches to Simulation-based Inference
  341. Overlap-aware meta-learning attention to enhance hypergraph neural networks for node classification
  342. Recent Advances in Hypergraph Neural Networks
  343. Pre-trained Models Succeed in Medical Imaging with Representation Similarity Degradation
  344. NeRF-VIO: Map-Based Visual-Inertial Odometry with Initialization Leveraging Neural Radiance Fields
  345. Decoupled Cross-Modal Alignment Network for Text-RGBT Person Retrieval and A High-Quality Benchmark
  346. 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting
  347. Enhancing Sentiment Analysis through Multimodal Fusion: A BERT-DINOv2 Approach
  348. STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications
  349. BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes
  350. STRMs: Spatial Temporal Reasoning Models for Vision-Based Localization Rivaling GPS Precision
  351. CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
  352. Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures
  353. From Slices to Sequences: Autoregressive Tracking Transformer for Cohesive and Consistent 3D Lymph Node Detection in CT Scans
  354. The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course
  355. Learning Gentle Grasping Using Vision, Sound, and Touch