mlsanityData to 7 Oct 2026

Papers

New on arXiv

Thu 13 Mar 2025

397 papers

  1. FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  2. LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. RPO: Fine-Tuning Visual Generative Models via Rich Vision-Language PreferencesDiffusion models → Diffusion and flow policies for robotics +1
  4. OuroMamba: A Data-Free Quantization Framework for Vision MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  5. Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM HallucinationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  6. ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  7. OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM ResponsesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  8. Learning to Inference Adaptively for Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  9. Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSMState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  10. Taxonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable ClassificationRetrieval-augmented generation → Multimodal RAG
  11. Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language DataLLM reasoning → Time series reasoning
  12. Teamwork makes the dream work: LLMs-Based Agents for GitHub README.MD SummarizationLLM agents and tool use → Software engineering coding agents
  13. Mamba time series forecasting with uncertainty quantificationState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  14. TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  15. RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  16. Towards Understanding Graphical Perception in Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  17. Thinking Machines: A Survey of LLM based Reasoning StrategiesLLM reasoning → Reasoning benchmarks and evaluation
  18. MIP against Agent: Malicious Image Patches Hijacking Multimodal OS AgentsLLM agents and tool use → Agent threats, guardrails and governance
  19. Fixed-Point RNNs: Interpolating from Diagonal to DenseState-space sequence models (S4, Mamba) → Core SSM architectures for language
  20. The Power of One: A Single Example is All it Takes for Segmentation in VLMsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  21. Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  22. Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video ProcessingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  23. Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor CoresMixture-of-experts → MoE large language models
  24. RankPO: Preference Optimization for Job-Talent MatchingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  25. AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  26. ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMsEfficient LLM inference and serving → KV cache optimization
  27. GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and EditingLLM reasoning → Multimodal reasoning +1
  28. Studying Classifier(-Free) Guidance From a Classifier-Centric PerspectiveDiffusion models → Diffusion foundations and sampling
  29. Distilling Diversity and Control in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  30. The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based GenerationDiffusion models → Flow matching, time series and science
  31. A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  32. V2Edit: Versatile Video Diffusion Editor for Videos and 3D ScenesDiffusion models → Video generation
  33. HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action ModelVision-language-action models → Efficient VLA inference and adaptation
  34. SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific ProblemsLLM reasoning → Multimodal reasoning +1
  35. NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  36. DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  37. Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree SearchLLM safety and security → Jailbreaking
  38. DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image GenerationDiffusion models → Image generation, text-to-image and editing
  39. R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal FormalizationLLM reasoning → Multimodal reasoning
  40. CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image EditingDiffusion models → Image generation, text-to-image and editing +1
  41. MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene ReconstructionWorld models → World models for autonomous driving +1
  42. TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-InterventionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  43. CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion ModelsDiffusion models → Video generation
  44. Long Context Tuning for Video GenerationDiffusion models → Video generation
  45. Unlock the Power of Unlabeled Data in Language Driving ModelEnd-to-end autonomous driving → VLMs for autonomous driving
  46. VisualWebInstruct: Scaling up Multimodal Instruction Data through Web SearchMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  47. Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained ApproachLLM reasoning → Mathematical reasoning
  48. Autoregressive Image Generation with Randomized Parallel DecodingEfficient LLM inference and serving → Fast autoregressive visual generation
  49. ASIDE: Architectural Separation of Instructions and Data in Language ModelsLLM safety and security → Prompt injection and agent security
  50. Controllable Adversarial Makeup for Privacy via Text-Guided DiffusionDiffusion models → Robustness, privacy and adversarial aspects
  51. KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  52. PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  53. TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  54. MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model EvaluationLLM reasoning → Reasoning benchmarks and evaluation
  55. World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task PlanningWorld models → World models for navigation +2
  56. Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and BeyondLLM reasoning → Reasoning benchmarks and evaluation +1
  57. 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  58. Learning Personalized Driving Styles via Reinforcement Learning from Human FeedbackEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  59. VisTW: Benchmarking Vision-Language Models for Traditional Chinese in TaiwanMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. Category Prompt Mamba Network for Nuclei Segmentation and ClassificationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  61. dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data AnalysisMixture-of-experts → Federated mixture-of-experts
  62. Out-of-Context Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  63. Hyper3D: Efficient 3D Representation via Hybrid Triplane and Octree Feature for Enhanced 3D Shape Variational Auto-EncodersDiffusion models → 3D, point cloud and scene generation
  64. RoMA: Scaling up Mamba-based Foundation Models for Remote SensingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  65. CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based GuidanceDiffusion models → Video generation
  66. Probabilistic Forecasting via Autoregressive Flow MatchingDiffusion models → Flow matching, time series and science
  67. LUMOS: Language-Conditioned Imitation Learning with World ModelsWorld models → Embodied and robot world models +1
  68. New Trends for Modern Machine Translation with Large Reasoning ModelsLLM reasoning → Reasoning benchmarks and evaluation
  69. Enhancing Facial Privacy Protection via Weakening Diffusion PurificationDiffusion models → Robustness, privacy and adversarial aspects
  70. DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single ImageDiffusion models → Video generation
  71. KV-Distill: Nearly Lossless Learnable Context Compression for LLMsEfficient LLM inference and serving → Prompt and context compression
  72. Collaborative Speculative Inference for Efficient LLM Inference ServingEfficient LLM inference and serving → Speculative decoding
  73. Towards Fast, Memory-based and Data-Efficient Vision-Language PolicyMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  74. CoDiPhy: A General Framework for Applying Denoising Diffusion Models to the Physical Layer of Wireless Communication SystemsDiffusion models → Diffusion for compression and wireless
  75. CODEI: Resource-Efficient Task-Driven Co-Design of Perception and Decision Making for Mobile Robots Applied to Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  76. VisualPRM: An Effective Process Reward Model for Multimodal ReasoningLLM reasoning → Multimodal reasoning +2
  77. Targeted Data Poisoning for Black-Box Audio Datasets Ownership VerificationLLM safety and security → Backdoor and data poisoning attacks
  78. SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video AnalysisLLM reasoning → Clinical and biomedical applications +1
  79. LLM Agents Display Human Biases but Exhibit Distinct Learning PatternsLLM agents and tool use → Social simulation and multi-agent debate
  80. SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal ReasoningLLM reasoning → Reasoning for agents, planning and code
  81. Policy Teaching via Data Poisoning in Learning from Human PreferencesLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  82. Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURALLM reasoning → Spatial and embodied reasoning
  83. Probability-Flow ODE in Infinite-Dimensional Function SpacesDiffusion models → Diffusion foundations and sampling
  84. CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and RecognitionDiffusion models → Medical imaging and segmentation
  85. MouseGPT: A Large-scale Vision-Language Model for Mouse Behavior AnalysisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  86. LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM AgentsLLM agents and tool use → Multimodal and embodied agents
  87. Red Teaming Contemporary AI Models: Insights from Spanish and Basque PerspectivesLLM safety and security → Prompt injection and agent security
  88. Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  89. "Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection DecodingLLM reasoning → Prompting and chain-of-thought reasoning
  90. ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective ReasoningMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  91. Data augmentation using diffusion models to enhance inverse Ising inferenceDiffusion models → Diffusion foundations and sampling
  92. A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  93. Retrieval-Augmented Generation with Hierarchical KnowledgeRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  94. Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  95. PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  96. Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image GenerationDiffusion models → Image generation, text-to-image and editing
  97. Hybrid Agents for Image RestorationLLM agents and tool use → Multimodal and embodied agents
  98. IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  99. StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-ErrorLLM agents and tool use → Educational agents and math problem solving
  100. Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal SpaceState-space sequence models (S4, Mamba) → Speech and audio SSMs
All 397
  1. Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online TextLLM reasoning → Clinical and biomedical applications
  2. Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward ModelingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  3. AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention DisruptionDiffusion models → Robustness, privacy and adversarial aspects
  4. Bayesian Prompt Flow Learning for Zero-Shot Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  5. Information Density Principle for MLLM BenchmarksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  6. Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLMLLM agents and tool use → Tool learning and function calling
  7. Provably Secure Covert Messaging Using Image-based Diffusion ProcessesDiffusion models → Robustness, privacy and adversarial aspects
  8. Compute Optimal Scaling of Skills: Knowledge vs ReasoningLLM reasoning → Test-time compute and efficient thinking
  9. Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model RepresentationsState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  10. Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based PolicyLLM agents and tool use → Reinforcement learning for LLM agents
  11. EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning AbilityLLM reasoning → Multimodal reasoning +1
  12. Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate DecompositionDiffusion models → Image generation, text-to-image and editing
  13. OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLMLLM reasoning → Reasoning for agents, planning and code +1
  14. Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor ScenesDiffusion models → 3D, point cloud and scene generation
  15. Style Evolving along Chain-of-Thought for Unknown-Domain Object DetectionLLM reasoning → Multimodal reasoning
  16. ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist ContentMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  17. MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based DistillationDiffusion models → Diffusion and flow policies for robotics
  18. Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion TransformersDiffusion models → Audio, speech and music
  19. VideoMerge: Towards Training-free Long Video GenerationDiffusion models → Video generation
  20. PluralLLM: Pluralistic Alignment in LLMs via Federated LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  21. Inter-environmental world modeling for continuous and compositional dynamicsWorld models → Embodied and robot world models
  22. CUBETESTERAI: Automated JUnit Test Generation using the LLaMA Model
  23. Enhancing Aviation Communication Transcription: Fine-Tuning Distil-Whisper with LoRA
  24. Accurate, provable and fast polychromatic tomographic reconstruction: A variational inequality approach
  25. Fewer Than 1% of Explainable AI Papers Validate Explainability with Humans
  26. Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation
  27. MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
  28. It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education
  29. NeurIPS 2023 LLM Efficiency Fine-tuning Competition
  30. The Role of Hyperparameters in Predictive Multiplicity
  31. Ensemble Learning for Large Language Models in Text and Code Generation: A Survey
  32. CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception
  33. The Relativity of Causal Knowledge
  34. Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks
  35. Predicting Stock Movement with BERTweet and Transformers
  36. Empirical Computation: Prompting versus Programming
  37. DNA Origami Nanostructures Observed in Transmission Electron Microscopy Images can be Characterized through Convolutional Neural Networks
  38. Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics
  39. Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
  40. Phishsense-1B: A Technical Perspective on an AI-Powered Phishing Detection Model
  41. Automated Tomato Maturity Estimation Using an Optimized Residual Model with Pruning and Quantization Techniques
  42. Multi-Domain Biometric Recognition using Body Embeddings
  43. Predicting Clinical Outcomes with Waveform LSTMs
  44. Resource Heterogeneity-Aware and Utilization-Enhanced Scheduling for Deep Learning Clusters
  45. PolyRoof: Precision Roof Polygonization in Urban Residential Building with Graph Neural Networks
  46. JPEG Compliant Compression for Both Human and Machine, A Report
  47. Ecological Neural Architecture Search
  48. H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic
  49. Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs
  50. HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
  51. SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable
  52. Task-Specific Activation Functions for Neuroevolution using Grammatical Evolution
  53. Convolutional Rectangular Attention Module
  54. Evaluating a Novel Neuroevolution and Neural Architecture Search System
  55. Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers
  56. Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
  57. Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
  58. Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?
  59. Lessons from the trenches on evaluating machine-learning systems in materials science
  60. Exploiting Concavity Information in Gaussian Process Contextual Bandit Optimization
  61. On the Identifiability of Causal Abstractions
  62. Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Size
  63. Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science
  64. Byzantine-Resilient Federated Learning via Distributed Optimization
  65. Data Caricatures: On the Representation of African American Language in Pretraining Corpora
  66. Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview
  67. Large-scale Pre-training for Grounded Video Caption Generation
  68. HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer
  69. Learn then Decide: A Learning Approach for Designing Data Marketplaces
  70. FlowTok: Flowing Seamlessly Across Text and Image Tokens
  71. Clothes-Changing Person Re-identification Based On Skeleton Dynamics
  72. Unifying 2D and 3D Vision-Language Understanding
  73. Predicting Treatment Response in Body Dysmorphic Disorder with Interpretable Machine Learning
  74. Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
  75. Visual Polarization Measurement Using Counterfactual Image Generation
  76. Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization
  77. OCPM2: Extending the Process Mining Methodology for Object-Centric Event Data Extraction
  78. TAU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection
  79. Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage
  80. Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images
  81. 3D Extended Object Tracking based on Extruded B-Spline Side View Profiles
  82. Numerical and statistical analysis of NeuralODE with Runge-Kutta time integration
  83. DarkBench: Benchmarking Dark Patterns in Large Language Models
  84. Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models
  85. Prototype-Guided Cross-Modal Knowledge Enhancement for Adaptive Survival Prediction
  86. Real-time Pollutant Identification through Optical PM Micro-Sensor
  87. TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics
  88. From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
  89. Long-Video Audio Synthesis with Multi-Agent Collaboration
  90. Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models
  91. Deep Learning-Based Automated Workflow for Accurate Segmentation and Measurement of Abdominal Organs in CT Scans
  92. HiCMamba: Enhancing Hi-C Resolution and Identifying 3D Genome Structures with State Space Modeling
  93. We Should Chart an Atlas of All the World's Models
  94. Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?
  95. UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
  96. Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
  97. Uncertainty in Action: Confidence Elicitation in Embodied Agents
  98. LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
  99. ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
  100. Transformers without Normalization
  101. From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM
  102. Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models
  103. OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
  104. ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer
  105. OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction
  106. Technical Approach for the EMI Challenge in the 8th Affective Behavior Analysis in-the-Wild Competition
  107. GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
  108. GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
  109. Poly-MgNet: Polynomial Building Blocks in Multigrid-Inspired ResNets
  110. The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity
  111. On the Injective Norm of Sums of Random Tensors and the Moments of Gaussian Chaoses
  112. Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection
  113. Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
  114. Radar: Fast Long-Context Decoding for Any Transformer
  115. FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis
  116. VisionLogic: Discovering and Grounding Decision-Relevant Visual Concepts
  117. From Linear to Spline-Based Classification:Developing and Enhancing SMPA for Noisy Non-Linear Datasets
  118. DP-GPL: Differentially Private Graph Prompt Learning
  119. Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More
  120. GBSVR: Granular Ball Support Vector Regression
  121. Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  122. The Impact of Item-Writing Flaws on Difficulty and Discrimination in Item Response Theory
  123. Lightweight Models for Emotional Analysis in Video
  124. Evaluating structural uncertainty in accelerated MRI: are voxelwise measures useful surrogates?
  125. NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
  126. Interactive Multimodal Fusion with Temporal Modeling
  127. AudioX: A Unified Framework for Anything-to-Audio Generation
  128. CountPath: Automating Fragment Counting in Digital Pathology
  129. Why the Brain Cannot Be a Digital Computer: History-Dependence and the Computational Limits of Consciousness
  130. Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
  131. Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression
  132. Extreme Learning Machines for Attention-based Multiple Instance Learning in Whole-Slide Image Classification
  133. From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
  134. Hoi2Threat: An Interpretable Threat Detection Method for Human Violence Scenarios Guided by Human-Object Interaction
  135. Sample Compression for Self Certified Continual Learning
  136. OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
  137. Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks
  138. Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents
  139. Meta-learning characteristics and dynamics of quantum systems
  140. Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling
  141. Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion
  142. LLMs in Disease Diagnosis: A Comparative Study of DeepSeek-R1 and O3 Mini Across Chronic Health Conditions
  143. DeclareAligner: A Leap Towards Efficient Optimal Alignments for Declarative Process Model Conformance Checking
  144. Applying Tabular Deep Learning Models to Estimate Crash Injury Types of Young Motorcyclists
  145. Siamese Foundation Models for Crystal Structure Prediction
  146. Statistical Analysis of Sentence Structures through ASCII, Lexical Alignment and PCA
  147. Deep Learning based discovery of Integrable Systems
  148. OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
  149. SortingEnv: An Extendable RL-Environment for an Industrial Sorting Process
  150. Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
  151. Sentiment Analysis in SemEval: A Review of Sentiment Identification Approaches
  152. DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation
  153. Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking
  154. Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings
  155. Learning Disease State from Noisy Ordinal Disease Progression Labels
  156. EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
  157. BeamLLM: Vision-Empowered mmWave Beam Prediction with Large Language Models
  158. Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
  159. Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data
  160. Improving Medical Waste Classification with Hybrid Capsule Networks
  161. Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems
  162. RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation
  163. RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
  164. Architecture-Aware Minimization (A2M): How to Find Flat Minima in Neural Architecture Search
  165. HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition
  166. Multi-thresholding Good Arm Identification with Bandit Feedback
  167. Subgroup Performance Analysis in Hidden Stratifications
  168. A Multimodal Fusion Model Leveraging MLP Mixer and Handcrafted Features-based Deep Learning Networks for Facial Palsy Detection
  169. Large-Small Model Collaboration for Enhancing Edge-Deployed Small Models
  170. Piece it Together: Part-Based Concepting with IP-Priors
  171. BioSerenity-E1: a self-supervised EEG model for medical applications
  172. ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
  173. Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark
  174. Object detection characteristics in a learning factory environment using YOLOv8
  175. A Hybrid Architecture with Efficient Fine Tuning for Abstractive Patent Document Summarization
  176. Safe exploration in reproducing kernel Hilbert spaces
  177. Mirror Online Conformal Prediction with Intermittent Feedback
  178. Characterizing Nonlinear Dynamics via Smooth Prototype Equivalences
  179. Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddings
  180. OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions
  181. IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification
  182. Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning
  183. An Ensemble-Based Two-Step Framework for Classification of Pap Smear Cell Images
  184. Capturing Semantic Flow of ML-based Systems
  185. 6D Object Pose Tracking in Internet Videos for Robotic Manipulation
  186. Eye on the Target: Eye Tracking Meets Rodent Tracking
  187. Large-Scale Auto-bidding with Nash Equilibrium Constraints
  188. Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech
  189. Wikipedia is Not a Dictionary, Delete! Text Classification as a Proxy for Analysing Wiki Deletion Discussions
  190. MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
  191. MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment
  192. VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames
  193. PyGDA: A Python Library for Graph Domain Adaptation
  194. HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings
  195. Robust Learning-Based Sparse Recovery for Device Activity Detection in Grant-Free Random Access Cell-Free Massive MIMO: Enhancing Resilience to Impairments
  196. Numerically robust Gaussian state estimation with singular observation noise
  197. Climate land use and other drivers impacts on island ecosystem services: a global review
  198. Resource efficient data transmission on animals based on machine learning
  199. EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
  200. An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)
  201. A Multi-Modal Federated Learning Framework for Remote Sensing Image Classification
  202. Markerless Tracking-Based Registration for Medical Image Motion Correction
  203. KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception
  204. AMR-Transformer: Enabling Efficient Long-range Interaction for Complex Neural Fluid Simulation
  205. ROODI: Reconstructing Occluded Objects with Denoising Inpainters
  206. PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Burst-Sampled Spatiotemporal Dynamics
  207. SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
  208. Numerical stability analysis of large language models
  209. Interpretable Image Classification via Non-parametric Part Prototype Learning
  210. MinorBench: A hand-built benchmark for content-based risks for children
  211. Spherical dimension
  212. ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents
  213. Flows on convex polytopes
  214. R.U.Psycho? Robust Unified Psychometric Testing of Language Models
  215. Assessing the validity of new paradigmatic complexity measures as criterial features for proficiency in L2 writings in English
  216. Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
  217. Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout
  218. Adaptive Preference Aggregation
  219. Singular Value Fine-tuning for Few-Shot Class-Incremental Learning
  220. Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation
  221. TARS: Traffic-Aware Radar Scene Flow Estimation
  222. Deep Learning for Time Series Forecasting: A Survey
  223. Predicting Chemical Reaction Outcomes Based on Electron Movements Using Machine Learning
  224. ST-FlowNet: An Efficient Spiking Neural Network for Event-Based Optical Flow Estimation
  225. Robustness Tokens: Towards Adversarial Robustness of Transformers
  226. Convergence and Connectivity: Dynamics of Multi-Agent Q-Learning in Random Networks
  227. PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning
  228. GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction
  229. Automatic quality control in multi-centric fetal brain MRI super-resolution reconstruction
  230. Unlocking Generalization Power in LiDAR Point Cloud Registration
  231. 3D Student Splatting and Scooping
  232. Multiplicative learning from observation-prediction ratios
  233. GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping
  234. Are Convex Optimization Curves Convex?
  235. Deep Learning-Based Direct Leaf Area Estimation using Two RGBD Datasets for Model Development
  236. An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer
  237. Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection
  238. MoEdit: On Learning Quantity Perception for Multi-object Image Editing
  239. Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing
  240. Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion
  241. Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation
  242. Geometric Parameter Estimations of Perovskite Solar Cells Based on Optical Simulations
  243. SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning
  244. A Self-supervised Motion Representation for Portrait Video Generation
  245. Semantic Synergy: Unlocking Policy Insights and Learning Pathways Through Advanced Skill Mapping
  246. Enhanced Route Planning with Calibrated Uncertainty Set
  247. Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs
  248. Image Quality Assessment: From Human to Machine Preference
  249. VMBench: A Benchmark for Perception-Aligned Video Motion Generation
  250. Parallelizing Multi-objective A* Search
  251. Impact of buckypaper on the mechanical properties and failure modes of composites
  252. AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI
  253. SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation
  254. PanDx: AI-assisted Early Detection of Pancreatic Ductal Adenocarcinoma on Contrast-enhanced CT
  255. Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
  256. Deep Learning Approaches for Anti-Money Laundering on Mobile Transactions: Review, Framework, and Directions
  257. Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributes
  258. DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks
  259. Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate Rollout
  260. Dual-domain Modulation Network for Lightweight Image Super-Resolution
  261. CPLOYO: A Pulmonary Nodule Detection Model with Multi-Scale Feature Fusion and Nonlinear Feature Learning
  262. FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution
  263. Rapid analysis of point-contact Andreev reflection spectra via machine learning with adaptive data augmentation
  264. V2X-ReaLO: An Open Online Framework and Dataset for Cooperative Perception in Reality
  265. A Neumann-Neumann Acceleration with Coarse Space for Domain Decomposition of Extreme Learning Machines
  266. Post-disaster building indoor damage and survivor detection using autonomous path planning and deep learning with unmanned aerial vehicles
  267. Using Context to Improve Word Segmentation
  268. DGNN: A Neural PDE Solver Induced by Discontinuous Galerkin Methods
  269. One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling
  270. Speedy MASt3R
  271. RSR-NF: Neural Field Regularization by Static Restoration Priors for Dynamic Imaging
  272. Revisiting Multi-Agent Asynchronous Online Optimization with Delays: the Strongly Convex Case
  273. Adaptive Moment Estimation Optimization Algorithm Using Projection Gradient for Deep Learning
  274. Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learning
  275. MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation
  276. TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs
  277. Label Unbalance in High-frequency Trading
  278. From Equations to Insights: Unraveling Symbolic Structures in PDEs with LLMs
  279. ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
  280. Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning
  281. Thermodynamic cost of inference and learning in physical neural networks
  282. Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning
  283. Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework
  284. Reference-Free 3D Reconstruction of Brain Dissection Slabs via Learned Atlas Coordinates
  285. Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
  286. Optimizing Fire Safety: Reducing False Alarms Using Advanced Machine Learning Techniques
  287. Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
  288. DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey
  289. Target-aware Bidirectional Fusion Transformer for Aerial Object Tracking
  290. UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
  291. Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction
  292. TGP: Two-modal occupancy prediction with 3D Gaussian and sparse points for 3D Environment Awareness
  293. PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation
  294. Emotion Recognition with CLIP and Sequential Learning
  295. Developing and Evaluating an AI-Assisted Prediction Model for Unplanned Intensive Care Admissions following Elective Neurosurgery using Natural Language Processing within an Electronic Healthcare Record System
  296. Type Information-Assisted Self-Supervised Knowledge Graph Denoising
  297. eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks