mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 24 Nov 2025

485 papers

  1. Replication Study: Federated Text-Driven Prompt Generation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  2. Intelligent Power Grid Design Review via Active Perception-Enabled Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  3. LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
  4. ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language ModelsLLM reasoning → Test-time compute and efficient thinking
  5. fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI UnderstandingLLM reasoning → Reasoning benchmarks and evaluation +1
  6. Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  7. A Longitudinal Measurement of Privacy Policy Evolution for Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
  8. Dissecting the Ledger: Locating and Suppressing "Liar Circuits" in Financial Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  9. Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  10. DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
  11. Solving Diffusion Inverse Problems with Restart Posterior SamplingDiffusion models → Inverse problems and image restoration
  12. Pretraining Transformer-Based Models on Diffusion-Generated Synthetic Graphs for Alzheimer's Disease PredictionDiffusion models → Medical imaging and segmentation
  13. PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic ApproachLLM agents and tool use → Agent threats, guardrails and governance
  14. Post-Pruning Accuracy Recovery via Data-Free Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  15. Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT FrameworkLLM reasoning → Multimodal reasoning
  16. Terminal Velocity MatchingDiffusion models → Flow matching, time series and science
  17. NOEM3A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Phase-Aligned RoPE for Mixed-Resolution Diffusion TransformerDiffusion models → Diffusion foundations and sampling
  19. Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMsLLM reasoning → Multimodal reasoning +2
  20. Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  21. Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model PromptsLLM safety and security → Prompt injection and agent security
  22. Rethinking Vision Transformer Depth via Structural ReparameterizationEfficient LLM inference and serving → Token pruning and merging for ViTs
  23. A Layered Protocol Architecture for the Internet of AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  24. INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  25. HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design OptimizationLLM agents and tool use → Software engineering coding agents
  26. Demystifying Diffusion Objectives: Reweighted Losses are Better Variational BoundsDiffusion models → Diffusion foundations and sampling
  27. Fara-7B: An Efficient Agentic Model for Computer UseLLM agents and tool use → Web, search, and research agents
  28. CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy OptimizationLLM reasoning → Multimodal reasoning +2
  29. Development of a Testbed for Autonomous Vehicles: Integrating MPC Control with Monocular Camera Lane DetectionEnd-to-end autonomous driving → End-to-end system architecture
  30. Navigating Gigapixel Pathology Images with Large Multimodal ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  31. Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided SearchLLM reasoning → Knowledge- and tool-augmented reasoning
  32. On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image ReconstructionMultimodal LLMs / vision-language models → Medical vision-language models
  33. Agint: Agentic Graph Compilation for Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  34. Learning Massively Multitask World Models for Continuous ControlWorld models → Latent dynamics models and model-based RL +1
  35. HunyuanOCR Technical ReportMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  36. ModHiFi: Identifying High Fidelity predictive components for Model ModificationLLM safety and security → Machine unlearning
  37. SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model AdaptationDiffusion models → Robustness, privacy and adversarial aspects +2
  38. Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage AssessmentLLM reasoning → Multimodal reasoning
  39. Cross-Domain Generalization of Multimodal LLMs for Global Photovoltaic AssessmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  40. AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based AgentsLLM agents and tool use → Agent threats, guardrails and governance
  41. Vidi2.5: Large Multimodal Models for Video Understanding and CreationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  42. Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated TrajectoriesVision-language-action models → Reinforcement learning and post-training
  43. Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  44. VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement LearningMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  45. EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question AnsweringLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  46. Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  47. Automating Deception: Scalable Multi-Turn LLM JailbreaksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  48. Connecting the Dots: Training-Free Visual Grounding via Agentic ReasoningLLM reasoning → Multimodal reasoning +1
  49. SCoTER: Structured Chain-of-Thought Transfer for Enhanced RecommendationLLM reasoning → LLM reasoning for recommendation
  50. VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-ReflectionLLM agents and tool use → Multimodal and embodied agents
  51. Are Image-to-Video Models Good Zero-Shot Image Editors?LLM reasoning → Multimodal reasoning +1
  52. Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained ExpertsDiffusion models → Diffusion foundations and sampling
  53. Mixture of Horizons in Action ChunkingVision-language-action models → Efficient VLA inference and adaptation
  54. Cook and Clean Together: Teaching Embodied Agents for Parallel Task ExecutionLLM agents and tool use → Multimodal and embodied agents
  55. Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme DesignLLM agents and tool use → Medical and scientific domain agents
  56. Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual TokensLLM reasoning → Multimodal reasoning +1
  57. Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent CollaborationLLM reasoning → Multimodal reasoning +1
  58. Learning Robust Social Strategies with Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  59. DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep ResearchLLM agents and tool use → Web, search, and research agents +1
  60. Predicting partially observable dynamical systems via diffusion models with a multiscale inference schemeDiffusion models → Flow matching, time series and science
  61. Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource HardwareDiffusion models → Flow matching, time series and science
  62. LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile SystemsLLM agents and tool use → Reinforcement learning for LLM agents
  63. DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image GenerationDiffusion models → Diffusion foundations and sampling
  64. Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception ReasoningLLM reasoning → Reinforcement learning for reasoning +2
  65. POUR: A Provably Optimal Method for Unlearning Representations via Neural CollapseLLM safety and security → Machine unlearning
  66. Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning TracesLLM reasoning → Reasoning benchmarks and evaluation
  67. Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal ApproachDiffusion models → Robustness, privacy and adversarial aspects +1
  68. Rethinking Intermediate Representation for VLM-based Robot ManipulationLLM reasoning → Spatial and embodied reasoning +1
  69. PRInTS: Reward Modeling for Long-Horizon Information SeekingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  70. AutoEnv: Automated Environments for Measuring Cross-Environment Agent LearningLLM agents and tool use → Reinforcement learning for LLM agents
  71. CDLM: Consistency Diffusion Language Models For Faster SamplingDiffusion models → Discrete and text diffusion
  72. BideDPO: Conditional Image Generation with Simultaneous Text and Condition AlignmentLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  73. Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural NetworksMechanistic interpretability → Circuits and mechanistic analysis
  74. LAST: LeArning to Think in Space and Time for Generalist Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  75. Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Medical vision-language models +1
  76. SimDiff: Simpler Yet Better Diffusion Model for Time Series Point ForecastingDiffusion models → Flow matching, time series and science
  77. MAESTRO: Multi-Agent Environment Shaping through Task and Reward OptimizationLLM agents and tool use → Multimodal and embodied agents
  78. Learning Plug-and-play Memory for Guiding Video Diffusion ModelsDiffusion models → Video generation
  79. Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  80. Are Large Vision Language Models Truly Grounded in Medical Images? Evidence from Italian Clinical Visual Question AnsweringMultimodal LLMs / vision-language models → Medical vision-language models
  81. Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and OptimizationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  82. ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided AlignmentLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  83. LLM-Based Agentic Negotiation for 6G: Addressing Uncertainty Neglect and Tail-Event RiskLLM agents and tool use → Agentic AI for wireless networks
  84. Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix CompletionLLM safety and security → Safety alignment, refusal and guardrails
  85. RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement ReasoningLLM reasoning → Multimodal reasoning
  86. First-order Sobolev Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  87. EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage PredictionMultimodal LLMs / vision-language models → Medical vision-language models
  88. Masked Diffusion Models are Secretly Learned-Order Autoregressive ModelsDiffusion models → Discrete and text diffusion
  89. From Pixels to Posts: Retrieval-Augmented Fashion Captioning and Hashtag GenerationRetrieval-augmented generation → Multimodal RAG
  90. Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation OptimizationLLM reasoning → Prompting and chain-of-thought reasoning
  91. When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIPDiffusion models → Image generation, text-to-image and editing
  92. MonoSR: Open-Vocabulary Spatial Reasoning from Monocular ImagesLLM reasoning → Spatial and embodied reasoning
  93. DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC DetectionDiffusion models → Image generation, text-to-image and editing
  94. EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow MatchingDiffusion models → Flow matching, time series and science
  95. A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective AnalysisLLM agents and tool use → Web, search, and research agents
  96. GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  97. Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video GenerationDiffusion models → Diffusion and flow policies for robotics +1
  98. Diagnosing Corruption-Induced Reliability Failures in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  99. OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +2
  100. End-to-end Autonomous Vehicle Following System using Monocular Fisheye CameraEnd-to-end autonomous driving → End-to-end system architecture
All 485
  1. Understanding and Mitigating Over-refusal for Large Language Models via Representation InterventionLLM safety and security → Safety alignment, refusal and guardrails
  2. A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene GenerationDiffusion models → 3D, point cloud and scene generation
  3. View-Consistent Diffusion Representations for 3D-Consistent Video GenerationDiffusion models → 3D, point cloud and scene generation
  4. Dynamic Mixture of Experts Against Severe Distribution ShiftsMixture-of-experts → Mixture of LoRA experts +1
  5. Zero-shot segmentation of skin tumors in whole-slide images with vision-language foundation modelsMultimodal LLMs / vision-language models → Medical vision-language models
  6. Synthesizing Visual Concepts as Vision-Language ProgramsLLM reasoning → Multimodal reasoning +1
  7. AVA-VLA: Improving Vision-Language-Action models with Active Visual AttentionVision-language-action models → Efficient VLA inference and adaptation
  8. Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic ManipulationVision-language-action models → Efficient VLA inference and adaptation +1
  9. VeCoR -- Velocity Contrastive Regularization for Flow MatchingDiffusion models → Flow matching, time series and science
  10. SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache CompressionEfficient LLM inference and serving → KV cache optimization
  11. Defending Large Language Models Against Jailbreak Exploits with Responsible AI ConsiderationsLLM safety and security → Jailbreaking
  12. Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based SearchMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  13. BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  14. EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  15. Learning What to Trust: Bayesian Prior-Guided Optimization for Visual GenerationLLM reasoning → Reinforcement learning for reasoning
  16. VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RLLLM reasoning → Reinforcement learning for reasoning
  17. MatMart: Material Reconstruction of 3D Objects via DiffusionDiffusion models → 3D, point cloud and scene generation
  18. MagicWorld: Towards Long-Horizon Stability for Interactive Video World ExplorationWorld models → Video-generation world models and simulators
  19. Accelerating Reinforcement Learning via Error-Related Human Brain SignalsDeep reinforcement learning methods → Deep RL algorithms and representations
  20. Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs InferenceLLM reasoning → Multimodal reasoning +1
  21. Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  22. KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed BanditsEfficient LLM inference and serving → Serving systems and request scheduling
  23. Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  24. UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World ModelWorld models → World models for navigation +1
  25. FlowSteer: Guiding Few-Step Image Synthesis with Authentic TrajectoriesDiffusion models → Flow matching, time series and science
  26. PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio GenerationLLM reasoning → Audio-language model reasoning +1
  27. Concept than Document: Context Compression via AMR-based Conceptual EntropyRetrieval-augmented generation → Generation and context integration +1
  28. Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation ModelsKnowledge distillation → Distillation for medical imaging
  29. Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image ClassificationKnowledge distillation → General knowledge distillation methods
  30. Assessing the alignment between infants' visual and linguistic experience using multimodal language modelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  31. VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  32. DiP: Taming Diffusion Models in Pixel SpaceDiffusion models → Diffusion foundations and sampling
  33. Disc3D: Automatic Curation of High-Quality 3D Dialog Data via Discriminative Object ReferringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action AgentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  35. HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic RepresentationsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  36. PartDiffuser: Part-wise 3D Mesh Generation via Discrete DiffusionDiffusion models → 3D, point cloud and scene generation
  37. RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM ModerationLLM safety and security → Jailbreaking
  38. Understanding Task Transfer in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  39. STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  40. Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided AlignmentDiffusion models → Flow matching, time series and science
  41. HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMsLLM reasoning → Mathematical reasoning
  42. Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web SearchLLM reasoning → Reasoning benchmarks and evaluation
  43. Any4D: Open-Prompt 4D Generation from Natural Language and ImagesWorld models → Embodied and robot world models
  44. ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal DiffusionDiffusion models → Diffusion and flow policies for robotics +1
  45. Multimodal Large Language Models with Adaptive Preference Optimization for Sequential RecommendationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  46. Thinking Ahead: Foresight Intelligence in MLLMs and World ModelWorld models → World models for autonomous driving +1
  47. GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  48. Reinforcement Learning for Self-Healing Material SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  49. Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLMLLM safety and security → Jailbreaking
  50. Seeing What Matters: Visual Preference Policy Optimization for Visual GenerationLLM reasoning → Reinforcement learning for reasoning
  51. HuggingR4: A Progressive Reasoning Framework for Discovering Optimal Model CompanionsLLM reasoning → Reasoning for agents, planning and code +1
  52. MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question GenerationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  53. DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics
  54. CoD: A Diffusion Foundation Model for Image CompressionDiffusion models → Diffusion for compression and wireless
  55. VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron ChunkingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  56. Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  57. Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video GenerationLLM safety and security → Vision-language and text-to-image safety
  58. MedVision: Benchmarking Quantitative Medical Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  59. Edit2Perceive: Image Editing Diffusion Models Are Strong Dense PerceiversDiffusion models → Image generation, text-to-image and editing
  60. Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective RefinementDiffusion models → 3D, point cloud and scene generation
  61. Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task ArithmeticLLM safety and security → Machine unlearning
  62. CLaRa: Bridging Retrieval and Generation with Continuous Latent ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  63. Automated Fault Detection in 5G Core Networks Using Large Language Models
  64. Large Language Models as Search Engines: Societal Challenges
  65. LATTICE: Democratize High-Fidelity 3D Generation at Scale
  66. Deep Research: A Systematic Survey
  67. ProvRain: Rain-Adaptive Denoising and Vehicle Detection via MobileNet-UNet and Faster R-CNN
  68. A CNN-Based Technique to Assist Layout-to-Generator Conversion for Analog Circuits
  69. Enhancing Cognitive Robotics with Commonsense through LLM-Generated Preconditions and Subgoals
  70. Satellite to Street : Disaster Impact Estimator
  71. SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning
  72. Factors That Support Grounded Responses in LLM Conversations: A Rapid Review
  73. LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti
  74. Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
  75. Who Owns the Knowledge? Copyright, GenAI, and the Future of Academic Publishing
  76. Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models
  77. Active Slice Discovery in Large Language Models
  78. A Set of Rules for Model Validation
  79. Paraconsistent-Lib: an intuitive PAL2v algorithm Python Library
  80. In Defense of the Turing Test and its Legacy
  81. On the Role of Hidden States of Modern Hopfield Network in Transformer
  82. Musical Score Understanding Benchmark: Evaluating Large Language Models' Comprehension of Complete Musical Scores
  83. Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding
  84. A Brief History of Digital Twin Technology
  85. Development of a fully deep learning model to improve the reproducibility of sector classification systems for predicting unerupted maxillary canine likelihood of impaction
  86. KOM: A Multi-Agent Artificial Intelligence System for Precision Management of Knee Osteoarthritis (KOA)
  87. When +1% Is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements
  88. Gender Bias in Emotion Recognition by Large Language Models
  89. Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation
  90. Order Selection in Vector Autoregression by Mean Square Information Criterion
  91. A Storage-Efficient Feature for 3D Concrete Defect Segmentation to Replace Normal Vector
  92. Vision-Language Enhanced Foundation Model for Semi-Supervised Medical Image Segmentation
  93. What does it mean to understand language?
  94. Clustering Approaches for Mixed-Type Data: A Comparative Study
  95. What You See is (Usually) What You Get: Multimodal Prototype Networks that Abstain from Expensive Modalities
  96. Leveraging Foundation Models for Histological Grading in Cutaneous Squamous Cell Carcinoma using PathFMTools
  97. DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning
  98. Scaling Item-to-Standard Alignment with Large Language Models: Accuracy, Limits, and Solutions
  99. Efficient Transferable Optimal Transport via Min-Sliced Transport Plans
  100. CAMformer: Associative Memory is All You Need
  101. Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation
  102. Integrating RCTs, RWD, AI/ML and Statistics: Next-Generation Evidence Synthesis
  103. Training-Free Active Learning Framework in Materials Science with Large Language Models
  104. Maritime Small Object Detection from UAVs using Deep Learning with Altitude-Aware Dynamic Tiling
  105. An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design
  106. Individual and group fairness in geographical partitioning
  107. Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian
  108. Large Scale Community-Aware Network Generation
  109. Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability
  110. CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation
  111. Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
  112. CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
  113. RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models
  114. The Alexander-Hirschowitz theorem for neurovarieties
  115. TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification
  116. TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
  117. CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation
  118. IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants
  119. FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking
  120. OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis
  121. Structured Noise Modeling for Enhanced Time-Series Forecasting
  122. Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
  123. Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning vs. Full Fine-Tuning
  124. Synthetic Data: AI's New Weapon Against Android Malware
  125. Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
  126. IRSDA: An Agent-Orchestrated Framework for Enterprise Intrusion Response
  127. Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Models
  128. SkillSight: Efficient First-Person Skill Assessment with Gaze
  129. Optimization and Regularization Under Arbitrary Objectives
  130. Towards Synergistic Teacher-AI Interactions with Generative Artificial Intelligence
  131. Multiscale Vector-Quantized Variational Autoencoder for Endoscopic Image Synthesis
  132. From Wearables to Warnings: Predicting Pain Spikes in Patients with Opioid Use Disorder
  133. Leveraging Unlabeled Scans for NCCT Image Segmentation in Early Stroke Diagnosis: A Semi-Supervised GAN Approach
  134. Neural Tractability via Structure: Learning-Augmented Algorithms for Graph Combinatorial Optimization
  135. An Invariant Latent Space Perspective on Language Model Inversion
  136. Deductive Systems for Logic Programs with Counting
  137. Trust-Based Social Learning for Communication (TSLEC) Protocol Evolution in Multi-Agent Reinforcement Learning
  138. Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
  139. Online Sparse Feature Selection in Data Streams via Differential Evolution
  140. The Semiotic Channel Principle: Measuring the Capacity for Meaning in LLM Communication
  141. Neural Evidence and Behavioural Welfare Economics: When Can Neuroeconomics Inform Policy?
  142. Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
  143. Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation
  144. PhysDNet: Physics-Guided Decomposition Network of Side-Scan Sonar Imagery
  145. Studying Maps at Scale: A Digital Investigation of Cartography and the Evolution of Figuration
  146. Masked Autoencoder Joint Learning for Robust Spitzoid Tumor Classification
  147. MapRF: Weakly Supervised Online HD Map Construction via NeRF-Guided Self-Training
  148. Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space
  149. Blinking Beyond EAR: A Stable Eyelid Angle Metric for Driver Drowsiness Detection and Data Augmentation
  150. Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning
  151. Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
  152. Single Image to High-Quality 3D Object via Latent Features
  153. The Determinant Ratio Matrix Approach to Solving 3D Matching and 2D Orthographic Projection Alignment Tasks
  154. TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception
  155. LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
  156. Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
  157. Flow Map Distillation Without Data
  158. Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering
  159. Ref-SAM3D: Bridging SAM3D with Text for Reference 3D Reconstruction
  160. SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
  161. SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning
  162. UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
  163. Nonparametric Instrumental Variable Regression with Observed Covariates
  164. In-Video Instructions: Visual Signals as Generative Control
  165. PTF Testing Lower Bounds for Non-Gaussian Component Analysis
  166. Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environments
  167. BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
  168. UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrieval
  169. AnatomicalNets: A Multi-Structure Segmentation and Contour-Based Distance Estimation Pipeline for Clinically Grounded Lung Cancer T-Staging
  170. Neural surrogates for designing gravitational wave detectors
  171. Enhancing Conformal Prediction via Class Similarity
  172. Rethinking Reward Signals in Video GRPO: When Scores Become Targets
  173. Leveraging LLMs for reward function design in reinforcement learning control tasks
  174. CellFMCount: A Fluorescence Microscopy Dataset, Benchmark, and Methods for Cell Counting
  175. Scalable Parameter-Light Spectral Method for Clustering Short Text Embeddings with a Cohesion-Based Evaluation Metric
  176. Artificial Intelligence Driven Workflow for Accelerating Design of Novel Photosensitizers
  177. Annotation-Free Class-Incremental Learning
  178. Explicit Tonal Tension Conditioning via Dual-Level Beam Search for Symbolic Music Generation
  179. High-throughput validation of phase formability and simulation accuracy of Cantor alloys
  180. Targeted Manipulation: Slope-Based Attacks on Financial Time-Series Data
  181. Understanding the Staged Dynamics of Transformers in Learning Latent Structure
  182. MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation
  183. Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval
  184. What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models
  185. SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
  186. SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis
  187. MultiBanAbs: A Comprehensive Multi-Domain Bangla Abstractive Text Summarization Dataset
  188. Dual-Granularity Semantic Prompting for Language Guidance Infrared Small Target Detection
  189. IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection
  190. Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
  191. DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
  192. TorchQuantumDistributed
  193. Performance Guarantees for Quantum Neural Estimation of Entropies
  194. The Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Fragility
  195. Data Flows and Colonial Regimes in Africa: A Critical Analysis of the Colonial Futurities Embedded in AI Ecosystems
  196. MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings
  197. ReMatch: Boosting Representation through Matching for Multimodal Retrieval
  198. Closing Gaps in Emissions Monitoring with Climate TRACE
  199. Dynamic Multi-Species Bird Soundscape Generation with Acoustic Patterning and 3D Spatialization
  200. Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection
  201. Scalable Bayesian Network Structure Learning Using Tsetlin Machine to Constrain the Search Space
  202. Tiny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Model
  203. Leveraging Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting
  204. Interpreting GFlowNets for Drug Discovery: What probes can and cannot show
  205. Solar-GECO: Perovskite Solar Cell Property Prediction with Geometric-Aware Co-Attention
  206. Psychometric Tests for AI Agents and Their Moduli Space
  207. Wrist Photoplethysmography Predicts Dietary Information
  208. Adversarial Patch Attacks on Vision-Based Cargo Occupancy Estimation via Differentiable 3D Simulation
  209. FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
  210. Neural Architecture Search for Quantum Autoencoders
  211. Local Entropy Search over Descent Sequences for Bayesian Optimization
  212. Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform
  213. SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control
  214. IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
  215. In Machina N400: Pinpointing Where a Causal Language Model Detects Semantic Violations
  216. NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
  217. Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?
  218. CLASH: A Benchmark for Cross-Modal Contradiction Detection
  219. Three-Dimensional Anatomical Data Generation Based on Artificial Neural Networks
  220. SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection
  221. Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement
  222. nnActive: A Framework for Evaluation of Active Learning in 3D Biomedical Segmentation
  223. Evaluating Deep Learning and Traditional Approaches Used in Source Camera Identification
  224. From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation
  225. MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
  226. Test-Time Preference Optimization for Image Restoration
  227. Epistemic Familiarity is Associated With Belief Stability in Large Language Models
  228. A Robust State Filter Against Unmodeled Process And Measurement Noise
  229. Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints
  230. Feature Ranking in Credit-Risk with Qudit-Based Networks
  231. Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation
  232. Activation Boundary Matching: Task-Informed Initialization for Low-Rank Adaptation
  233. FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation
  234. MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery
  235. Uncertainty-Aware Deep Learning Framework for Remaining Useful Life Prediction in Turbofan Engines with Learned Aleatoric Uncertainty
  236. Emotion-Enhanced Multi-Task Learning with LLMs for Aspect Category Sentiment Analysis
  237. ReLU-Based and DNN-Based Generalized Maximum Score Estimators
  238. On the Optimality of Kinship Naming: an Information-theoretic Approach
  239. A symbolic Perl algorithm for the unification of Nahuatl word spellings
  240. 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
  241. AI Consciousness and Existential Risk
  242. Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation
  243. HABIT: Human Action Benchmark for Interactive Traffic in CARLA
  244. The Core in Max-Loss Non-Centroid Clustering Can Be Empty
  245. Graph-based 3D Human Pose Estimation using WiFi Signals
  246. Edge-Based Predictive Data Reduction for Smart Agriculture: A Lightweight Approach to Efficient IoT Communication
  247. Extracting Robust Register Automata from Neural Networks over Data Sequences
  248. Optimization of Deep Learning Models for Dynamic Market Behavior Prediction
  249. Towards Generalizable Deepfake Detection via Forgery-aware Audio-Visual Adaptation: A Variational Bayesian Approach
  250. Structured Matching via Cost-Regularized Unbalanced Optimal Transport
  251. DEAP-3DSAM: Decoder Enhanced and Auto Prompt SAM for 3D Medical Image Segmentation
  252. DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling
  253. Mitigating Participation Imbalance Bias in Asynchronous Federated Learning
  254. Understanding, Accelerating, and Improving MeanFlow Training
  255. Logic of Montage
  256. Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation
  257. LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space
  258. Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study
  259. MedSAM3: Delving into Segment Anything with Medical Concepts
  260. Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
  261. Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones
  262. ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
  263. Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling
  264. Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting
  265. 3D Dynamic Radio Map Prediction Using Vision Transformers for Low-Altitude Wireless Networks
  266. Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
  267. Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers
  268. AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization
  269. Classification EM-PCA for clustering and embedding
  270. Rethinking Plant Disease Diagnosis: Bridging the Academic-Practical Gap with Vision Transformers and Zero-Shot Learning
  271. UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection
  272. MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design
  273. FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
  274. Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNs
  275. CataractCompDetect: Intraoperative Complication Detection in Cataract Surgery
  276. LLM-CSEC: Empirical Evaluation of Security in C/C++ Code Generated by Large Language Models
  277. Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation
  278. Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
  279. Active Inference is a Subtype of Variational Inference
  280. Leveraging Adversarial Learning for Pathological Fidelity in Virtual Staining
  281. MIST: Mutual Information Estimation Via Supervised Training
  282. Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery
  283. Knowledge-based Graphical Method for Safety Signal Detection in Clinical Trials
  284. Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
  285. Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs
  286. Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation
  287. FineXtrol: Controllable Motion Generation via Fine-Grained Text
  288. MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems
  289. LookSharp: Attention Entropy Minimization for Test-Time Adaptation
  290. LLM-Driven Kernel Evolution: Automating Driver Updates in Linux
  291. One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control
  292. How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining
  293. Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels
  294. Reproducibility Study of Large Language Model Bayesian Optimization
  295. Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
  296. CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation
  297. MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model
  298. Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
  299. Facade Segmentation for Solar Photovoltaic Suitability
  300. Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
  301. GContextFormer: A global context-aware hybrid multi-head attention approach with scaled additive aggregation for multimodal trajectory prediction
  302. Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
  303. HunyuanVideo 1.5 Technical Report
  304. Hear: Hierarchically Enhanced Aesthetic Representations For Multidimensional Music Evaluation
  305. DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection
  306. Generating Reading Comprehension Exercises with Large Language Models for Educational Applications
  307. Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
  308. Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
  309. Deep Hybrid Model for Region of Interest Detection in Omnidirectional Videos
  310. Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect
  311. FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models
  312. Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
  313. Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
  314. Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming
  315. Large Language Models for the Summarization of Czech Documents: From History to the Present
  316. Personalized Federated Segmentation with Shared Feature Aggregation and Boundary-Focused Calibration
  317. WaveTuner: Comprehensive Wavelet Subband Tuning for Time Series Forecasting
  318. A Reproducible Framework for Neural Topic Modeling in Focus Group Analysis
  319. Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds
  320. Federated style aware transformer aggregation of representations
  321. Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation
  322. Enhancing Multi-Label Thoracic Disease Diagnosis with Deep Ensemble-Based Uncertainty Quantification
  323. FVAR: Visual Autoregressive Modeling via Next Focus Prediction
  324. Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data
  325. VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
  326. Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM
  327. Solving a Research Problem in Mathematical Statistics with AI Assistance
  328. Leveraging Metaheuristic Approaches to Improve Deep Learning Systems for Anxiety Disorder Detection
  329. Q-Save: Towards Scoring and Attribution for Generated Video Evaluation
  330. Unsupervised simulation of incompressible flows with physics- and equality- constrained artificial neural networks
  331. SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation
  332. DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video
  333. Uncertainty of Network Topology with Applications to Out-of-Distribution Detection
  334. Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
  335. TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging
  336. ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
  337. NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations
  338. Scale What Counts, Mask What Matters: Evaluating Foundation Models for Zero-Shot Cross-Domain Wi-Fi Sensing
  339. Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors
  340. StereoDETR: Stereo-based Transformer for 3D Object Detection
  341. Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
  342. A Novel Dual-Stream Framework for dMRI Tractography Streamline Classification with Joint dMRI and fMRI Data
  343. ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
  344. SAOT: An Enhanced Locality-Aware Spectral Transformer for Solving PDEs
  345. Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
  346. Zero-Shot Context-Aware ASR for Diverse Arabic Varieties
  347. Sampling Control for Imbalanced Calibration in Semi-Supervised Learning
  348. Re-Key-Free, Risky-Free: Adaptable Model Usage Control
  349. NI-Tex: Non-isometric Image-based Garment Texture Generation
  350. VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
  351. From Features to Reference Points: Lightweight and Adaptive Fusion for Cooperative Autonomous Driving
  352. Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion
  353. On Instability of Minimax Optimal Optimism-Based Bandit Algorithms
  354. RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
  355. A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection
  356. Joint learning of a network of linear dynamical systems via total variation penalization
  357. Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
  358. OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting
  359. Large-Scale In-Game Outcome Forecasting for Match, Team and Players in Football using an Axial Transformer Neural Network
  360. LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
  361. Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation
  362. N2N: A Parallel Framework for Large-Scale MILP under Distributed Memory
  363. AIRHILT: A Human-in-the-Loop Testbed for Multimodal Conflict Detection in Aviation
  364. When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation
  365. GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction
  366. Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation
  367. CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection
  368. ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction
  369. Dendritic Convolution for Noise Image Recognition
  370. Multimodal Real-Time Anomaly Detection and Industrial Applications
  371. Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models
  372. Exploring Surround-View Fisheye Camera 3D Object Detection
  373. Stable Multi-Drone GNSS Tracking System for Marine Robots
  374. EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification
  375. QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks
  376. Hierarchical GraphCut Phase Unwrapping based on Invariance of Diffeomorphisms Framework
  377. Inverse Rendering for High-Genus Surface Meshes from Multi-View Images
  378. Neural Geometry Image-Based Representations with Optimal Transport (OT)
  379. A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification
  380. Low-Rank GEMM: Efficient Matrix Multiplication via Low-Rank Approximation with FP8 Acceleration
  381. Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition
  382. Deterministic Continuous Replacement: Fast and Stable Module Replacement in Pretrained Transformers
  383. Data Augmentation Strategies for Robust Lane Marking Detection
  384. Equivariant Deep Equilibrium Models for Imaging Inverse Problems
  385. Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data