mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 3 Mar 2025

451 papers

  1. RAVEN: An Agentic Framework for Multimodal Entity Discovery from Large-Scale Video CollectionsLLM agents and tool use → Multimodal and embodied agents
  2. How Do Consumers Really Choose: Exposing Hidden Preferences with the Mixture of Experts ModelMixture-of-experts → MoE theory and gating functions
  3. Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  4. HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  5. Surgical Vision World ModelWorld models → Medical and surgical world models
  6. ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  7. HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single StageDiffusion models → Diffusion and flow policies for robotics
  8. Average-DICE: Stationary Distribution Correction by RegressionDeep reinforcement learning methods → RL theory and sample complexity
  9. NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance PointsDeep reinforcement learning methods → RL for robot navigation and UAV control
  10. Superficial Self-Improved Reasoners Benefit from Model MergingLLM reasoning → Test-time compute and efficient thinking +1
  11. Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized DetectionDiffusion models → Image generation, text-to-image and editing
  12. Linear Representations of Political Perspective Emerge in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  13. Superscopes: Amplifying Internal Feature Representations for Language Model InterpretationMechanistic interpretability → Knowledge and representations inside LLMs
  14. M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed QualityLLM agents and tool use → Reinforcement learning for LLM agents +1
  15. CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous VehiclesEnd-to-end autonomous driving → Large language models for driving
  16. Active Alignments of Lens Systems with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  17. Interactive Debugging and Steering of Multi-Agent AI SystemsLLM agents and tool use → Software engineering coding agents
  18. FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action GenerationDiffusion models → Diffusion and flow policies for robotics
  19. Dynamic Search for Inference-Time Alignment in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  20. Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM InteractionsLLM agents and tool use → Social simulation and multi-agent debate
  21. Comparative Analysis of OpenAI GPT-4o and DeepSeek R1 for Scientific Text Categorization Using Prompt EngineeringLLM reasoning → Knowledge- and tool-augmented reasoning
  22. Accelerating Multi-Task Temporal Difference Learning under Low-Rank RepresentationDeep reinforcement learning methods → RL theory and sample complexity
  23. HoT: Highlighted Chain of Thought for Referencing Supporting Facts from InputsLLM reasoning → Prompting and chain-of-thought reasoning
  24. Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  25. Task Scheduling & Forgetting in Multi-Task Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  26. AskToAct: Enhancing LLMs Tool Use via Self-Correcting ClarificationLLM agents and tool use → Tool learning and function calling
  27. MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentsLLM reasoning → Reasoning for agents, planning and code +1
  28. Denoising Functional Maps: Diffusion Models for Shape CorrespondenceDiffusion models → 3D, point cloud and scene generation
  29. EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time TestEfficient LLM inference and serving → Speculative decoding
  30. Jailbreaking Safeguarded Text-to-Image Models via Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
  31. Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model LearningWorld models → Embodied and robot world models +1
  32. CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM WisdomSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  33. Cracking Vector Search IndexesRetrieval-augmented generation → RAG pipeline design and evaluation
  34. Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept GeometryMechanistic interpretability → Sparse autoencoder training and evaluation
  35. Do GFlowNets Transfer? Case Study on the Game of 24/42LLM reasoning → Mathematical reasoning
  36. Visual-RFT: Visual Reinforcement Fine-TuningLLM reasoning → Multimodal reasoning
  37. Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  38. Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  39. Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus AreasLLM reasoning → Spatial and embodied reasoning +1
  40. Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language ModelsLLM agents and tool use → Tool learning and function calling
  41. SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning TracesLLM reasoning → Multimodal reasoning +2
  42. Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  43. Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language ModelsLLM safety and security → Prompt injection and agent security
  44. Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout ScenariosDiffusion models → Flow matching, time series and science
  45. Adversarial Agents: Black-Box Evasion Attacks with Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  46. Mamba base PKD for efficient knowledge compressionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  47. SAGE: A Framework of Precise Retrieval for RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  48. Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-EvolutionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  49. ToLo: A Two-Stage, Training-Free Layout-To-Image Generation Framework For High-Overlap LayoutsDiffusion models → Image generation, text-to-image and editing
  50. CoPL: Collaborative Preference Learning for Personalizing LLMsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  51. CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  52. DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  53. Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  54. The Emergence of Grammar through Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  55. SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative LearningState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  56. CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly ResolutionLLM reasoning → Chain-of-thought reasoning for driving
  57. Advancing vision-language models in front-end development via data synthesisMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
  58. RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. RevTogether: Supporting Science Story Revision with Multiple AI AgentsLLM agents and tool use → Web, search, and research agents
  60. EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank ProjectionEfficient LLM inference and serving → KV cache optimization
  61. SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World ModelsWorld models → Latent dynamics models and model-based RL +1
  62. MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingDiffusion models → Medical imaging and segmentation
  63. MapExRL: Human-Inspired Indoor Exploration with Predicted Environment Context and Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  64. Compositional Reasoning with Transformers, RNNs, and Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  65. Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic LanguageLLM reasoning → Reasoning benchmarks and evaluation
  66. Diversity Covariance-Aware Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  67. What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the SecretLLM reasoning → Reinforcement learning for reasoning
  68. Improving Retrospective Language Agents via Joint Policy Gradient OptimizationLLM reasoning → Reasoning for agents, planning and code +2
  69. FlowDec: A flow-based full-band general audio codec with high perceptual qualityDiffusion models → Audio, speech and music
  70. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity ReductionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  71. Overcoming Non-stationary Dynamics with Evidential Proximal Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  72. Rethinking Data: Towards Better Performing Domain-Specific Small Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  73. Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  74. Investigating Memory in Model-Free RL with POPGym ArcadeDeep reinforcement learning methods → Deep RL algorithms and representations
  75. Eau De Q-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  76. Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early DecodingLLM reasoning → Test-time compute and efficient thinking +1
  77. Learning Actionable World Models for Industrial Process ControlWorld models → Latent dynamics models and model-based RL
  78. Jailbreaking Generative AI: Empowering Novices to Conduct Phishing AttacksLLM safety and security → Prompt injection and agent security
  79. Q-NL Verifier: Leveraging Synthetic Data for Robust Knowledge Graph Question AnsweringSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  80. CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVsLLM reasoning → Spatial and embodied reasoning +1
  81. Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via TransformersDiffusion models → Flow matching, time series and science
  82. Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset GenerationDiffusion models → 3D, point cloud and scene generation
  83. FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot InteractionOffline RL and imitation learning from data → Robot manipulation imitation learning
  84. DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts ModelsMixture-of-experts → MoE theory and gating functions
  85. SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia GraphRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  86. Group Relative Policy Optimization for Image CaptioningLLM reasoning → Reinforcement learning for reasoning
  87. WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language ModelsEfficient LLM inference and serving → KV cache optimization
  88. CacheQuant: Comprehensively Accelerated Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  89. Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  90. Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRsLLM reasoning → Reinforcement learning for reasoning +1
  91. From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  92. PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level AdaptationMixture-of-experts → Mixture of LoRA experts
  93. Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative ModelsLLM reasoning → Multimodal reasoning
  94. Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric OutpaintingDiffusion models → 3D, point cloud and scene generation
  95. Stone Soup Multi-Target Tracking Feature Extraction For Autonomous Search And Track In Deep Reinforcement Learning EnvironmentDeep reinforcement learning methods → RL for robot navigation and UAV control
  96. Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in DualDiffusion models → Inverse problems and image restoration
  97. DCI: A Coordinated Allocation and Filling Workload-Aware Dual-Cache Allocation GNN Inference Acceleration SystemEfficient LLM inference and serving → KV cache optimization
  98. DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion ModelsDiffusion models → Flow matching, time series and science
  99. OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFDLLM reasoning → Spatial and embodied reasoning
  100. Generalizable Prompt Learning of CLIP: A Brief OverviewMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
All 451
  1. Impact of Static Friction on Sim2Real in Robotic Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  2. Catching Spinning Table Tennis Balls in Simulation with End-to-End Curriculum Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  3. A Taxonomy for Evaluating Generalist Robot Manipulation PoliciesVision-language-action models → Generalist VLA models and benchmarks
  4. PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy ExtrapolationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. CE-U: Cross Entropy UnlearningLLM safety and security → Machine unlearning
  6. Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAGMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  7. Tera-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusionDiffusion models → Medical imaging and segmentation
  8. Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  9. Action Tokenizer Matters in In-Context Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  10. DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  11. DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent DiffusionDiffusion models → Audio, speech and music
  12. Differentiable Information Enhanced Model-Based Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  13. Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic DataSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  14. Split Gibbs Discrete Diffusion Posterior SamplingDiffusion models → Inverse problems and image restoration
  15. Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario AugmentationDeep reinforcement learning methods → RL for robot navigation and UAV control
  16. CoInD: Enabling Logical Compositions in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. Diffusion Classifier-Driven Reward for Offline Preference-based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity ApproachLLM reasoning → Test-time compute and efficient thinking
  19. Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPsDeep reinforcement learning methods → RL theory and sample complexity
  20. Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected ObstaclesDeep reinforcement learning methods → RL for robot navigation and UAV control
  21. TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  22. ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion PersonalizationDiffusion models → Image generation, text-to-image and editing
  23. SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in StructuresState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  24. KineSoft: Learning Proprioceptive Manipulation Policies with Soft Robot HandsOffline RL and imitation learning from data → Robot manipulation imitation learning
  25. Active Learning for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  26. Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPSDiffusion models → Medical imaging and segmentation
  27. All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-TuningDeep reinforcement learning methods → RL training of language and agent models
  28. Scientific Reasoning: Assessment of Multimodal Generative LLMsLLM reasoning → Multimodal reasoning
  29. Interview AI-ssistant: Designing for Real-Time Human-AI Collaboration in Interview Preparation and Execution
  30. A Diverse and Effective Retrieval-Based Debt Collection System with Expert Knowledge
  31. Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension
  32. Conditional Electrocardiogram Generation Using Hierarchical Variational Autoencoders
  33. A CGAN-LSTM-Based Framework for Time-Varying Non-Stationary Channel Modeling
  34. Hate Speech and Sentiment of YouTube Video Comments From Public and Private Sources Covering the Israel-Palestine Conflict
  35. Empowering the Future Workforce: Prioritizing Education for the AI-Accelerated Job Market
  36. Holistically Evaluating the Environmental Impact of Creating Language Models
  37. Federated Learning Framework via Distributed Mutual Learning
  38. Illuminant and light direction estimation using Wasserstein distance method
  39. From Target Tracking to Targeting Track -- Part III: Stochastic Process Modeling and Online Learning
  40. A Multi-Scale Attention-Based Attack Diagnosis Mechanism for Parallel Cyber-Physical Attacks in Power Grids
  41. Towards Multi-Stakeholder Evaluation of ML Models: A Crowdsourcing Study on Metric Preferences in Job-matching System
  42. What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text
  43. An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem
  44. The order in speech disorder: a scoping review of state of the art machine learning methods for clinical speech classification
  45. Direct Speech to Speech Translation: A Review
  46. Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)
  47. A Survey on Semantic Communications in Internet of Vehicles
  48. Hyperspectral Image Restoration and Super-resolution with Physics-Aware Deep Learning for Biomedical Applications
  49. Fine-Tuning Whisper for Inclusive Prosodic Stress Analysis
  50. Diagnosis of Patients with Viral, Bacterial, and Non-Pneumonia Based on Chest X-Ray Images Using Convolutional Neural Networks
  51. Machine Learning Applications to Diffuse Reflectance Spectroscopy in Optical Diagnosis; A Systematic Review
  52. OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels
  53. Modality-Agnostic Style Transfer for Holistic Feature Imputation
  54. A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokerage
  55. A Generalized Theory of Mixup for Structure-Preserving Synthetic Data
  56. Development of a Deep Learning Model for the Prediction of Ventilator Weaning
  57. Video-DPRP: A Differentially Private Approach for Visual Privacy-Preserving Video Human Activity Recognition
  58. Gradient-free stochastic optimization for additive models
  59. Forgetting Transformer: Softmax Attention with a Forget Gate
  60. Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
  61. Aerial Infrared Health Monitoring of Solar Photovoltaic Farms at Scale
  62. A Hybrid CNN-Transformer Model for Heart Disease Prediction Using Life History Data
  63. TMIQ: Quantifying Test and Measurement Domain Intelligence in Large Language Models
  64. An Efficient Plugin Method for Metric Optimization of Black-Box Models
  65. Parabolic Continual Learning
  66. Fairness and/or Privacy on Social Graphs
  67. Deep Learning is Not So Mysterious or Different
  68. Building Machine Learning Challenges for Anomaly Detection in Science
  69. Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification
  70. Correcting Mode Proportion Bias in Generalized Bayesian Inference via a Weighted Kernel Stein Discrepancy
  71. Foundation Model in Biomedicine
  72. Provable Benefits of Task-Specific Prompts for In-context Learning
  73. LLMs as Educational Analysts: Transforming Multimodal Data Traces into Actionable Reading Assessment Reports
  74. Correlation to Causation: A Causal Deep Learning Framework for Arctic Sea Ice Prediction
  75. Data Augmentation for NeRFs in the Low Data Limit
  76. Uncertainty Representation in a SOTIF-Related Use Case with Dempster-Shafer Theory for LiDAR Sensor-Based Object Detection
  77. Twenty Years of Personality Computing: Threats, Challenges and Future Directions
  78. AI persuading AI vs AI persuading Humans: LLMs' Differential Effectiveness in Promoting Pro-Environmental Behavior
  79. Too Much to Trust? Measuring the Security and Cognitive Impacts of Explainability in AI-Driven SOCs
  80. CrossFusion: A Multi-Scale Cross-Attention Convolutional Fusion Model for Cancer Survival Prediction
  81. V2Dial: Unification of Video and Visual Dialog via Multimodal Experts
  82. RiboGen: RNA Sequence and Structure Co-Generation with Equivariant MultiFlow
  83. Hebbian learning the local structure of language
  84. CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations
  85. EPEE: Towards Efficient and Effective Foundation Models in Biomedicine
  86. Constrained Linear Thompson Sampling
  87. Latent Domain Modeling Improves Robustness to Geographic Shifts
  88. Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA
  89. A Lightweight and Secure Deep Learning Model for Privacy-Preserving Federated Learning in Intelligent Enterprises
  90. Mind the (Belief) Gap: Group Identity in the World of LLMs
  91. Pretrained Embeddings as a Behavior Specification Mechanism
  92. Interval Regression: A Comparative Study with Proposed Models
  93. Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization
  94. TactStyle: Generating Tactile Textures with Generative AI for Digital Fabrication
  95. A Deep Autoregressive Model for Dynamic Combinatorial Complexes
  96. One ruler to measure them all: Benchmarking multilingual long-context language models
  97. Adaptively profiling models with task elicitation
  98. Proportional Committee Elections with Positive and Negative Votes
  99. Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts
  100. Mathematical Foundation of Interpretable Equivariant Surrogate Models
  101. A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
  102. Synthetic Tabular Data Detection In the Wild
  103. Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization
  104. Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective
  105. A General Neural Network Potential for Energetic Materials with C, H, N, and O elements
  106. Adversarial Generative Flow Network for Solving Vehicle Routing Problems
  107. Road Boundary Detection Using 4D mmWave Radar for Autonomous Driving
  108. Can (A)I Change Your Mind?
  109. When Can You Get Away with Low Memory Adam?
  110. GRAIN: Exact Graph Reconstruction from Gradients
  111. Primus: Enforcing Attention Usage for 3D Medical Image Segmentation
  112. Rotary Offset Features in Large Language Models
  113. From Language to Cognition: How LLMs Outgrow the Human Language Network
  114. Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
  115. Open-source framework for detecting bias and overfitting for large pathology images
  116. From superposition to sparse codes: interpretable representations in neural networks
  117. On the Power of Context-Enhanced Learning in LLMs
  118. RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
  119. Gradient-Based Optimization on G"odel Logic as Discrete Local Search
  120. LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
  121. AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
  122. Large-Scale Data Selection for Instruction Tuning
  123. Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers
  124. textttSEM-CTRL: Semantically Controlled Decoding
  125. Deep Reinforcement Learning-Based User Association in Hybrid LiFi/WiFi Indoor Networks
  126. PhishVQC: Optimizing Phishing URL Detection with Correlation Based Feature Selection and Variational Quantum Classifier
  127. OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment
  128. Generating Counterfactual Explanations Under Temporal Constraints
  129. vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding
  130. Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
  131. m4: A Learned Flow-level Network Simulator
  132. SHADE-AD: An LLM-Based Framework for Synthesizing Activity Data of Alzheimer's Patients
  133. Optimal Differentially Private Sampling of Unbounded Gaussians
  134. Zero-Trust Artificial Intelligence Model Security Based on Moving Target Defense and Content Disarm and Reconstruction
  135. Boolean-aware Attention for Dense Retrieval
  136. SAKE: Steering Activations for Knowledge Editing
  137. ECG-EmotionNet: Nested Mixture of Expert (NMoE) Adaptation of ECG-Foundation Model for Driver Emotion Recognition
  138. Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
  139. VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
  140. DeepSuM: Deep Sufficient Modality Learning Framework
  141. HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
  142. Syntactic Learnability of Echo State Neural Language Models at Scale
  143. How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings
  144. Learning Exposure Mapping Functions for Inferring Heterogeneous Peer Effects
  145. Quality Measures for Dynamic Graph Generative Models
  146. Learning surrogate equations for the analysis of an agent-based cancer model
  147. KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation
  148. Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia
  149. MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment
  150. Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
  151. DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems
  152. On the Development of Binary Classification Algorithm Based on Principles of Geometry and Statistical Inference
  153. Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
  154. Regret Minimization for Piecewise Linear Rewards: Contracts, Auctions, and Beyond
  155. Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation
  156. Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring
  157. When an LLM is apprehensive about its answers -- and when its uncertainty is justified
  158. textscPerseus: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes
  159. An Efficient Learning Method to Connect Observables
  160. GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models
  161. Perceptual Motor Learning with Active Inference Framework for Robust Lateral Control
  162. Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks
  163. Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge
  164. Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization
  165. An Efficient Continual Learning Framework for Multivariate Time Series Prediction Tasks with Application to Vehicle State Estimation
  166. Merging Hazy Sets with m-Schemes: A Geometric Approach to Data Visualization
  167. MUSt3R: Multi-view Network for Stereo 3D Reconstruction
  168. Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks
  169. Detecting Stylistic Fingerprints of Large Language Models
  170. Can Optical Denoising Clean Sonar Images? A Benchmark and Fusion Approach
  171. A Shared Encoder Approach to Multimodal Representation Learning
  172. Distilled Prompt Learning for Incomplete Multimodal Survival Prediction
  173. OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
  174. Cauchy-Schwarz Regularizers
  175. M-SCAN: A Multistage Framework for Lumbar Spinal Canal Stenosis Grading Using Multi-View Cross Attention
  176. Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data
  177. A General Purpose Spectral Foundational Model for Both Proximal and Remote Sensing Spectral Imaging
  178. Annotating and Inferring Compositional Structures in Numeral Systems Across Languages
  179. Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations
  180. DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation
  181. Robust Palm-Vein Recognition Using the MMD Filter: Improving SIFT-Based Feature Matching
  182. In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models
  183. Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
  184. Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering
  185. A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation
  186. Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
  187. Evaluating Stenosis Detection with Grounding DINO, YOLO, and DINO-DETR
  188. Heterogeneity Matters even More in Distributed Learning: Study from Generalization Perspective
  189. STAR: Stability-Inducing Weight Perturbation for Continual Learning
  190. An Efficient Approach to Detecting Lung Nodules Using Swin Transformer
  191. The Role of Deep Learning in Financial Asset Management: A Systematic Review
  192. Category-level Meta-learned NeRF Priors for Efficient Object Mapping
  193. A Selective Learning Method for Temporal Graph Continual Learning
  194. Meta Learning-Driven Iterative Refinement for Robust Anomaly Detection in Industrial Inspection
  195. AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
  196. Attention Condensation via Sparsity Induced Regularized Training
  197. MoCFL: Mobile Cluster Federated Learning Framework for Highly Dynamic Network
  198. Effective High-order Graph Representation Learning for Credit Card Fraud Detection
  199. Co-creation for Sign Language Processing and Machine Translation
  200. None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering
  201. AI-Driven Relocation Tracking in Dynamic Kitchen Environments
  202. Revisiting Large Language Model Pruning using Neuron Semantic Attribution
  203. Entailment vs. Verification for Partial-assignment Satisfiability and Enumeration
  204. Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning
  205. R2VF: A Two-Step Regularization Algorithm to Cluster Categories in GLMs
  206. Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey
  207. KoWit-24: A Richly Annotated Dataset of Wordplay in News Headlines
  208. Enabling AI Scientists to Recognize Innovation: A Domain-Agnostic Algorithm for Assessing Novelty
  209. Compare different SG-Schemes based on large least square problems
  210. SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
  211. Lossy Neural Compression for Geospatial Analytics: A Review
  212. An Approach for Air Drawing Using Background Subtraction and Contour Extraction
  213. Liger: Linearizing Large Language Models to Gated Recurrent Structures
  214. Improving the statistical efficiency of cross-conformal prediction
  215. Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting
  216. InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization
  217. KurTail : Kurtosis-based LLM Quantization
  218. ProRCA: A Causal Python Package for Actionable Root Cause Analysis in Real-world Business Scenarios
  219. Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems
  220. MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
  221. S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging
  222. Primer C-VAE: An interpretable deep learning primer design method to detect emerging virus variants
  223. SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning
  224. Structural Deep Encoding for Table Question Answering
  225. Proper decision trees: An axiomatic framework for solving optimal decision tree problems with arbitrary splitting rules
  226. AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language
  227. Generative Human Geometry Distribution
  228. Leveraging LLMs for Mental Health: Detection and Recommendations from Social Discussions
  229. A Randomized Linearly Convergent Frank-Wolfe-type Method for Smooth Convex Minimization over the Spectrahedron
  230. Trajectory-Class-Aware Multi-Agent Reinforcement Learning
  231. Fall Detection from Indoor Videos using MediaPipe and Handcrafted Feature
  232. Reconstruction of muon bundles in KM3NeT detectors using machine learning methods
  233. How simple can you go? An off-the-shelf transformer approach to molecular dynamics
  234. DLF: Extreme Image Compression with Dual-generative Latent Fusion
  235. MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing
  236. From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems
  237. Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace
  238. Learning to Generate Long-term Future Narrations Describing Activities of Daily Living
  239. Building Interval Type-2 Fuzzy Membership Function: A Deck of Cards based Co-constructive Approach
  240. Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
  241. Hyperspectral image segmentation with a machine learning model trained using quantum annealer
  242. Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election
  243. Learning Conjecturing from Scratch
  244. Blind Augmentation: Calibration-free Camera Distortion Model Estimation for Real-time Mixed-reality Consistency
  245. Geo-Semantic-Parsing: AI-powered geoparsing by traversing semantic knowledge graphs
  246. SwiLTra-Bench: The Swiss Legal Translation Benchmark
  247. Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model
  248. Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
  249. Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging
  250. From Spots to Pixels: Dense Spatial Gene Expression Prediction from Histology Images
  251. Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness
  252. UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
  253. Wavelet-Enhanced Desnowing: A Novel Single Image Restoration Approach for Traffic Surveillance under Adverse Weather Conditions
  254. Composed Multi-modal Retrieval: A Survey of Approaches and Applications
  255. Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models
  256. Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
  257. PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
  258. MAB-Based Channel Scheduling for Asynchronous Federated Learning in Non-Stationary Environments
  259. Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches
  260. OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging
  261. Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension
  262. Regularization-based Framework for Quantization-, Fault- and Variability-Aware Training
  263. PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness
  264. SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
  265. ACTIVA: Amortized Causal Effect Estimation via Transformer-based Variational Autoencoder
  266. Robust Simulation-Based Inference under Missing Data via Neural Processes
  267. Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention
  268. Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning
  269. ChatGPT for President! Presupposed content in politicians versus GPT-generated texts
  270. Multi-Level Collaboration in Model Merging
  271. Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology
  272. Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning
  273. Object-Aware Video Matting with Cross-Frame Guidance
  274. Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
  275. OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest
  276. SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
  277. Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners
  278. Convex Hull-based Algebraic Constraint for Visual Quadric SLAM
  279. Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Clinical Assessment of Diabetic Retinopathy Severity
  280. Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications
  281. Gaussian Process Surrogate Models for Efficient Estimation of Structural Response Distributions and Order Statistics
  282. LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains
  283. Your Model is Overconfident, and Other Lies We Tell Ourselves
  284. Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection
  285. Learning Covariance-Based Multi-Scale Representation of Neuroimaging Measures for Alzheimer Classification
  286. Enhancing Network Security Management in Water Systems using FM-based Attack Attribution
  287. Pre-training Graph Neural Networks with Structural Fingerprints for Materials Discovery
  288. Dementia Insights: A Context-Based MultiModal Approach
  289. HREB-CRF: Hierarchical Reduced-bias EMA for Chinese Named Entity Recognition
  290. Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling
  291. One-Step Event-Driven High-Speed Autofocus
  292. Understanding Dataset Distillation via Spectral Filtering
  293. Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond
  294. Hypergraph Foundation Model
  295. A Multi-Sensor Fusion Approach for Rapid Orthoimage Generation in Large-Scale UAV Mapping
  296. Parameter-free Video Segmentation for Vision and Language Understanding
  297. LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign
  298. PostHoc FREE Calibrating on Kolmogorov Arnold Networks
  299. Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs
  300. Near-infrared Image Deblurring and Event Denoising with Synergistic Neuromorphic Imaging
  301. Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling
  302. Language-Assisted Feature Transformation for Anomaly Detection
  303. SAR-W-MixMAE: SAR Foundation Model Training Using Backscatter Power Weighting
  304. Prognostics and Health Management of Wafer Chemical-Mechanical Polishing System using Autoencoder
  305. HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation
  306. Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
  307. A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models
  308. Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis
  309. Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers
  310. Large Language Models for Healthcare Text Classification: A Systematic Review
  311. EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting
  312. Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting
  313. Nature-Inspired Population-Based Evolution of Large Language Models
  314. STGAN: Spatial-temporal Graph Autoregression Network for Pavement Distress Deterioration Prediction
  315. ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
  316. MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages
  317. Dynamic spillovers and investment strategies across artificial intelligence ETFs, artificial intelligence tokens, and green markets
  318. One-shot In-context Part Segmentation
  319. DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows
  320. Can Large Language Models Help Experimental Design for Causal Discovery?
  321. Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing
  322. Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs
  323. AirRoom: Objects Matter in Room Reidentification
  324. Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming
  325. Constrained multi-fidelity Bayesian optimization with automatic stop condition
  326. ViKANformer: Embedding Kolmogorov Arnold Networks in Vision Transformers for Pattern-Based Learning
  327. Hybrid Metaheuristic Vehicle Routing Problem for Security Dispatch Operations
  328. Large AI Model for Delay-Doppler Domain Channel Prediction in 6G OTFS-Based Vehicular Networks
  329. WeGen: A Unified Model for Interactive Multimodal Generation as We Chat
  330. Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations
  331. FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion
  332. VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors
  333. Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
  334. Ground contact and reaction force sensing for linear policy control of quadruped robot
  335. Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection
  336. Towards Automated Smart Contract Generation: Evaluation, Benchmarking, and Retrieval-Augmented Repair
  337. Measuring the Validity of Clustering Validation Datasets
  338. One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes
  339. Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
  340. Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time
  341. FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet
  342. Identity documents recognition and detection using semantic segmentation with convolutional neural network
  343. Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media
  344. Depth-Adaptive Graph Neural Networks via Learnable Bakry-'Emery Curvature
  345. Learning Stochastic Dynamical Systems with Structured Noise
  346. OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Framework
  347. Vector Copula Variational Inference and Dependent Block Posterior Approximations
  348. Multi-Agent Reinforcement Learning with Long-Term Performance Objectives for Service Workforce Optimization
  349. Language-Guided Object Search in Agricultural Environments
  350. Alchemist: Towards the Design of Efficient Online Continual Learning System
  351. Powerful rank verification for multivariate Gaussian data with any covariance structure