mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 13 Apr 2025

167 papers

  1. HEAT:History-Enhanced Dual-phase Actor-Critic Algorithm with A Shared TransformerDeep reinforcement learning methods → RL for energy, networks and operations
  2. CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM AgentLLM agents and tool use → Agent threats, guardrails and governance
  3. QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized ModelLLM reasoning → Clinical and biomedical applications
  4. Meta-Evaluating Local LLMs: Rethinking Performance Metrics for Serious GamesLLM reasoning → Reasoning for agents, planning and code
  5. HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  6. AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature ReuseDiffusion models → Diffusion foundations and sampling
  7. A Survey on Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM AgentsLLM agents and tool use → Web, search, and research agents
  9. The Structural Safety Generalization ProblemLLM safety and security → Safety alignment, refusal and guardrails
  10. DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingLLM reasoning → Reinforcement learning for reasoning
  11. MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?LLM agents and tool use → Web, search, and research agents
  12. SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing WorkflowDiffusion models → Image generation, text-to-image and editing
  13. GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language ModelsLLM reasoning → Reinforcement learning for reasoning
  14. AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent SimulationsLLM agents and tool use → Social simulation and multi-agent debate
  15. KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual AnimationDiffusion models → Video generation
  16. OmniMamba4D: Spatio-temporal Mamba for longitudinal CT lesion segmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  17. SegEarth-R1: Geospatial Pixel Reasoning via Large Language ModelLLM reasoning → Spatial and embodied reasoning
  18. Iterative Self-Training for Code Generation via Reinforced Re-RankingSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  19. TinyLLaVA-Video-R1: Towards Smaller LMMs for Video ReasoningLLM reasoning → Multimodal reasoning +1
  20. Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model CapabilityLLM reasoning → Test-time compute and efficient thinking
  21. Slow Thinking for Sequential RecommendationLLM reasoning → LLM reasoning for recommendation
  22. Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian InferenceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded GapsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient TrainingDiffusion models → Diffusion foundations and sampling
  25. Mitigating Many-Shot JailbreakingLLM safety and security → Jailbreaking
  26. Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical SegmentationMixture-of-experts → Medical and biomedical MoE
  27. DualPrompt-MedCap: A Dual-Prompt Enhanced Approach for Medical Image CaptioningMultimodal LLMs / vision-language models → Medical vision-language models
  28. ControlNET: A Firewall for RAG-based LLM SystemRetrieval-augmented generation → Privacy and security of RAG +1
  29. Efficient LLM Serving on Hybrid Real-time and Best-effort RequestsEfficient LLM inference and serving → Serving systems and request scheduling
  30. GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigationLLM reasoning → Spatial and embodied reasoning
  31. Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust PerformanceLLM reasoning → Prompting and chain-of-thought reasoning
  32. AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic UnderstandingLLM agents and tool use → Multimodal and embodied agents
  33. Syzygy of Thoughts: Improving LLM CoT with the Minimal Free ResolutionLLM reasoning → Prompting and chain-of-thought reasoning
  34. LoopLynx: A Scalable Dataflow Architecture for Efficient LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  35. Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-ManipulationLLM agents and tool use → Multimodal and embodied agents
  36. DiffuMural: Restoring Dunhuang Murals with Multi-scale DiffusionDiffusion models → Image generation, text-to-image and editing
  37. GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder AlignmentLLM reasoning → Reasoning benchmarks and evaluation
  38. Vision-Language Model for Object Detection and Segmentation: A Review and EvaluationMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  39. Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram GenerationLLM reasoning → Multimodal reasoning
  40. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak DefenderLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  41. Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  42. D2iT: Dynamic Diffusion Transformer for Accurate Image GenerationDiffusion models → Diffusion foundations and sampling
  43. FractalForensics: Proactive Deepfake Detection and Localization via Fractal WatermarksLLM safety and security → Watermarking generated content and models
  44. Sparse Deformable Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  45. Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination DetectionLLM reasoning → Mathematical reasoning
  46. Identity-Aware Vision-Language Model for Explainable Face Forgery DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  47. BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant LearningLLM reasoning → Multimodal reasoning +1
  48. ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language modelLLM reasoning → Clinical and biomedical applications
  49. SaRO: Enhancing LLM Safety through Reasoning-based AlignmentLLM reasoning → Reasoning for agents, planning and code +2
  50. UXAgent: A System for Simulating Usability Testing of Web Design with LLM AgentsLLM agents and tool use → GUI and mobile agents
  51. Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step ReadingLLM reasoning → Reasoning benchmarks and evaluation
  52. Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic RegimesDeep reinforcement learning methods → RL theory and sample complexity
  53. DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion TransformersDiffusion models → Audio, speech and music
  54. Towards Automated Formal Verification of Backend Systems with LLMs
  55. Dual-Modality Computational Ophthalmic Imaging with Deep Learning and Coaxial Optical Design
  56. Psychological Effect of AI driven marketing tools for beauty/facial feature enhancement
  57. Two-Timescale Joint Transmit and Pinching Beamforming for Pinching-Antenna Systems
  58. SeizureFormer: A Transformer Model for IEA-Based Seizure Risk Forecasting
  59. A CNN-based Local-Global Self-Attention via Averaged Window Embeddings for Hierarchical ECG Analysis
  60. The Quantum LLM: Modeling Semantic Spaces with Quantum Principles
  61. Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation
  62. Can the capability of Large Language Models be described by human ability? A Meta Study
  63. Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation
  64. snnTrans-DHZ: A Lightweight Spiking Neural Network Architecture for Underwater Image Dehazing
  65. Intelligent driving vehicle front multi-target tracking and detection based on YOLOv5 and point cloud 3D projection
  66. HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
  67. An Efficient Quantum Classifier Based on Hamiltonian Representations
  68. Multi-Modal Hypergraph Enhanced LLM Learning for Recommendation
  69. Physics-Informed Neural Networks for Enhanced Interface Preservation in Lattice Boltzmann Multiphase Simulations
  70. Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation
  71. Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP
  72. Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
  73. Enhancing Classifier Evaluation: A Fairer Benchmarking Strategy Based on Ability and Robustness
  74. Integrating Large Language Models for Automated Structural Analysis
  75. Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance
  76. Stochastic generative methods for stable and accurate closure modeling of chaotic dynamical systems
  77. Automatic Detection of Intro and Credits in Video using CLIP and Multihead Attention
  78. Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025
  79. Dynamik: Syntactically-Driven Dynamic Font Sizing for Emphasis of Key Information
  80. Epsilon-Neighborhood Decision-Boundary Governed Estimation (EDGE) of 2D Black Box Classifier Functions
  81. Adapting Robot's Explanation for Failures Based on Observed Human Behavior in Human-Robot Collaboration
  82. Dominated Actions in Imperfect-Information Games
  83. Evaluating the Quality of Benchmark Datasets for Low-Resource Languages: A Case Study on Turkish
  84. Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization
  85. InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals
  86. Modeling Discrete Coating Degradation Events via Hawkes Processes
  87. Transformer-Based Representation Learning for Robust Gene Expression Modeling and Cancer Prognosis
  88. ToolTipNet: A Segmentation-Driven Deep Learning Baseline for Surgical Instrument Tip Detection
  89. Computer-Aided Layout Generation for Building Design: A Review
  90. Migrating Code At Scale With LLMs At Google
  91. EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
  92. Domain-Adaptive Continued Pre-Training of Small Language Models
  93. Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?
  94. SPOT: Spatio-Temporal Pattern Mining and Optimization for Load Consolidation in Freight Transportation Networks
  95. LightHeadEd: Relightable & Editable Head Avatars from a Smartphone
  96. Uncertainty Guided Refinement for Fine-Grained Salient Object Detection
  97. CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering
  98. Adapting to the Unknown: Robust Meta-Learning for Zero-Shot Financial Time Series Forecasting
  99. Ordinary Least Squares as an Attention Mechanism
  100. RANSAC Revisited: An Improved Algorithm for Robust Subspace Recovery under Adversarial and Noisy Corruptions
All 167
  1. Building AI Service Repositories for On-Demand Service Orchestration in 6G AI-RAN
  2. Myanmar XNLI: Building a Dataset and Exploring Low-resource Approaches to Natural Language Inference with Myanmar
  3. A Two-Stage Interpretable Matching Framework for Causal Inference
  4. Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
  5. Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding
  6. Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
  7. A highly maneuverable flying squirrel drone with agility-improving foldable wings
  8. Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations
  9. Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
  10. TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting
  11. Reduction of Supervision for Biomedical Knowledge Discovery
  12. An Improved FOX Optimization Algorithm Using Adaptive Exploration and Exploitation for Global Optimization
  13. LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
  14. From Conditional to Unconditional Independence: Testing Conditional Independence via Transport Maps
  15. Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark
  16. SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification
  17. A simulation-heuristics dual-process model for intuitive physics
  18. Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling
  19. EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler
  20. FastRSR: Efficient and Accurate Road Surface Reconstruction from Bird's Eye View
  21. Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders
  22. AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions
  23. How new data permeates LLM knowledge and how to dilute it
  24. 3D CoCa: Contrastive Learners are 3D Captioners
  25. FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding
  26. Capturing Longitudinal Changes in Brain Morphology Using Temporally Parameterized Neural Displacement Fields
  27. Optimal sparse phase retrieval via a quasi-Bayesian approach
  28. FVOS for MOSE Track of 4th PVUW Challenge: 3rd Place Solution
  29. Pillar-Voxel Fusion Network for 3D Object Detection in Airborne Hyperspectral Point Clouds
  30. MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs
  31. PCM-SAR: Physics-Driven Contrastive Mutual Learning for SAR Classification
  32. Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning
  33. EasyREG: Easy Depth-Based Markerless Registration and Tracking using Augmented Reality Device for Surgical Guidance
  34. Federated Prototype Graph Learning
  35. DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
  36. Kongzi: A Historical Large Language Model with Fact Enhancement
  37. Adaptive Cluster-Based Synthetic Minority Oversampling Technique for Traffic Mode Choice Prediction with Imbalanced Dataset
  38. An overview of condensation phenomenon in deep learning
  39. HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
  40. Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation
  41. A highly maneuverable flying squirrel drone with controllable foldable wings
  42. MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
  43. Zero-Shot Personalized Camera Motion Control for Image-to-Video Synthesis
  44. Comorbidity-Informed Transfer Learning for Neuro-developmental Disorder Diagnosis
  45. Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach
  46. Enhancing Wide-Angle Image Using Narrow-Angle View of the Same Scene
  47. aweSOM: a CPU/GPU-accelerated Self-organizing Map and Statistically Combined Ensemble Framework for Machine-learning Clustering Analysis
  48. Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization
  49. Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidance
  50. Constants of motion network revisited
  51. Predicting ulcer in H&E images of inflammatory bowel disease using domain-knowledge-driven graph neural network
  52. FROG: Effective Friend Recommendation in Online Games via Modality-aware User Preferences
  53. Ensemble-Enhanced Graph Autoencoder with GAT and Transformer-Based Encoders for Robust Fault Diagnosis
  54. Comparing Performance of Preprocessing Techniques for Traffic Sign Recognition Using a HOG-SVM
  55. Spatially Directional Dual-Attention GAT for Spatial Fluoride Health Risk Modeling
  56. Nash Equilibrium Between Consumer Electronic Devices and DoS Attacker for Distributed IoT-enabled RSE Systems
  57. Mirror Descent Linearized Augmented Lagrangian Methods for Nonconvex Constrained Stochastic Zeroth-Order Optimization
  58. Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training
  59. Composable NLP Workflows for BERT-based Ranking and QA System
  60. Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification
  61. Vision Transformers Exhibit Human-Like Biases: Evidence of Orientation and Color Selectivity, Categorical Perception, and Phase Transitions
  62. Measuring LLM Novelty As The Frontier Of Original And High-Quality Output
  63. On Language Models' Sensitivity to Suspicious Coincidences
  64. Expressivity of Quadratic Neural ODEs
  65. Contour Flow Constraint: Preserving Global Shape Similarity for Deep Learning based Image Segmentation
  66. Low-Light Image Enhancement using Event-Based Illumination Estimation
  67. Can you map it to English? The Role of Cross-Lingual Alignment in Multilingual Performance of LLMs