mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 28 Jun 2025

151 papers

  1. RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context DivergenceRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  2. DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk PredictionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  3. Iterative Zoom-In: Temporal Interval Exploration for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  4. SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement LearningDeep reinforcement learning methods → Spiking and neuromorphic RL
  5. Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy NetworksDeep reinforcement learning methods → Adversarial robustness and RL in finance
  6. Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based RetrievalRetrieval-augmented generation → RAG robustness and adaptive retrieval
  7. Scenario-Based Hierarchical Reinforcement Learning for Automated Driving Decision MakingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  8. MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language ModelsLLM reasoning → Audio-language model reasoning +1
  9. A Reinforcement Learning Approach for Optimal Control in MicrogridsDeep reinforcement learning methods → RL for energy, networks and operations
  10. MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and PlanningLLM reasoning → Spatial and embodied reasoning
  11. Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  12. Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  13. Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  15. GamerAstra: Supporting 2D Non-Twitch Video Games for Blind and Low-Vision Players through a Multi-Agent FrameworkLLM agents and tool use → Reinforcement learning for LLM agents
  16. Improving Rationality in the Reasoning Process of Language Models through Self-playing GameLLM reasoning → Reasoning for agents, planning and code +1
  17. Hecto: Modular Sparse Experts for Adaptive and Interpretable ReasoningMixture-of-experts → MoE large language models
  18. Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle ExampleDeep reinforcement learning methods → RL for autonomous driving and traffic
  19. Agentic Enterprise: AI-Centric User to User-Centric AILLM agents and tool use → Software engineering coding agents
  20. CA-Diff: Collaborative Anatomy Diffusion for Brain Tissue SegmentationDiffusion models → Medical imaging and segmentation
  21. Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and GrounderLLM reasoning → Multimodal reasoning
  22. ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  23. DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party DialoguesLLM agents and tool use → Tool learning and function calling
  24. Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog SystemsLLM agents and tool use → Web, search, and research agents
  25. Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionalityDeep reinforcement learning methods → RL theory and sample complexity
  26. Listener-Rewarded Thinking in VLMs for Image PreferencesLLM reasoning → Multimodal reasoning +2
  27. Prompting without Panic: Attribute-aware, Zero-shot, Test-Time CalibrationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  28. Memory as a Service (MaaS): Purpose-Bound Memory Mediation for Cooperative AgentsLLM agents and tool use → Agent memory systems
  29. Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention GateDiffusion models → Robustness, privacy and adversarial aspects
  30. RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  31. Offline Reinforcement Learning for Mobility Robustness OptimizationOffline RL and imitation learning from data → Offline multi-agent RL
  32. Multimodal Atmospheric Super-Resolution With Deep Generative ModelsDiffusion models → Diffusion foundations and sampling
  33. Teaching Models to Verbalize Reward Hacking in Chain-of-Thought ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  34. VSRM: A Robust Mamba-Based Framework for Video Super-ResolutionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  35. Enhancing Android Malware Detection with Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  36. RAILS: Retrieval-Augmented Intelligence for Learning Software DevelopmentRetrieval-augmented generation → RAG for code
  37. FairMarket-RL: LLM-Guided Fairness Shaping for Multi-Agent Reinforcement Learning in Peer-to-Peer MarketsLLM agents and tool use → Financial trading and forecasting agents
  38. P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial CodeRetrieval-augmented generation → RAG for code
  39. VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMsEfficient LLM inference and serving → Speculative decoding
  40. Disaster Informatics after the COVID-19 Pandemic: Bibliometric and Topic Analysis based on Large-scale Academic Literature
  41. A parametric activation function based on Wendland RBF
  42. Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counseling
  43. The Application of Large Language Models on Major Depressive Disorder Support Based on African Natural Products
  44. Beyond Parallelism: Synergistic Computational Graph Effects in Multi-Head Attention
  45. Predicting and Explaining Customer Data Sharing in the Open Banking
  46. A Data Science Approach to Calcutta High Court Judgments: An Efficient LLM and RAG-powered Framework for Summarization and Similar Cases Retrieval
  47. Loop2Net: Data-Driven Generation and Optimization of Airfoil CFD Meshes from Sparse Boundary Coordinates
  48. Evaluating Pavement Deterioration Rates Due to Flooding Events Using Explainable AI
  49. Prompt Mechanisms in Medical Imaging: A Comprehensive Survey
  50. An efficient plant disease detection using transfer learning approach
  51. MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding
  52. InSight-R: A Framework for Risk-informed Human Failure Event Identification and Interface-Induced Risk Assessment Driven by AutoGraph
  53. Inpainting is All You Need: A Diffusion-based Augmentation Method for Semi-supervised Medical Image Segmentation
  54. What Must a Fairness Audit Report When Demographic Data Is Incomplete?
  55. VisionScores -- A system-segmented image score dataset for deep learning tasks
  56. Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models
  57. BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
  58. Deep Learning in Mild Cognitive Impairment Diagnosis using Eye Movements and Image Content in Visual Memory Tasks
  59. Generating Privacy Stories From Software Documentation
  60. On Universality of Non-Separable Approximate Message Passing Algorithms
  61. A Novel Frame Identification and Synchronization Technique for Smartphone Visible Light Communication Systems Based on Convolutional Neural Networks
  62. Kernel Outlier Detection
  63. Cybersecurity-Focused Anomaly Detection in Connected Autonomous Vehicles Using Machine Learning
  64. A Systematic Study of Compositional Syntactic Transformer Language Models
  65. On the Generalizability of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals"
  66. Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
  67. Hierarchical Decentralized Stochastic Control for Cyber-Physical Systems
  68. Against 'softmaxing' culture
  69. ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
  70. CN-SBM: Categorical Block Modelling For Primary and Residual Copy Number Variation
  71. Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
  72. YM-WML: A new Yolo-based segmentation Model with Weighted Multi-class Loss for medical imaging
  73. Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization
  74. A Study on Semi-Supervised Detection of DDoS Attacks under Class Imbalance
  75. Positioning AI Tools to Support Online Harm Reduction Practice: Applications and Design Directions
  76. Utilizing a Novel Deep Learning Method for Scene Categorization in Remote Sensing Data
  77. Efficient Cybersecurity Assessment Using SVM and Fuzzy Evidential Reasoning for Resilient Infrastructure
  78. Differentiable Radar Ambiguity Functions: Mathematical Formulation and Computational Implementation
  79. Towards Explainable Bilingual Multimodal Misinformation Detection and Localization
  80. Mathematical Computation on High-dimensional Data via Array Programming and Parallel Acceleration
  81. Towards Time Series Generation Conditioned on Unstructured Natural Language
  82. Learning Truthful Mechanisms without Discretization
  83. Attention to the Burstiness in Visual Prompt Tuning!
  84. MagShield: Towards Better Robustness in Sparse Inertial Motion Capture Under Magnetic Disturbances
  85. Point Cloud Compression and Objective Quality Assessment: A Survey
  86. Missing-Modality-Aware Graph Neural Network for Cancer Classification
  87. MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering
  88. Neural Cellular Automata: From Cells to Pixels
  89. Interpretable Time Series Autoregression for Periodicity Quantification
  90. CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems
  91. Performance Measurements in the AI-Centric Computing Continuum Systems
  92. CLIP-like Model as a Foundational Density Ratio Estimator
  93. P2U: Progressive Precision Update For Efficient Model Distribution
  94. STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing
  95. Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception
  96. Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval
  97. Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram
  98. Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions
  99. DMD-Net: Deep Mesh Denoising Network
  100. Scalable Structure Learning of Bayesian Networks by Learning Algorithm Ensembles
All 151
  1. Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization
  2. Quantum Neural Networks for Wind Energy Forecasting: A Comparative Study of Performance and Scalability with Classical Models
  3. AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results
  4. xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
  5. FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition
  6. SemFaceEdit: Semantic Face Editing on Generative Radiance Manifolds
  7. Denoising Multi-Color QR Codes and Stiefel-Valued Data by Relaxed Regularizations
  8. Deep learning four decades of human migration
  9. TriADA: Massively Parallel Trilinear Matrix-by-Tensor Multiply-Add Algorithm and Device Architecture for the Acceleration of 3D Discrete Transformations
  10. Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding
  11. Efficient Multi-Crop Saliency Partitioning for Automatic Image Cropping
  12. Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models
  13. Learning Adapter Rank via Symmetry Breaking
  14. MedEthicsQA: A Comprehensive Question Answering Benchmark for Medical Ethics Evaluation of LLMs
  15. FreqDGT: Frequency-Adaptive Dynamic Graph Networks with Transformer for Cross-subject EEG Emotion Recognition
  16. Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding
  17. Riemannian-Geometric Fingerprints of Generative Models
  18. VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
  19. ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
  20. ICME 2025 Generalizable HDR and SDR Video Quality Measurement Grand Challenge
  21. WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing
  22. Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching
  23. PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detection
  24. Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation
  25. Bridging Ethical Principles and Algorithmic Methods: An Alternative Approach for Assessing Trustworthiness in AI Systems
  26. Not All Water Consumption Is Equal: A Water Stress Weighted Metric for Sustainable Computing
  27. FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision
  28. Can We Reliably Predict the Fed's Next Move? A Multi-Modal Approach to U.S. Monetary Policy Forecasting
  29. Jan-nano Technical Report
  30. RoboPearls: Editable Video Simulation for Robot Manipulation
  31. Doubly robust estimation of causal effects for random object outcomes with continuous treatments
  32. Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography
  33. Deep Learning based Joint Geometry and Attribute Up-sampling for Large-Scale Colored Point Clouds
  34. Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
  35. UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments
  36. Robust Tensor Completion via Gradient Tensor Nulclear L1-L2 Norm for Traffic Data Recovery
  37. Persistence Paradox in Dynamic Science: Evidence from the Deep Learning Revolution
  38. XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge
  39. The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure
  40. Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
  41. Deterministic Object Pose Confidence Region Estimation
  42. Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians
  43. BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
  44. Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication
  45. Generalized Linear Mode Connectivity for Transformers
  46. LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning
  47. General Autonomous Cybersecurity Defense: Learning Robust Policies for Dynamic Topologies and Diverse Attackers
  48. Beyond Code: The Multidimensional Impacts of Large Language Models in Software Development
  49. Lower bounds for trace estimation via Block Krylov and other methods
  50. Text Production and Comprehension by Human and Artificial Intelligence: Interdisciplinary Workshop Report
  51. Residual Matrix Transformers: Scaling the Size of the Residual Stream