mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 18 Aug 2024

135 papers

  1. Agentic Retrieval-Augmented Generation for Time Series AnalysisRetrieval-augmented generation → Agentic RAG, agents and memory +1
  2. Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph ForecastingRetrieval-augmented generation → Time series and agricultural RAG
  3. DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order OptimizationDiffusion models → Robustness, privacy and adversarial aspects +1
  4. Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  5. Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  6. HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language ModelLLM reasoning → Reasoning for agents, planning and code +1
  7. Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest PathLLM reasoning → Knowledge- and tool-augmented reasoning
  8. Beyond Local Views: Global State Inference with Diffusion Models for Cooperative Multi-Agent Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics
  9. Directed Exploration in Reinforcement Learning from Linear Temporal LogicDeep reinforcement learning methods → Interpretable and logic-guided RL
  10. Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  11. Image-Based Geolocation Using Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  12. Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control FrameworkEnd-to-end autonomous driving → Cooperative and V2X driving
  13. WPN: An Unlearning Method Based on N-pair Contrastive Learning in Language ModelsLLM safety and security → Machine unlearning
  14. CLIP-CID: Efficient CLIP Distillation via Cluster-Instance DiscriminationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  15. Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  16. GRLinQ: An Intelligent Spectrum Sharing Mechanism for Device-to-Device Communications with Graph Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  17. Reward Difference Optimization For Sample Reweighting In Offline RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion ModelDiffusion models → Audio, speech and music
  19. Exploratory Optimal Stopping: A Singular Control FormulationDeep reinforcement learning methods → RL theory and sample complexity
  20. Characterizing and Evaluating the Reliability of LLMs against Jailbreak AttacksLLM safety and security → Jailbreaking
  21. Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent DiffusionDiffusion models → Medical imaging and segmentation
  22. Rethinking Deep Learning: Propagating Information in Neural Networks without Backpropagation and Statistical Optimization
  23. Glyph-Based Uncertainty Visualization and Analysis of Time-Varying Vector Fields
  24. Needles in Needle Stacks: Meaningful Clinical Information Buried in Noisy Waveform Data
  25. Methods based on Radon transform for non-affine deformable image registration of noisy images
  26. GNN-Empowered Effective Partial Observation MARL Method for AoI Management in Multi-UAV Network
  27. EEG Right & Left Voluntary Hand Movement-based Virtual Brain-Computer Interfacing Keyboard Using Hybrid Deep Learning Approach
  28. Neural CRNs: A Natural Implementation of Learning in Chemical Reaction Networks
  29. Gravix: Active Learning for Gravitational Waves Classification Algorithms
  30. An Introduction to Cognidynamics
  31. Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design
  32. NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models
  33. The First Competition on Resource-Limited Infrared Small Target Detection Challenge: Methods and Results
  34. Circuit design in biology and machine learning. I. Random networks and dimensional reduction
  35. Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters
  36. Moonshine: Distilling Game Content Generators into Steerable Generative Models
  37. SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras
  38. On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification
  39. Convolutional Conditional Neural Processes
  40. A Likelihood-Free Approach to Goal-Oriented Bayesian Optimal Experimental Design
  41. A Markov Random Field Multi-Modal Variational AutoEncoder
  42. PhysBERT: A Text Embedding Model for Physics Scientific Literature
  43. Say My Name: a Model's Bias Discovery Framework
  44. MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair
  45. Enhancing ASL Recognition with GCNs and Successive Residual Connections
  46. Grammatical Error Feedback: An Implicit Evaluation Approach
  47. Security Concerns in Quantum Machine Learning as a Service
  48. Generating Automatically Print/Scan Textures for Morphing Attack Detection Applications
  49. Addressing Heterogeneity in Federated Learning: Challenges and Solutions for a Shared Production Environment
  50. Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Images
  51. Seamless Integration: Sampling Strategies in Federated Learning Systems
  52. No Such Thing as a General Learner: Language models and their dual optimization
  53. Using ChatGPT to Score Essays and Short-Form Constructed Responses
  54. Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
  55. Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening
  56. AnomalyFactory: Regard Anomaly Generation as Unsupervised Anomaly Localization
  57. Deep Limit Model-free Prediction in Regression
  58. PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding
  59. ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion
  60. Fine-gained air quality inference based on low-quality sensing data using self-supervised learning
  61. Enhancing Quantum Memory Lifetime with Measurement-Free Local Error Correction and Reinforcement Learning
  62. Understanding Transformer Architecture through Continuous Dynamics: A Partial Differential Equation Perspective
  63. A Logic for Policy Based Resource Exchanges in Multiagent Systems
  64. NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality
  65. Out-of-distribution generalization via composition: a lens through induction heads in Transformers
  66. StyleBrush: Style Extraction and Transfer from a Single Image
  67. Source-Free Test-Time Adaptation For Online Surface-Defect Detection
  68. Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
  69. REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
  70. Activated Parameter Locating via Causal Intervention for Model Merging
  71. PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
  72. Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
  73. Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions
  74. MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment
  75. 3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification
  76. Advancements in Molecular Property Prediction: A Survey of Single and Multimodal Approaches
  77. Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
  78. G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
  79. In-Memory Learning Automata Architecture using Y-Flash Cell
  80. Retina-Inspired Object Motion Segmentation for Event-Cameras
  81. Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
  82. Identifying Speakers and Addressees of Quotations in Novels with Prompt Learning
  83. GraphSPNs: Sum-Product Networks Benefit From Canonical Orderings
  84. From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification
  85. Parameterized Physics-informed Neural Networks for Parameterized PDEs
  86. Parallel Sampling via Counting
  87. Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting
  88. Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition
  89. Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi
  90. HySem: A context length optimized LLM pipeline for unstructured tabular extraction
  91. Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs
  92. Adversarial Attacked Teacher for Unsupervised Domain Adaptive Object Detection
  93. FASST: Fast LLM-based Simultaneous Speech Translation
  94. A Robust Algorithm for Contactless Fingerprint Enhancement and Matching
  95. OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras
  96. Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
  97. Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method
  98. Challenges and Responses in the Practice of Large Language Models
  99. Clustering and Alignment: Understanding the Training Dynamics in Modular Addition
  100. Weakly Supervised Lymph Nodes Segmentation Based on Partial Instance Annotations with Pre-trained Dual-branch Network and Pseudo Label Learning
All 135
  1. BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations
  2. OPPH: A Vision-Based Operator for Measuring Body Movements for Personal Healthcare
  3. VrdONE: One-stage Video Visual Relation Detection
  4. Comparison between the Structures of Word Co-occurrence and Word Similarity Networks for Ill-formed and Well-formed Texts in Taiwan Mandarin
  5. Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversion
  6. Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
  7. OU-CoViT: Copula-Enhanced Bi-Channel Multi-Task Vision Transformers with Dual Adaptation for OU-UWF Images
  8. Federated Graph Learning with Structure Proxy Alignment
  9. Game Development as Human-LLM Interaction
  10. VRCopilot: Authoring 3D Layouts with Generative AI Models in VR
  11. ELASTIC: Efficient Linear Attention for Sequential Interest Compression
  12. Mutual Information Multinomial Estimation
  13. Detecting the Undetectable: Combining Kolmogorov-Arnold Networks and MLP for AI-Generated Image Detection
  14. Flemme: A Flexible and Modular Learning Platform for Medical Images
  15. Improving Lung Cancer Diagnosis and Survival Prediction with Deep Learning and CT Imaging
  16. Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities
  17. Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting
  18. Angle of Arrival Estimation with Transformer: A Sparse and Gridless Method with Zero-Shot Capability
  19. Behavioral Learning of Dish Rinsing and Scrubbing based on Interruptive Direct Teaching Considering Assistance Rate
  20. Panorama Tomosynthesis from Head CBCT with Simulated Projection Geometry
  21. Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation
  22. Joint Temporal Pooling for Improving Skeleton-based Action Recognition
  23. Boundary-Recovering Network for Temporal Action Detection
  24. E-CGL: An Efficient Continual Graph Learner
  25. Hyperstroke: A Novel High-quality Stroke Representation for Assistive Artistic Drawing
  26. S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis
  27. Enhanced BPINN Training Convergence in Solving General and Multi-scale Elliptic PDEs with Noise
  28. Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration
  29. SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama
  30. YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems
  31. Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset
  32. Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs
  33. A Probabilistic Framework for Adapting to Changing and Recurring Concepts in Data Streams
  34. Predicting travel demand of a bike sharing system using graph convolutional neural networks
  35. Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously