mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 17 Nov 2024

111 papers

  1. Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time ApplicationsDeep reinforcement learning methods → RL for energy, networks and operations
  2. AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics DataRetrieval-augmented generation → RAG pipeline design and evaluation
  3. On-Board Vision-Language Models for Personalized Autonomous Vehicle Motion Control: System Design and Real-World ValidationMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  4. F3OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-HeuristicsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  5. SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  6. Debiasing Watermarks for Large Language Models via Maximal CouplingLLM safety and security → Watermarking generated content and models
  7. Stealing Training Graphs from Graph Neural NetworksDiffusion models → Flow matching, time series and science
  8. AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with TransformersDeep reinforcement learning methods → Deep RL algorithms and representations
  9. Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive RobotsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  10. Robust Defense Against Extreme Grid Events Using Dual-Policy Reinforcement Learning AgentsDeep reinforcement learning methods → RL for energy, networks and operations
  11. CLMIA: Membership Inference Attacks via Unsupervised Contrastive LearningLLM safety and security → Membership inference attacks
  12. Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion MethodDiffusion models → Image generation, text-to-image and editing
  13. JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and CircuitLLM safety and security → Jailbreaking
  14. An Investigation of Offline Reinforcement Learning in Factorisable Action SpacesOffline RL and imitation learning from data → Offline RL algorithms
  15. D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical ClassificationDiffusion models → Medical imaging and segmentation
  16. TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  17. FastDraft: How to Train Your DraftEfficient LLM inference and serving → Speculative decoding
  18. SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code GenerationLLM reasoning → Reasoning for agents, planning and code
  19. Efficient Federated Unlearning with Adaptive Differential Privacy PreservationLLM safety and security → Federated unlearning and poisoning
  20. FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball MethodLLM safety and security → Federated unlearning and poisoning
  21. Time Step Generating: A Universal Synthesized Deepfake Image DetectorDiffusion models → Image generation, text-to-image and editing
  22. BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationLLM safety and security → Backdoor and data poisoning attacks
  23. Modulating Reservoir Dynamics via Reinforcement Learning for Efficient Robot Skill SynthesisDeep reinforcement learning methods → Deep RL algorithms and representations
  24. VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?Multimodal LLMs / vision-language models → Video understanding with MLLMs
  25. Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  26. Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained InquiryMultimodal LLMs / vision-language models → Medical vision-language models
  27. Constrained Diffusion with Trust SamplingDiffusion models → Diffusion foundations and sampling
  28. Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Leveraging Large Language Models for Generating Labeled Mineral Site Record Linkage Data
  30. Back-filling Missing Data When Predicting Domestic Electricity Consumption From Smart Meter Data
  31. Improving Tool Retrieval by Leveraging Large Language Models for Query Generation
  32. Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph
  33. Image Forgery Localization via Guided Noise and Multi-Scale Feature Aggregation
  34. AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings
  35. Leveraging AI and NLP for Bank Marketing: A Systematic Review and Gap Analysis
  36. Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
  37. Artificial Intelligence in Cybersecurity: Building Resilient Cyber Diplomacy Frameworks
  38. SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text
  39. ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling
  40. AIGS: Generating Science from AI-Powered Automated Falsification
  41. Capturing Sparks of Abstraction for the ARC Challenge
  42. Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
  43. BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression
  44. PickScan: Object discovery and reconstruction from handheld interactions
  45. Accelerating Quantum Emitter Characterization with Latent Neural Ordinary Differential Equations
  46. DeepSPV: A Deep Learning Pipeline for 3D Spleen Volume Estimation from 2D Ultrasound Images
  47. Freqformer: Frequency-Domain Transformer for 3-D Reconstruction and Quantification of Human Retinal Vasculature
  48. Mixing Neural Networks and Exponential Moving Averages for Predicting Wireless Links Behavior
  49. Enhanced Anime Image Generation Using USE-CMHSA-GAN
  50. Infinite Width Limits of Self Supervised Neural Networks
  51. Learning the Sherrington-Kirkpatrick Model Even at Low Temperature
  52. LL"aMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch
  53. RPN 2: On Interdependence Function Learning Towards Unifying and Advancing CNN, RNN, GNN, and Transformer
  54. MPLite: Multi-Aspect Pretraining for Mining Clinical Health Records
  55. Federated Learning for UAV-Based Spectrum Sensing: Enhancing Accuracy Through SNR-Weighted Model Aggregation
  56. Person Segmentation and Action Classification for Multi-Channel Hemisphere Field of View LiDAR Sensors
  57. A Comprehensive Survey on Visual Question Answering Datasets and Algorithms
  58. From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis
  59. TabDeco: A Comprehensive Contrastive Framework for Decoupled Representations in Tabular Data
  60. Variational Bayesian Bow tie Neural Networks with Shrinkage
  61. DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation
  62. Retinal Vessel Segmentation via Neuron Programming
  63. Label Sharing Incremental Learning Framework for Independent Multi-Label Segmentation Tasks
  64. Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
  65. Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
  66. MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild
  67. STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks
  68. The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection
  69. Electrostatic Force Regularization for Neural Structured Pruning
  70. Spectral Subspace Clustering for Attributed Graphs
  71. Machine learning-based probabilistic forecasting of solar irradiance in Chile
  72. Multilingual Large Language Models: A Systematic Survey
  73. Skeleton-Guided Spatial-Temporal Feature Learning for Video-Based Visible-Infrared Person Re-Identification
  74. Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text
  75. Reinforcing Competitive Multi-Agents for Playing 'So Long Sucker'
  76. Generating medical screening questionnaires through analysis of social media data
  77. Knowledge-enhanced Transformer for Multivariate Long Sequence Time-series Forecasting
  78. StableV2V: Stablizing Shape Consistency in Video-to-Video Editing
  79. EfQAT: An Efficient Framework for Quantization-Aware Training
  80. Wafer Map Defect Classification Using Autoencoder-Based Data Augmentation and Convolutional Neural Network
  81. BianCang: A Traditional Chinese Medicine Large Language Model
  82. VeGaS: Video Gaussian Splatting
  83. Training a Label-Noise-Resistant GNN with Reduced Complexity
  84. CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules
  85. EROAM: Event-based Camera Rotational Odometry and Mapping in Real-time
  86. TeG: Temporal-Granularity Method for Anomaly Detection with Attention in Smart City Surveillance
  87. Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
  88. Off the Normal Path: Learning Spatial Density Models of Node Mobility
  89. AppSign: Multi-level Approximate Computing for Real-Time Traffic Sign Recognition in Autonomous Vehicles
  90. Framework for developing and evaluating ethical collaboration between expert and machine
  91. Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations
  92. V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception
  93. Map-Free Trajectory Prediction with Map Distillation and Hierarchical Encoding
  94. Program Evaluation with Remotely Sensed Outcomes
  95. SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
  96. STAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs
  97. A Topic-aware Comparable Corpus of Chinese Variations
  98. Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
  99. TSFormer: A Robust Framework for Efficient UHD Image Restoration
  100. Towards Accurate and Efficient Sub-8-Bit Integer Training
All 111
  1. Direct and Explicit 3D Generation from a Single Image
  2. Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera
  3. A Monocular SLAM-based Multi-User Positioning System with Image Occlusion in Augmented Reality
  4. Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion
  5. Analyzing Pok'emon and Mario Streamers' Twitch Chat with LLM-based User Embeddings
  6. Compositional Phoneme Approximation for L1-Grounded L2 Pronunciation Training
  7. Hyperspectral Imaging-Based Grain Quality Assessment With Limited Labelled Data
  8. Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
  9. Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
  10. Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness Assessment
  11. INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection