mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 10 Aug 2024

108 papers

  1. Pretrained-Guided Conditional Diffusion Models for Microbiome Data AnalysisDiffusion models → Flow matching, time series and science
  2. Eigen Attention: Attention in Low-Rank Space for KV Cache CompressionLLM reasoning → Test-time compute and efficient thinking +1
  3. Speculative Diffusion Decoding: Accelerating Language Generation through DiffusionEfficient LLM inference and serving → Speculative decoding
  4. Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality DemonstrationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  5. Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at ScaleEnd-to-end autonomous driving → Cooperative and V2X driving
  6. Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMsRetrieval-augmented generation → Generation and context integration
  7. SWIFT:A Scalable lightWeight Infrastructure for Fine-TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  8. LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at ScaleEfficient LLM inference and serving → Serving systems and request scheduling
  9. ZePo: Zero-Shot Portrait Stylization with Faster SamplingDiffusion models → Image generation, text-to-image and editing
  10. ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial AttackDiffusion models → Robustness, privacy and adversarial aspects
  11. Multi-Agent Planning Using Visual Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  12. Trajectory Planning for Teleoperated Space Manipulators Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  13. Multimodal generative semantic communication based on latent diffusion modelDiffusion models → Diffusion for compression and wireless
  14. Mathematical Models of Computation in SuperpositionMechanistic interpretability → Sparse autoencoder training and evaluation
  15. HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at KuaishouMixture-of-experts → MoE theory and gating functions
  16. High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion ModelDiffusion models → Audio, speech and music
  17. Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Models
  18. Transformer-based Neuro-Animator for Qualitative Simulation of Soft Body Movement
  19. Balancing Innovation and Ethics in AI-Driven Software Development
  20. Hierarchical Multi-Armed Bandits for the Concurrent Intelligent Tutoring of Concepts and Problems of Varying Difficulty Levels
  21. ViC: Virtual Compiler Is All You Need For Assembly Code Search
  22. Dilated Convolution with Learnable Spacings
  23. FedRobo: Federated Learning Driven Autonomous Inter Robots Communication For Optimal Chemical Sprays
  24. WiDe-analysis: Enabling One-click Content Moderation Analysis on Wikipedia's Articles for Deletion
  25. Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasets
  26. Controlling for discrete unmeasured confounding in nonlinear causal models
  27. BeyondCT: A deep learning model for predicting pulmonary function from chest CT scans
  28. Federated Smoothing Proximal Gradient for Quantile Regression with Non-Convex Penalties
  29. Enhancing Computational Efficiency in Intensive Domains via Redundant Residue Number Systems
  30. Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis
  31. PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer
  32. Quantum-secure multiparty deep learning
  33. Forecasting Day-Ahead Electricity Prices in the Integrated Single Electricity Market: Addressing Volatility with Comparative Machine Learning Methods
  34. An Information-Theoretic Analysis of Temporal GNNs
  35. A forward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations
  36. UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling
  37. Residual-INR: Communication Efficient On-Device Learning Using Implicit Neural Representation
  38. Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Performance
  39. Safety Enhancement in Planetary Rovers: Early Detection of Tip-over Risks Using Autoencoders
  40. Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
  41. Meta Clustering of Neural Bandits
  42. Dynamical causality under invisible confounders
  43. Non-Negative Reduced Biquaternion Matrix Factorization with Applications in Color Face Recognition
  44. Camera Perspective Transformation to Bird's Eye View via Spatial Transformer Model for Road Intersection Monitoring
  45. In-Context Exploiter for Extensive-Form Games
  46. Metacognitive Myopia in Large Language Models
  47. Document-Level Event Extraction with Definition-Driven ICL
  48. Impacts of Darwinian Evolution on Pre-trained Deep Neural Networks
  49. What Matters in Autonomous Driving Anomaly Detection: A Weakly Supervised Horizon
  50. Incremental Gauss-Newton Descent for Machine Learning
  51. Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matching
  52. Evolutionary Neural Architecture Search for 3D Point Cloud Analysis
  53. Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction
  54. Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text
  55. Multi-layer Sequence Labeling-based Joint Biomedical Event Extraction
  56. PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacement
  57. P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training
  58. Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
  59. S-SIRUS: an explainability algorithm for spatial regression Random Forest
  60. Latent class analysis for multi-layer categorical data
  61. Can LLMs Replace Manual Annotation of Software Engineering Artifacts?
  62. Radiance Field Learners As UAV First-Person Viewers
  63. CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM
  64. DeepFace-Attention: Multimodal Face Biometrics for Attention Estimation with Application to e-Learning
  65. Long working distance portable smartphone microscopy for metallic mesh defect detection
  66. Anticipation through Head Pose Estimation: a preliminary study
  67. PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecture
  68. Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers
  69. Disentangled Noisy Correspondence Learning
  70. GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph
  71. PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
  72. A Laplacian-based Quantum Graph Neural Network for Semi-Supervised Learning
  73. MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge
  74. Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks
  75. Structure and Reduction of MCTS for Explainable-AI
  76. Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
  77. Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE
  78. Artworks Reimagined: Exploring Human-AI Co-Creation through Body Prompting
  79. Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network
  80. A Structural Feature-Based Approach for Comprehensive Graph Classification
  81. FuXi Weather: A data-to-forecast machine learning system for global weather
  82. A Versatile Framework for Attributed Network Clustering via K-Nearest Neighbor Augmentation
  83. Investigating Instruction Tuning Large Language Models on Graphs
  84. Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation
  85. EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency
  86. Unidirectional imaging with partially coherent light
  87. Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
  88. Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution
  89. Predicting Long-Term Allograft Survival in Liver Transplant Recipients
  90. A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities
  91. SuperEncoder: Towards Universal Neural Approximate Quantum State Preparation
  92. Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan
  93. Generalized Encouragement-Based Instrumental Variables for Counterfactual Regression
  94. Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning
  95. SAM-FNet: SAM-Guided Fusion Network for Laryngo-Pharyngeal Tumor Detection
  96. Modeling Multi-Step Scientific Processes with Graph Transformer Networks
  97. EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
  98. Interface Laplace Learning: Learnable Interface Term Helps Semi-Supervised Learning
  99. Style-Preserving Lip Sync via Audio-Aware Style Reference
  100. How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model
All 108
  1. RSL-BA: Rolling Shutter Line Bundle Adjustment
  2. Efficient Quantum Gradient and Higher-order Derivative Estimation via Generalized Hadamard Test
  3. LaiDA: Linguistics-aware In-context Learning with Data Augmentation for Metaphor Components Identification
  4. Mesh deformation-based single-view 3D reconstruction of thin eyeglasses frames with differentiable rendering
  5. PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
  6. fastkqr: A Fast Algorithm for Kernel Quantile Regression
  7. SAMSA: Efficient Transformer for Many Data Modalities
  8. Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions