mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 28 Jul 2024

99 papers

  1. Faculty Perspectives on the Potential of RAG in Computer Science Higher EducationRetrieval-augmented generation → RAG pipeline design and evaluation
  2. Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language ModelsMixture-of-experts → MoE large language models +1
  3. Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-JudgeSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  4. Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction CycleDiffusion models → 3D, point cloud and scene generation
  5. Temporal Feature Matters: A Framework for Diffusion Model QuantizationDiffusion models → Diffusion foundations and sampling
  6. Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge DistillationKnowledge distillation → Distillation for medical imaging
  7. The Interpretability of Codebooks in Model-Based Reinforcement Learning is LimitedDeep reinforcement learning methods → Interpretable and logic-guided RL
  8. White Matter Geometry-Guided Score-Based Diffusion Model for Tissue Microstructure Imputation in Tractography ImagingDiffusion models → Medical imaging and segmentation
  9. FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  10. Conversational AI Multi-Agent Interoperability, Universal Open APIs for Agentic Natural Language Multimodal CommunicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Identity-Driven Hierarchical Role-Playing AgentsLLM agents and tool use → Social simulation and multi-agent debate
  12. AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question AnsweringEfficient LLM inference and serving → Prompt and context compression
  13. LLAVADI: What Matters For Multimodal Large Language Models DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  14. Logic Distillation: Learning from Code Function by Function for Decision-making TasksLLM reasoning → Prompting and chain-of-thought reasoning
  15. NAVIX: Scaling MiniGrid Environments with JAXDeep reinforcement learning methods → RL training of language and agent models
  16. Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis TreatmentDeep reinforcement learning methods → RL for clinical treatment and surgery
  17. ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  18. The Emerged Security and Privacy of LLM Agent: A Survey with Case StudiesLLM agents and tool use → Agent threats, guardrails and governance
  19. Analysis of sensors for movement analysis
  20. Optimizing Emotion Recognition with Wearable Sensor Data: Unveiling Patterns in Body Movements and Heart Rate through Random Forest Hyperparameter Tuning
  21. GNN-Based Joint Channel and Power Allocation in Heterogeneous Wireless Networks
  22. MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili
  23. Towards a Universal Method for Meaningful Signal Detection
  24. Occam's Razor and Bender and Koller's Octopus
  25. High-Dimensional Fault Tolerance Testing of Highly Automated Vehicles Based on Low-Rank Models
  26. Exploring Genre and Success Classification through Song Lyrics using DistilBERT: A Fun NLP Venture
  27. ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks
  28. A Bayesian Flow Network Framework for Chemistry Tasks
  29. Look Hear: Gaze Prediction for Speech-directed Human Attention
  30. You shall know a piece by the company it keeps. Chess plays as a data for word2vec models
  31. Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture
  32. Is Generative AI an Existential Threat to Human Creatives? Insights from Financial Economics
  33. SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
  34. Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
  35. Are LLMs Good Annotators for Discourse-level Event Relation Extraction?
  36. Sharp Bounds for Poly-GNNs and the Effect of Graph Noise
  37. Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models
  38. Neural stochastic Volterra equations: learning path-dependent dynamics
  39. Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection
  40. Improving Domain Adaptation Through Class Aware Frequency Transformation
  41. MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
  42. UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation
  43. Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis
  44. Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family
  45. Impact of Decoding Methods on Human Alignment of Conversational LLMs
  46. VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary
  47. Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
  48. Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation
  49. Solving Short-Term Relocalization Problems In Monocular Keyframe Visual SLAM Using Spatial And Semantic Data
  50. Evaluating LLMs for Text-to-SQL Generation With Complex SQL Workload
  51. Detached and Interactive Multimodal Learning
  52. Large-scale cervical precancerous screening via AI-assisted cytology whole slide image analysis
  53. EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024
  54. WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting
  55. Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph
  56. Official-NV: An LLM-Generated News Video Dataset for Multimodal Fake News Detection
  57. Heads Up eXperience (HUX): Always-On AI Companion for Human Computer Environment Interaction
  58. Multi-modal Crowd Counting via Modal Emulation
  59. What can we learn about Reionization astrophysical parameters using Gaussian Process Regression?
  60. Multi-task Neural Networks for Pain Intensity Estimation using Electrocardiogram and Demographic Factors
  61. Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
  62. Combined CNN and ViT features off-the-shelf: Another astounding baseline for recognition
  63. On the Evaluation Consistency of Attribution-based Explanations
  64. Interpretable Triplet Importance for Personalized Ranking
  65. MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability
  66. Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights
  67. Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
  68. Piecewise deterministic generative models
  69. Nudging Consent and the New Opt Out System to the Processing of Health Data in England
  70. Leave-One-Out Analysis for Nonconvex Robust Matrix Completion with General Thresholding Functions
  71. Business and Regulatory Responses to Artificial Intelligence: Dynamic Regulation, Innovation Ecosystems and the Strategic Management of Disruptive Technology
  72. X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images
  73. ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding
  74. FINER++: Building a Family of Variable-periodic Functions for Activating Implicit Neural Representation
  75. Progressive Domain Adaptation for Thermal Infrared Object Tracking
  76. FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning
  77. Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction with Blockchain
  78. Causal Discovery in Linear Models with Unobserved Variables and Measurement Error
  79. A Generic Review of Integrating Artificial Intelligence in Cognitive Behavioral Therapy
  80. Improved physics-informed neural network in mitigating gradient related failures
  81. UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks
  82. Start from Video-Music Retrieval: An Inter-Intra Modal Loss for Cross Modal Retrieval
  83. Appformer: A Novel Framework for Mobile App Usage Prediction Leveraging Progressive Multi-Modal Data Fusion and Feature Extraction
  84. Near-Isotropic Sub-AAngstrom 3D Resolution Phase Contrast Imaging Achieved by End-to-End Ptychographic Electron Tomography
  85. NVC-1B: A Large Neural Video Coding Model
  86. Towards Secure and Private AI: A Framework for Decentralized Inference
  87. Word Segmentation for Asian Languages: Chinese, Korean, and Japanese
  88. IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
  89. Domain Adaptive Lung Nodule Detection in X-ray Image
  90. Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
  91. Integrating Cognitive AI with Generative Models for Enhanced Question Answering in Skill-based Learning
  92. FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
  93. Multi-modal Imaging Genomics Transformer: Attentive Integration of Imaging with Genomic Biomarkers for Schizophrenia Classification
  94. Uncertainty Quantification of Data Shapley via Statistical Inference
  95. Deep State-Space Generative Model For Correlated Time-to-Event Predictions
  96. Enhancing Black-Scholes Delta Hedging via Deep Learning
  97. Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction
  98. Spring-block theory of feature learning in deep neural networks
  99. Design and Optimization of Big Data and Machine Learning-Based Risk Monitoring System in Financial Markets