Daily Papers of 2024-12-04

  1. VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation 55 upvotes, #1 of 2024-12-04
  2. Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability 47 upvotes, #2 of 2024-12-04
  3. MALT: Improving Reasoning with Multi-Agent LLM Training 36 upvotes, #3 of 2024-12-04
  4. Free Process Rewards without Process Labels 26 upvotes, #4 of 2024-12-04
  5. AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning 25 upvotes, #5 of 2024-12-04
  6. AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information? 21 upvotes, #6 of 2024-12-04
  7. Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS 18 upvotes, #7 of 2024-12-04
  8. OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation 18 upvotes, #7 of 2024-12-04
  9. OmniCreator: Self-Supervised Unified Generation with Universal Editing 13 upvotes, #9 of 2024-12-04
  10. Motion Prompting: Controlling Video Generation with Motion Trajectories 12 upvotes, #10 of 2024-12-04
  11. LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences 9 upvotes, #11 of 2024-12-04
  12. Scaling Image Tokenizers with Grouped Spherical Quantization 9 upvotes, #11 of 2024-12-04
  13. MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation 6 upvotes, #13 of 2024-12-04
  14. A dynamic parallel method for performance optimization on hybrid CPUs 5 upvotes, #14 of 2024-12-04
  15. Generating a Low-code Complete Workflow via Task Decomposition and RAG 4 upvotes, #15 of 2024-12-04
  16. VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval 4 upvotes, #15 of 2024-12-04

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.