Daily Papers of 2024-07-17

  1. NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window? 39 upvotes, #1 of 2024-07-17
  2. Qwen2-Audio Technical Report 34 upvotes, #2 of 2024-07-17
  3. Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes 23 upvotes, #3 of 2024-07-17
  4. Scaling Diffusion Transformers to 16 Billion Parameters 21 upvotes, #4 of 2024-07-17
  5. Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning 12 upvotes, #5 of 2024-07-17
  6. DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation 11 upvotes, #6 of 2024-07-17
  7. VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models 11 upvotes, #6 of 2024-07-17
  8. FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models 8 upvotes, #8 of 2024-07-17
  9. YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus 7 upvotes, #9 of 2024-07-17
  10. Animate3D: Animating Any 3D Model with Multi-view Video Diffusion 7 upvotes, #9 of 2024-07-17
  11. OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces 7 upvotes, #9 of 2024-07-17
  12. Efficient Training with Denoised Neural Weights 7 upvotes, #9 of 2024-07-17
  13. From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients 6 upvotes, #13 of 2024-07-17
  14. EfficientQAT: Efficient Quantization-Aware Training for Large Language Models 5 upvotes, #14 of 2024-07-17
  15. Grasping Diverse Objects with Simulated Humanoids 5 upvotes, #14 of 2024-07-17
  16. Data-Juicer Sandbox: A Comprehensive Suite for Multimodal Data-Model Co-development 4 upvotes, #16 of 2024-07-17
  17. Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors 4 upvotes, #16 of 2024-07-17
  18. Click-Gaussian: Interactive Segmentation to Any 3D Gaussians 3 upvotes, #18 of 2024-07-17
  19. Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models 1 upvotes, #19 of 2024-07-17

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.