Daily Papers of 2024-03-21

  1. Mora: Enabling Generalist Video Generation via A Multi-Agent Framework 64 upvotes, #1 of 2024-03-21
  2. LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models 47 upvotes, #2 of 2024-03-21
  3. Evolutionary Optimization of Model Merging Recipes 41 upvotes, #3 of 2024-03-21
  4. SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model 30 upvotes, #4 of 2024-03-21
  5. When Do We Not Need Larger Vision Models? 23 upvotes, #5 of 2024-03-21
  6. IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models 20 upvotes, #6 of 2024-03-21
  7. RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS 17 upvotes, #7 of 2024-03-21
  8. HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models 16 upvotes, #8 of 2024-03-21
  9. RewardBench: Evaluating Reward Models for Language Modeling 14 upvotes, #9 of 2024-03-21
  10. ZigMa: Zigzag Mamba Diffusion Model 14 upvotes, #9 of 2024-03-21
  11. DepthFM: Fast Monocular Depth Estimation with Flow Matching 13 upvotes, #11 of 2024-03-21
  12. Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos 11 upvotes, #12 of 2024-03-21
  13. Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation 10 upvotes, #13 of 2024-03-21
  14. Reverse Training to Nurse the Reversal Curse 10 upvotes, #13 of 2024-03-21
  15. Towards 3D Molecule-Text Interpretation in Language Models 9 upvotes, #15 of 2024-03-21
  16. VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis 9 upvotes, #15 of 2024-03-21
  17. Compress3D: a Compressed Latent Space for 3D Generation from a Single Image 8 upvotes, #17 of 2024-03-21
  18. Evaluating Frontier Models for Dangerous Capabilities 7 upvotes, #18 of 2024-03-21

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.