Daily Papers of 2024-02-28

  1. The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits 630 upvotes, #1 of 2024-02-28
  2. EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions 193 upvotes, #2 of 2024-02-28
  3. Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models 87 upvotes, #3 of 2024-02-28
  4. When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method 26 upvotes, #4 of 2024-02-28
  5. OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web 25 upvotes, #5 of 2024-02-28
  6. DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Model 23 upvotes, #6 of 2024-02-28
  7. Training-Free Long-Context Scaling of Large Language Models 23 upvotes, #6 of 2024-02-28
  8. Video as the New Language for Real-World Decision Making 21 upvotes, #8 of 2024-02-28
  9. Evaluating Very Long-Term Conversational Memory of LLM Agents 20 upvotes, #9 of 2024-02-28
  10. Towards Optimal Learning of Language Models 18 upvotes, #10 of 2024-02-28
  11. Sora Generates Videos with Stunning Geometrical Consistency 16 upvotes, #11 of 2024-02-28
  12. Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners 15 upvotes, #12 of 2024-02-28
  13. Disentangled 3D Scene Generation with Layout Learning 11 upvotes, #13 of 2024-02-28
  14. Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation 10 upvotes, #14 of 2024-02-28
  15. VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction 10 upvotes, #14 of 2024-02-28

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.