Daily Papers of 2024-02-22

  1. LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens 116 upvotes, #1 of 2024-02-22
  2. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information 49 upvotes, #2 of 2024-02-22
  3. Aria Everyday Activities Dataset 31 upvotes, #3 of 2024-02-22
  4. SDXL-Lightning: Progressive Adversarial Diffusion Distillation 27 upvotes, #4 of 2024-02-22
  5. User-LLM: Efficient LLM Contextualization with User Embeddings 22 upvotes, #5 of 2024-02-22
  6. In deep reinforcement learning, a pruned network is a good network 19 upvotes, #6 of 2024-02-22
  7. Coercing LLMs to do and reveal (almost) anything 13 upvotes, #7 of 2024-02-22
  8. ToDo: Token Downsampling for Efficient Generation of High-Resolution Images 10 upvotes, #8 of 2024-02-22
  9. Music Style Transfer with Time-Varying Inversion of Diffusion Models 10 upvotes, #8 of 2024-02-22
  10. BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models 9 upvotes, #10 of 2024-02-22
  11. Ouroboros: Speculative Decoding with Large Model Enhanced Drafting 7 upvotes, #11 of 2024-02-22
  12. D-Flow: Differentiating through Flows for Controlled Generation 7 upvotes, #11 of 2024-02-22

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.