Daily Papers of 2024-02-06

  1. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 150 upvotes, #1 of 2024-02-06
  2. Training-Free Consistent Text-to-Image Generation 67 upvotes, #2 of 2024-02-06
  3. OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models 28 upvotes, #3 of 2024-02-06
  4. BlackMamba: Mixture of Experts for State-Space Models 25 upvotes, #4 of 2024-02-06
  5. Rethinking Interpretability in the Era of Large Language Models 23 upvotes, #5 of 2024-02-06
  6. LiPO: Listwise Preference Optimization through Learning-to-Rank 20 upvotes, #6 of 2024-02-06
  7. Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion 20 upvotes, #6 of 2024-02-06
  8. InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions 19 upvotes, #8 of 2024-02-06
  9. Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities 17 upvotes, #9 of 2024-02-06
  10. Shortened LLaMA: A Simple Depth Pruning for Large Language Models 17 upvotes, #9 of 2024-02-06
  11. Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization 16 upvotes, #11 of 2024-02-06
  12. V-IRL: Grounding Virtual Intelligence in Real Life 16 upvotes, #11 of 2024-02-06
  13. Code Representation Learning At Scale 13 upvotes, #13 of 2024-02-06
  14. Rethinking Optimization and Architecture for Tiny Language Models 13 upvotes, #13 of 2024-02-06
  15. DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing 8 upvotes, #15 of 2024-02-06

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.