Daily Papers of 2024-04-19

  1. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing 44 upvotes, #1 of 2024-04-19
  2. Dynamic Typography: Bringing Words to Life 38 upvotes, #2 of 2024-04-19
  3. Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models 31 upvotes, #3 of 2024-04-19
  4. MeshLRM: Large Reconstruction Model for High-Quality Mesh 21 upvotes, #4 of 2024-04-19
  5. BLINK: Multimodal Large Language Models Can See but Not Perceive 20 upvotes, #5 of 2024-04-19
  6. EdgeFusion: On-Device Text-to-Image Generation 19 upvotes, #6 of 2024-04-19
  7. TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding 14 upvotes, #7 of 2024-04-19
  8. MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation 12 upvotes, #8 of 2024-04-19
  9. Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment 12 upvotes, #8 of 2024-04-19
  10. OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data 11 upvotes, #10 of 2024-04-19
  11. Introducing v0.5 of the AI Safety Benchmark from MLCommons 10 upvotes, #11 of 2024-04-19
  12. AniClipart: Clipart Animation with Text-to-Video Priors 10 upvotes, #11 of 2024-04-19

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.