Daily Papers of 2024-08-16

  1. DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search 48 upvotes, #1 of 2024-08-16
  2. I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm 30 upvotes, #2 of 2024-08-16
  3. Towards flexible perception with visual memory 19 upvotes, #3 of 2024-08-16
  4. Heavy Labels Out! Dataset Distillation with Label Space Lightening 17 upvotes, #4 of 2024-08-16
  5. Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability 14 upvotes, #5 of 2024-08-16
  6. FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance 13 upvotes, #6 of 2024-08-16
  7. BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts 10 upvotes, #7 of 2024-08-16
  8. FuseChat: Knowledge Fusion of Chat Models 9 upvotes, #8 of 2024-08-16
  9. The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community 9 upvotes, #8 of 2024-08-16
  10. Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization 8 upvotes, #10 of 2024-08-16
  11. MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing 6 upvotes, #11 of 2024-08-16
  12. Can Large Language Models Understand Symbolic Graphics Programs? 6 upvotes, #11 of 2024-08-16

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.