Daily Papers of 2024-08-27

  1. SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher 57 upvotes, #1 of 2024-08-27
  2. SWE-bench-java: A GitHub Issue Resolving Benchmark for Java 40 upvotes, #2 of 2024-08-27
  3. Foundation Models for Music: A Survey 35 upvotes, #3 of 2024-08-27
  4. K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences 33 upvotes, #4 of 2024-08-27
  5. LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs 23 upvotes, #5 of 2024-08-27
  6. Learning to Move Like Professional Counter-Strike Players 20 upvotes, #6 of 2024-08-27
  7. Training-free Long Video Generation with Chain of Diffusion Model Experts 19 upvotes, #7 of 2024-08-27
  8. Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler 18 upvotes, #8 of 2024-08-27
  9. LLaVaOLMoBitnet1B: Ternary LLM goes Multimodal! 17 upvotes, #9 of 2024-08-27
  10. NanoFlow: Towards Optimal Large Language Model Serving Throughput 14 upvotes, #10 of 2024-08-27
  11. TVG: A Training-free Transition Video Generation Method with Diffusion Models 12 upvotes, #11 of 2024-08-27
  12. MobileQuant: Mobile-friendly Quantization for On-device Language Models 11 upvotes, #12 of 2024-08-27
  13. Efficient Detection of Toxic Prompts in Large Language Models 10 upvotes, #13 of 2024-08-27
  14. MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement 7 upvotes, #14 of 2024-08-27

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.