linbin

linbin on Hugging Face Daily Papers: 14 papers, 4 in the top 3 of their day, 451 upvotes.

  1. Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback 18 upvotes, #13 of 2025-10-21
  2. GIR-Bench: Versatile Benchmark for Generating Images with Reasoning 17 upvotes, #20 of 2025-10-14
  3. Can Understanding and Generation Truly Benefit Together -- or Just Coexist? 32 upvotes, #9 of 2025-09-12
  4. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation 58 upvotes, #2 of 2025-06-04
  5. ImgEdit: A Unified Image Editing Dataset and Benchmark 17 upvotes, #25 of 2025-05-28
  6. OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation 52 upvotes, #8 of 2025-05-28
  7. WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation 4 upvotes, #29 of 2025-03-11
  8. WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model 10 upvotes, #15 of 2024-12-03
  9. Open-Sora Plan: Open-Source Large Video Generation Model 30 upvotes, #3 of 2024-12-03
  10. OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model 10 upvotes, #12 of 2024-09-04
  11. Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle 20 upvotes, #13 of 2024-07-30
  12. ShareGPT4Video: Improving Video Understanding and Generation with Better Captions 61 upvotes, #1 of 2024-06-07
  13. MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators 19 upvotes, #7 of 2024-04-09
  14. MoE-LLaVA: Mixture of Experts for Large Vision-Language Models 54 upvotes, #2 of 2024-01-30

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.