Yif Yang

Yif Yang on Hugging Face Daily Papers: 17 papers, 8 in the top 3 of their day, 920 upvotes.

  1. RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources 141 upvotes, #2 of 2026-07-20
  2. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation 39 upvotes, #4 of 2026-07-10
  3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces 101 upvotes, #3 of 2026-06-12
  4. Latent Spatial Memory for Video World Models 66 upvotes, #4 of 2026-06-09
  5. From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills 29 upvotes, #9 of 2026-05-25
  6. SkillOpt: Executive Strategy for Self-Evolving Agent Skills 212 upvotes, #1 of 2026-05-25
  7. Covering Human Action Space for Computer Use: Data Synthesis and Benchmark 14 upvotes, #25 of 2026-05-13
  8. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 34 upvotes, #2 of 2026-04-28
  9. MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation 6 upvotes, #20 of 2026-04-17
  10. AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation 3 upvotes, #26 of 2026-04-13
  11. BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation 11 upvotes, #23 of 2026-04-01
  12. Phi-Ground Tech Report: Advancing Perception in GUI Grounding 40 upvotes, #2 of 2025-08-01
  13. ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL 10 upvotes, #21 of 2025-06-02
  14. Region-Adaptive Sampling for Diffusion Transformers 52 upvotes, #3 of 2025-02-17
  15. LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation 33 upvotes, #1 of 2024-11-11
  16. DreamDistribution: Prompt Distribution Learning for Text-to-Image Diffusion Models 12 upvotes, #8 of 2023-12-26
  17. ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation 15 upvotes, #2 of 2023-08-03

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.