Zecheng Tang

Zecheng Tang on Hugging Face Daily Papers: 14 papers, 4 in the top 3 of their day, 738 upvotes.

  1. Qwen-Image-2.0 Technical Report 106 upvotes, #1 of 2026-05-12
  2. Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers 33 upvotes, #6 of 2026-01-27
  3. MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models 26 upvotes, #8 of 2026-01-21
  4. Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition 55 upvotes, #2 of 2025-12-18
  5. LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling 14 upvotes, #26 of 2025-10-10
  6. Revisiting Long-context Modeling from Context Denoising Perspective 20 upvotes, #15 of 2025-10-09
  7. Qwen-Image Technical Report 173 upvotes, #1 of 2025-08-05
  8. LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework 9 upvotes, #20 of 2025-07-09
  9. Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model 49 upvotes, #4 of 2025-02-17
  10. LOGO -- Long cOntext aliGnment via efficient preference Optimization 42 upvotes, #3 of 2024-10-25
  11. L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding? 10 upvotes, #15 of 2024-10-04
  12. StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis 20 upvotes, #4 of 2024-01-31
  13. OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch 17 upvotes, #5 of 2023-09-20
  14. LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models 15 upvotes, #7 of 2023-09-19

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.