Haozhe Wang

Haozhe Wang on Hugging Face Daily Papers: 17 papers, 6 in the top 3 of their day, 1,050 upvotes.

  1. Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation 76 upvotes, #5 of 2026-07-28
  2. Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation 86 upvotes, #2 of 2026-07-15
  3. Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields 21 upvotes, #15 of 2026-06-10
  4. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time 100 upvotes, #2 of 2026-04-16
  5. LongCat-Next: Lexicalizing Modalities as Discrete Tokens 137 upvotes, #3 of 2026-04-01
  6. Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining 8 upvotes, #21 of 2026-03-13
  7. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience 89 upvotes, #1 of 2026-01-23
  8. A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports 18 upvotes, #17 of 2025-10-03
  9. VideoScore2: Think before You Score in Generative Video Evaluation 22 upvotes, #18 of 2025-09-30
  10. Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning 26 upvotes, #8 of 2025-09-10
  11. Reverse-Engineered Reasoning for Open-Ended Generation 142 upvotes, #1 of 2025-09-09
  12. VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use 64 upvotes, #5 of 2025-09-03
  13. Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL 19 upvotes, #22 of 2025-05-28
  14. StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs 18 upvotes, #19 of 2025-05-27
  15. Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning 48 upvotes, #4 of 2025-05-23
  16. VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning 42 upvotes, #4 of 2025-04-15
  17. ACECODER: Acing Coder RL via Automated Test-Case Synthesis 23 upvotes, #3 of 2025-02-05

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.