Daixuan Cheng

Daixuan Cheng on Hugging Face Daily Papers: 12 papers, 5 in the top 3 of their day, 694 upvotes.

  1. ClawGym II: Exploring Black-Box RL on Agent Harness 39 upvotes, #8 of 2026-08-18
  2. ClawGym: A Scalable Framework for Building Effective Claw Agents 54 upvotes, #3 of 2026-04-30
  3. BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? 53 upvotes, #4 of 2026-03-04
  4. SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training 36 upvotes, #10 of 2026-02-04
  5. LLM-in-Sandbox Elicits General Agentic Intelligence 82 upvotes, #2 of 2026-01-23
  6. FlowRL: Matching Reward Distributions for LLM Reasoning 100 upvotes, #2 of 2025-09-19
  7. Reasoning with Exploration: An Entropy Perspective 26 upvotes, #8 of 2025-06-18
  8. An Empirical Study on Eliciting and Improving R1-like Reasoning Models 8 upvotes, #18 of 2025-03-10
  9. How to Synthesize Text Data without Model Collapse? 46 upvotes, #4 of 2024-12-20
  10. On Domain-Specific Post-Training for Multimodal Large Language Models 24 upvotes, #4 of 2024-12-02
  11. Instruction Pre-Training: Language Models are Supervised Multitask Learners 74 upvotes, #2 of 2024-06-21
  12. Adapting Large Language Models via Reading Comprehension 82 upvotes, #2 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.