Dian Yu

Dian Yu on Hugging Face Daily Papers: 12 papers, 4 in the top 3 of their day, 423 upvotes.

1. One Token to Fool LLM-as-a-Judge 29 upvotes, #8 of 2025-07-14
2. DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning 11 upvotes, #17 of 2025-04-16
3. Expanding RL with Verifiable Rewards Across Diverse Domains 17 upvotes, #11 of 2025-04-01
4. Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs 51 upvotes, #2 of 2025-01-31
5. OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas 6 upvotes, #12 of 2025-01-28
6. Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs 27 upvotes, #5 of 2024-12-31
7. LiteSearch: Efficacious Tree Search for LLM 34 upvotes, #4 of 2024-07-02
8. Scaling Synthetic Data Creation with 1,000,000,000 Personas 79 upvotes, #1 of 2024-07-01
9. Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning 6 upvotes, #8 of 2024-07-01
10. Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning 10 upvotes, #16 of 2024-06-19
11. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing 44 upvotes, #1 of 2024-04-19
12. Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models 24 upvotes, #2 of 2023-08-02

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.