Skip to content
View yafuly's full-sized avatar
61 followers · 32 following

Achievements

Achievement: QuickdrawAchievement: Starstruckx2

Achievements

Achievement: QuickdrawAchievement: Starstruckx2

Block or report yafuly

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yafuly/README.md

Research Portfolio

I am Yafu Li, a postdoctoral researcher at the Chinese University of Hong Kong under the supervision of Prof. Yu Cheng. My research focuses on reasoning, trustworthy AI, and multilinguality.

✨ ✨ ✨
We are looking for interns and joint PhD candidates (with THU, PKU, SJTU, FDU, etc.) to work on cutting-edge research in large language models. If you are interested, please feel free to contact me at yafuly@gmail.com.

Recent Focus 🚀

  • Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration (SpecBench) 📄 Paper | 💻 Code

  • Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models (MathIF) 📄 Paper | 💻 Code

  • Learning to Reason under Off-Policy Guidance (LUFFY) 📄 Paper | 💻 Code

  • A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond 📄 Paper | 💻 Code

  • Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback (TPO) 📄 Paper | 💻 Code

Pinned Loading

  1. ElliottYan/LUFFY ElliottYan/LUFFY Public

    Official Repository of "Learning to Reason under Off-Policy Guidance"

    Python 402 51

  2. TPO TPO Public

    Test-time preferenece optimization (ICML 2025).

    Jupyter Notebook 177 11

  3. zzzhr97/SpecBench zzzhr97/SpecBench Public

    Python 22 2

  4. TingchenFu/MathIF TingchenFu/MathIF Public

    instruction-following benchmark for large reasoning models

    Python 44 4

  5. XiaoYee/Awesome_Efficient_LRM_Reasoning XiaoYee/Awesome_Efficient_LRM_Reasoning Public

    😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond

    332 12