Skip to content
View sylvain-wei's full-sized avatar
😎
Hahaha
😎
Hahaha
35 followers · 77 following

Achievements

Achievement: StarstruckAchievement: Pull Shark

Achievements

Achievement: StarstruckAchievement: Pull Shark

Block or report sylvain-wei

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
sylvain-wei/README.md

Hi Bro👋

🧑🏻‍💻 Brief Intro

I am Shaohang Wei, a second-year Ph.D. student at the Institute of Computational Linguistics (计算语言学研究所), School of Computer Science, Peking University.

My research focuses on foundation model alignment and post-training, long-horizon capability generalization in agentic systems, and real-world data synthesis and construction for LLM agents. I am broadly interested in building reliable, generalizable, and self-improving AI agents for real-world environments.

You can also find me on X and 小紅書.

🤩 I am open to collaborations and discussions, and I am actively seeking research intern opportunities!

🤝🏻  Contact Me

If you are interested in any aspect of me, please feel free to reach out to me!

Email: veison1006[at]outlook.com (preferred) or shaohang[at]stu.pku.edu.cn

Homepage: Homepage

Pinned Loading

  1. TIME TIME Public

    [NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario

    Python 31

  2. 24-Game-Reasoning 24-Game-Reasoning Public

    超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

    Python 33 2

  3. Reasoning-Frontiers Reasoning-Frontiers Public

    A collection of key papers exploring reasoning generalization and pushing the boundaries of reasoning capabilities.

    5

  4. Self-training-Paper-List Self-training-Paper-List Public

    Self-training relies on the model's internal features, output layer probability distributions, and other data to construct supervisory signals. It selects essential key data and designs more reason…

    2

  5. NightingaleCen/LeafyLingo NightingaleCen/LeafyLingo Public

    An interactive plant recognition system with multi-model knowledge graph

    Python 1

  6. NightingaleCen/RL-MalmoPlayground NightingaleCen/RL-MalmoPlayground Public

    Python 2