IMG_3636.jpeg

Pronouns: she/her

<aside> <img src="/icons/mail_gray.svg" alt="/icons/mail_gray.svg" width="40px" /> Email

</aside>

<aside> <img src="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/cd361d2a-9856-49d3-bfa3-abc0d900c2fa/25231.png" alt="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/cd361d2a-9856-49d3-bfa3-abc0d900c2fa/25231.png" width="40px" /> Github

</aside>

<aside> <img src="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/f30b1dd3-7384-4ae2-b912-11f36f7e174f/Picture2.png" alt="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/f30b1dd3-7384-4ae2-b912-11f36f7e174f/Picture2.png" width="40px" /> Google Scholar

</aside>

<aside> <img src="/icons/briefcase_gray.svg" alt="/icons/briefcase_gray.svg" width="40px" /> LinkedIn

</aside>

<aside> <img src="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/4a681ff9-9560-425e-a09b-83cefa5ab4e8/twitter-3.png" alt="https://prod-files-secure.s3.us-west-2.amazonaws.com/ccfa533d-be64-4c51-bf9d-ab1a1cc53bfa/4a681ff9-9560-425e-a09b-83cefa5ab4e8/twitter-3.png" width="40px" /> X

</aside>

Medals of my team in a marathon race.

Medals of my team in a marathon race.

👋 Hi there!

I am a second-year third-year PhD student at New York University (Courant Institute). Previously I worked with Prof.Yulia Tsvekov(UW). I obtained my bachelor’s degree from Xi’an Jiaotong Univerity, where I worked with Prof. Minnan Luo.

🌋 Research Interests

My research interest lies in developing training and inference methods of machine learning. I’ve been interested in how LLMs can better assist human in long horizon tasks.

https://lyh6560new.github.io/notion-personal-website-assets/whats-new-scrollable.html

📜 Selected Publications

Please see my Google Scholar for the full list.

(*: equal contribution)


Which Skill to Distill? SGUID:twemoji_squid_512:: Selecting a Compact Skill Bank for Model-Skill Co-Evolution

Yuhan Liu, Xiyao Ma, Zhongkai Sun, Xu Han, Chengyuan Ma, Benjamin Z. Yao, Chenlei Guo

Under review.[paper]

No Single Best Model for Diversity: Learning a Router for Sample Diversity

Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar, Daphne Ippolito, Eunsol Choi

COLM 2026.[paper] [website] [code]

User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal

Yuhan Liu, Michael J.Q. Zhang, Eunsol Choi

EMNLP 2025. [paper] [code]

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration

Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov

EMNLP 2024. [paper]

P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models

Yuhan Liu,* Shangbin Feng*, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov

NAACL 2024. [paper] [code]

Knowledge Crosswords: Geometric Reasoning over Structured Knowledge with Large Language Models

Wenxuan Ding, Shangbin Feng, Yuhan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov

ACL 2024. [paper] [code]

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov

ACL 2023 🏆 Best Paper Award. [paper]   [code]   [Washington Post]  [ MIT Tech Review]   [Montreal AI Ethics Institute]  [ Better Conflict Bulletin]

BotMoE: Twitter Bot Detection with Community-Aware Mixtures of Modal-Specific Experts

Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, Minnan Luo

SIGIR 2023 [paper]  [ code]

TwiBot-22: Towards Graph-Based Twitter Bot Detection

Shangbin Feng, Zhaoxuan Tan, Herun Wan, Ningnan Wang, ..., Qinghua Zheng, ..., Yuhan Liu, ..., Jundong Li, Minnan Luo

NeurIPS 2022, Datasets and Benchmarks Track  [ website]  [ paper]   [code]   [poster]

🏝️ Miscellaneous