Weihao Liu
Email: wliu681@uic.edu  /  liuweihao2022@outlook.com

Email  /  Google Scholar  /  Semantic Scholar  /  Github  /  Codeforces

Hello, World!

I am Weihao Liu (刘伟浩), a first-year Ph.D. student in Computer Science at University of Illinois Chicago, advised by Dr. Lu Cheng. Prior to this, I gained research experience as a research intern at Microsoft and Institute of Automation, CAS. I obtained my bachelor's degree in Computer Science from University of Science and Technology Beijing (USTB).

My research interest lies broadly in natural language processing (NLP) and large language models (LLMs). Currently, I am particularly interested in:

  • LLM Reasoning: Improving the reasoning capabilities of LLMs in a compute-efficient and robust manner, with an increasing interest on latent reasoning now.
  • Evaluating Human-like Traits in LLMs: Developing rigorous evaluation frameworks for assessing human-like cognitive abilities in LLMs, particularly creativity and other higher-order traits.

Previously, I have also worked on long-context modeling, RAG, and cross-modal / cross-lingual reasoning.

  News
  • [2026.02] We propose a new tuning method for latent reasoning! [Arxiv].NEW
  • [2025.08] Start my Ph.D. journey at UIC!
  • [2025.02] Our work MuDAF is available on arXiv!
  • [2024.12] One paper accepted by COLING 2025 as an ORAL presentation!
  Experience
Microsoft Research Intern, Microsoft, Beijing, China
2023.10 — 2025.04
Mentored by Wenbiao Ding and Dr. Ming Gong. Worked on long-context modeling and cross-lingual trustworthiness of LLMs.
CASIA Research Assistant, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2023.03 — 2023.08
Advised by Prof. Kang Liu. Focused on multimodal question answering.
  Publications
Selected Languages are All You Need for Cross-lingual Truthfulness Transfer
Weihao Liu, Ning Wu, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang
COLING , 2025, Oral
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, Tianyu Du
ACL, 2024
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
Yanming Liu, Xinyue Peng, Tianyu Du, Jianwei Yin, Weihao Liu, Xuhong Zhang
ACL, 2024
Answer-based entity extraction and alignment for visual text question answering
Jun Yu, Mohan Jing, Weihao Liu, Tongxu Luo, Bingyuan Zhang, Keda Lu, Fangyu Lei, Jianqing Sun, Jiaen Liang
MM, 2023
  Selected Preprints
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Weihao Liu, Dehai Min, Lu Cheng
arXiv preprint , 2026
[pdf] [code]
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
Weihao Liu, Ning Wu, Shiping Yang, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang
arXiv preprint , 2025
MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images
Weihao Liu, Fangyu Lei, Tongxu Luo, Jiahe Lei, Shizhu He, Jun Zhao, Kang Liu
arXiv preprint, 2023
  Awards & Honors
  • Silver Medal in ACM-ICPC Asia-East Continent Final, 2022
  • National Scholarship, China, 2021
  • Bronze Medal in National Olympiad in Informatics (NOI), China, 2019
  Teaching
  • Teaching Assistant: CS 109 - Matlab, UIC, Spring 2026
  • Teaching Assistant: CS 361 - System Programming, UIC, Fall 2025
  • Teaching Assistant: Programming Fundamentals A, USTB, 2021 & 2022
  Professional Service
  • Conference Reviewer: ACL 2025, ACL 2026, ICML 2026
  Friends from Afar