Curriculum Vitae
Download PDF Updated Apr 2026
Education
2024 - 2027 M.S. (Academic) in Computer Science
Advisor: Assoc. Prof. Yunfang Wu
2020 - 2024 B.S. in Computer Science
GPA: 3.72/4.00
Publications
Refereed Publications
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error ACL 2026
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
Aligning Language Models with Real-time Knowledge Editing ACL 2026
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
Think Outside the Policy: In-Context Steered Policy Optimization ACL 2026 Findings
Findings of the Association for Computational Linguistics: ACL 2026
Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions EMNLP 2025 Findings
Findings of the Association for Computational Linguistics: EMNLP 2025
SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation EMNLP 2024
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction NAACL 2024
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Are Pre-trained Language Models Useful for Model Ensemble in Chinese Grammatical Error Correction? ACL 2023
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Preprints
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model arXiv 2026
arXiv preprint arXiv:2604.17739
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation arXiv 2026
arXiv preprint arXiv:2605.28396
RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data arXiv 2026
arXiv preprint arXiv:2605.26971
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning arXiv 2026
arXiv preprint arXiv:2601.08310
Lost in the Passage: Passage-level In-context Learning Does Not Necessarily Need a "Passage" arXiv 2025
arXiv preprint arXiv:2502.10634
arXiv preprint arXiv:2307.03972
* Equal Contribution.
Research Experience
2026 - Present University of Illinois Urbana-Champaign
Agent Memory
2025 - 2026 Tencent & Peking University
Agentic Reinforcement Learning · Reasoning-oriented Reinforcement Fine-tuning
2022 - 2025 Peking University
Knowledge Editing · Prompting and In-context Learning · Grammatical Error Correction
Honors and Awards
2024 Outstanding Graduate
2023 Exceptional Award for Academic Innovation
2023 First prize
2022 Second place
Teaching
Spring 2025 Teaching Assistant, Introduction to Computing (C)
Instructor: Prof. Zhifang Sui & Assoc. Prof. Yunfang Wu
Standardized Tests
TOEFL iBT
111
R: 30 | L: 28 | S: 23 | W: 30
GRE General Test
336
V: 166 | Q: 170 | AWA: 3.5
