Junyi Li

Postdoc, City University of Hong Kong

Joined

August 2021

Names

Junyi Li (Preferred)

Emails

****@ruc.edu.cn (Confirmed)

****@nus.edu.sg (Confirmed)

****@gmail.com (Confirmed)

****@cityu.edu.hk (Confirmed)

Personal Links

Career & Education History

Postdoc

City University of Hong Kong (cityu.edu.hk)

2025 – 2026

Postdoc

National University of Singapore (nus.edu.sg)

2024 – 2025

PhD student

Renmin University of China (ruc.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Xin Zhao

2020 – 2024

Expertise

agent

2024 – 2025

large language model

2022 – 2025

text generation

2018 – 2022

Publications

Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design
Yihong Liu, Junyi Li, Xin Zhao, Hongyu Lu, Ji-Rong Wen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents
Zikang Liu, Junyi Li, Xin Zhao, Dawei Gao, Yaliang Li, Ji-Rong Wen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
Yingyi Zhang, Junyi Li, Wenlin Zhang, Pengyue Jia, Xianneng Li, Yichao Wang, Derong Xu, Yi Wen, Huifeng Guo, Yong Liu, Xiangyu Zhao
- ICLR 2026 Poster
- Readers: Everyone
Enhancing Cross-task Transfer of Large Language Models via Fourier Activation Steering
Xinyu Tang, Zhihao Lv, Yu-Liang Zhan, Xiaoxue Cheng, Junyi Li, Xin Zhao, zujie wen, Zhiqiang Zhang, JUN ZHOU
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
Zican Dong, Peiyu Liu, Junyi Li, Zhipeng Chen, Han Peng, Shuo Wang, Xin Zhao
- Submitted to ICLR 2026
- Readers: Everyone
Memory Type Matters: Enhancing Long-Term Memory in Large Language Models with Hybrid Strategies
Yi Wen, Derong Xu, Pengyue Jia, Yichao Wang, Yingyi Zhang, Maolin Wang, Junyi Li, Yue Liu, Huifeng Guo, Yong Liu, Xiangyu Zhao
- Submitted to ICLR 2026
- Readers: Everyone
Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models
Muhammad Reza Qorib, Junyi Li, Hwee Tou Ng
- ACL 2025
- Readers: Everyone
Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
Junyi Li, Hwee Tou Ng
- NeurIPS 2025 poster
- Readers: Everyone
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Xiaoxue Cheng, Junyi Li, Zhenduo Zhang, Xinyu Tang, Xin Zhao, XinYu KONG, Zhiqiang Zhang
- NeurIPS 2025 poster
- Readers: Everyone
LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation
Zican Dong, Junyi Li, Jinhao Jiang, Mingyu Xu, Wayne Xin Zhao, Bingning Wang, Weipeng Chen
- CoRR 2025
- Readers: Everyone

View all 34 publications

Co-Authors

View all 102 co-authors