University of Science and Technology of China & Shanghai AI Laboratory
Ph.D. student in Artificial Intelligence. Advisors: Dahua Lin and Feng Zhao.
Joint Ph.D. Student · USTC × Shanghai AI Laboratory
I am currently a joint Ph.D. student at the University of Science and Technology of China (USTC) and Shanghai AI Laboratory. My M.S. advisor is Academician Feng Wu, and my Ph.D. advisors are Prof. Dahua Lin and Prof. Feng Zhao. I received my Bachelor's degree in 2024 from the School of the Gifted Young (少年班) at USTC. My current research focuses on LLM post-training and Agentic AI. My research interests also include Embodied AI, especially World Models and Vision-Language-Action (VLA) models. A recurring theme across my work is improving the efficiency of large-scale AI systems. Previously, I worked on AI4EDA, mainly reinforcement learning for chip placement optimization.
- Expected Ph.D.
- June 2029
- Focus
- LLM Post-training · Agentic RL
- Affiliation
- USTC & Shanghai AI Lab
Updates
News
-
Released MMPO and Evolve as a Team on long-horizon agents and multi-agent self-evolution.
-
ThoughtFold, ArborKV, and DeepContour were accepted to ICML 2026.
-
ACCO was accepted to DATE 2026 (Design, Automation and Test in Europe), a leading international conference in electronic design automation.
-
Released VLA-Pruner; together with Evo-1, this line explores lightweight and efficient VLA inference. Evo-1 was accepted to CVPR 2026.
-
ChipBench was accepted to NeurIPS 2025 Datasets and Benchmarks Track.
-
LaMPlace was accepted as an ICLR 2025 Oral paper.
-
EfficientPlace was accepted to ICML 2024.
Education
Education
University of Science and Technology of China · School of Information Science and Technology
M.S. student in Artificial Intelligence. Advisor: Feng Wu.
University of Science and Technology of China · School of the Gifted Young
B.S. in Physics. GPA: 90.11/100.
Publications
Selected Publications
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
Ziyan Liu*, Xueda Shen*, Yuzhe Gu*, ..., Dahua Lin, Wenwei Zhang†, Kai Chen†
ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
Yeqiu Chen*, Ziyan Liu*, Zhenxin Huang, Runquan Gui, Hong Wang, Lei Liu†
Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference (VLA-Pruner)
Ziyan Liu*, Yeqiu Chen*, Hongyi Cai, Tao Lin, Shuo Yang, Zheng Liu, Bo Zhao
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Ziyan Liu*, Zhezheng Hao*, Yeqiu Chen*, Hong Wang, ..., Wei Xia†, Feng Liu
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
Zhezheng Hao, Tianfu Wang, Huanshuo Dong, Ziyan Liu, Hong Wang, Xiankun Lin, Qiang Lin, Can Wang, Hande Dong, Jiawei Chen
PPA-driven Placement via Adaptive Cluster Constraints Optimization
Ziyan Liu, Siyuan Xu, Jie Wang†, Zijie Geng, Yeqiu Chen, Mingxuan Yuan, Jianye Hao, Feng Wu
Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized Eigensolver
Yeqiu Chen*, Ziyan Liu*, Hong Wang†, Lei Liu
LaMPlace: Learning to Optimize Cross-stage Metrics in Macro Placement
Zijie Geng, Jie Wang†, Ziyan Liu, ..., Jianye Hao, Feng Wu
Benchmarking End-to-end Performance of AI-based Chip Placement Algorithms
Zhihai Wang*, Zijie Geng*, ..., Ziyan Liu, ..., et al.
EfficientPlace: Reinforcement Learning within Tree Search for Fast Macro Placement
Zijie Geng, Jie Wang†, Ziyan Liu, Siyuan Xu, ..., Feng Wu
Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
Tao Lin, Yilei Zhong, ..., Ziyan Liu, ..., et al.
Academic Service
Service
- ICML 2026 Silver Reviewer
- NeurIPS 2026 Reviewer
- ICLR 2026 Workshop RSI Reviewer
- AAAI 2026 Reviewer
Awards
Awards
- First-Class Graduate Academic Scholarship, USTC, 2024
- Second Prize, Research Physics Experiment Competition, USTC, 2023
- Outstanding Student Scholarship, USTC, 2020
- First Prize, Jiangsu Provincial Physics Competition, 2018