🔥 News
- 2026.04: 🎉 Four papers (1-first, 3-contribute) are accepted by ACL 2026. Congratulations to ReMe!
- 2025.11: 💪 My very first research work from my master’s studies, AutoHall, has finally been accepted by TASLP after a long and challenging review process🐢!
- 2025.05: 🎉 Two papers (1-first, 1-contribute) are accepted by ACL 2025.
- 2024.12: 🥳 SCANS is accepted by AAAI 2025 as Oral presentation.
- 2024.09: 🎉 Two papers (1-first, 1-contribute) are accepted by EMNLP 2024.
📃 Publications
A full publication list is available on my google scholar page.
(* denotes equal contribution)
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
Zouying Cao, Jiaji Deng, Li Yu, Weikang Zhou, Zhaoyang Liu, Bolin Ding, Hai Zhao.
[ACL-Findings, 2026] ||
|
|
- PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
Zouying Cao, Runze Wang, Yifei Yang, Xinbei Ma, Xiaoyong Zhu, Bo Zheng, Hai Zhao.
[ACL-Findings, 2025] ||
- LESA: Learnable LLM Layer Scaling-Up
Yifei Yang, Zouying Cao, Xinbei Ma, Yao Yao, Libo Qin, Zhi Chen, Hai Zhao.
[ACL-Main, 2025] |
- KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
Yifei Yang, Zouying Cao, Qiguang Chen, Libo Qin, Dongjie Yang, Hai Zhao, Zhi Chen.
[Preprint, 2024] |
- SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
Zouying Cao, Yifei Yang, Hai Zhao.
[AAAI Oral, 2025] |
- Head-wise Shareable Attention for Large Language Models
Zouying Cao, Yifei Yang, Hai Zhao.
[EMNLP-Findings, 2024] |
- LaCo: Large Language Model Pruning via Layer Collapse
Yifei Yang, Zouying Cao, Hai Zhao.
[EMNLP-Findings, 2024] |
- AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models
Zouying Cao, Yifei Yang, Hai Zhao.
[TASLP] |