Westlake University

Appearance

Publications

Selected Papers & Research Outputs

The lab publishes across large language models, multimodal learning, dialogue systems, AI agents, mental health support, and computer vision.

40 Papers2011-2025LLMs · Multimodal · Vision · Agents

  1. Zhanchao Zhou, Tianyi Wu, Zhiyun Jiang, Fares Obeid, Zhenzhong Lan*. Value Residual Learning For Alleviating Attention Concentration In Transformers. ACL 2025. (This paper tackles the issue of standard Transformers losing token-level information in deeper layers. The proposed solutions have been used in well-known projects such as NanoGPT, X-Formers, and RWKV-7, and are likely to be integrated in the next Deepseek model.)

  2. Huachuan Qiu, Zhenzhong Lan*. PsyDial: A Large-scale Long-term Conversational Dataset for Mental Health Support. ACL 2025.

  3. Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, Zhenzhong Lan*. Nova: An iterative planning and search approach to enhance novelty and diversity of LLM-generated ideas. ACL findings 2025. (Reported by top-tier domestic AI media, including Machine Intelligence, AI Tech Review, and Sina Finance.)

  4. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu. Openwebvoyager: Building multimodal web agents via iterative real-world exploration, feedback, and optimization. ACL 2025.

  5. Ma Chang, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, etc. AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents. NeurIPS 2025.

  6. Chiyu Song, Zhanchao Zhou, Jianhao Yan, Yuejiao Fei, Zhenzhong Lan, Yue Zhang. Dynamics of Instruction Fine-Tuning for Chinese Large Language Models. COLING 2025.

  7. Kevin FA Darras, Marcel Balle, Wenxiu Xu, Yang Yan, Vincent G Zakka, Manuel Toledo-Hernandez, Dong Sheng, Wei Lin, Boyu Zhang, Zhenzhong Lan, Li Fupeng, Thomas C Wanger. Eyes on nature: Embedded vision cameras for terrestrial biodiversity monitoring. MEE 2024.

  8. Anqi Li, Yu Lu, Nirui Song, Shuai Zhang, Lizhi Ma, Zhenzhong Lan*. Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs. EMNLP findings 2024.

  9. Huachuan Qiu, Lizhi Ma, Zhenzhong Lan*. PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counseling. EMNLP 2024.

  10. Jia Yu, Zhiwei Huang, Lichao Zhang, Yu Lu, Yuming Yan, Zhenyang Xiao, Zhenzhong Lan*. Benchmark for Detecting Child Pornography in Open Domain Dialogues Using Large Language Models. IJCNN 2024.

  11. Zijie Chen, Lichao Zhang, Fangsheng Weng, Lili Pan, Zhenzhong Lan*. Tailored visions: Enhancing text-to-image generation with personalized prompt rewriting. CVPR 2024.

  12. Huachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li, Zhenzhong Lan*. SMILE: Single-turn to Multiturn Inclusive Language Expansion via ChatGPT for Mental Health Support. EMNLP findings 2024. (Github 500+ stars)

  13. Qiyue Kang, Pengfei Fang, Shuai Zhang, Huachuan Qiu, Zhenzhong Lan*. Deep graph convolutional network for small-molecule retention time prediction. JCA 2023.

  14. Pengfei Fang, Mehrtash Harandi, Zhenzhong Lan, Lars Petersson. Poincare kernels for hyperbolic representations. IJCV 2023.

  15. Pengfei Fang, Yukang Zhang, Zhenzhong Lan*. Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification. MACH VISION APPL 2023.

  16. Anqi Li, Lizhi Ma, Yaling Mei, Hongliang He, Shuai Zhang, Huachuan Qiu, Zhenzhong Lan*. Understanding Client Reactions in Online Mental Health Counseling. ACL 2023.

  17. Huachuan Qiu, Tong Zhao, Anqi Li, Shuai Zhang, Hongliang He, Zhenzhong Lan*. A Benchmark for Understanding Dialogue Safety in Mental Health Support. NLPCC 2023.

  18. Junlei Zhang, Zhenzhong Lan, Junxian He. Contrastive Learning of Sentence Embeddings from Scratch. EMNLP 2023.

  19. Hongliang He, Junlei Zhang, Zhenzhong Lan*, Yue Zhang. Instance smoothed contrastive learning for unsupervised sentence embedding. AAAI 2023.

  20. Yuejiao Fei, Leyang Cui, Sen Yang, Wai Lam, Zhenzhong Lan, Shuming Shi. Enhancing Grammatical Error Correction Systems with Explanations. ACL 2023.

  21. Chiyu Song, Hongliang He, Haofei Yu, Pengfei Fang, Leyang Cui, Zhenzhong Lan*. Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems. ACL findings 2023.

  22. PengFei Fang, Xian Li, Yang Yan, Shuai Zhang, QiYue Kang, XiaoFei Li, Zhenzhong Lan*. Connecting the dots in self-supervised learning: a brief survey for beginners. JCST 2022.

  23. Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, Yunhe Wang. Dynamic resolution network. NeurIPS 2021.

  24. Ye Zheng, Zhang Chen, Dailin Lv, Zhixing Li, Zhenzhong Lan, Shiyu Zhao. Air-to-air visual detection of micro-UAVs: An experimental evaluation of deep learning. IEEE RAS 2021.

  25. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut. ALBERT: A Lite BERT for Self-supervised Learning of Language. ICLR 2020. (10000+ citations)

  26. Liang Xu, Xuanwei Zhang, Lu Li, Hai Hu, Chenjie Cao, Weitang Liu, Junyi Li, Yudong Li, Kai Sun, Yechen Xu, Yiming Cui, Cong Yu, Qianqian Dong, Yin Tian, Dian Yu, Bo Shi, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Zhenzhong Lan*. CLUE: A Chinese Language Understanding Evaluation Benchmark. COLING 2020.

  27. Shazeer, Noam, Zhenzhong Lan, Youlong Cheng, Nan Ding, and Le Hou. ”Talking-heads attention.” US patents 2020.

  28. Yi Zhu,Zhenzhong Lan, Shawn Newsam, Alexander Hauptmann. Hidden two-stream convolutional networks for action recognition. ACCV 2019.

  29. Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang. Strategies for Searching Video Content with Text Queries or Video Examples. ITE TRANS MEDIA TECH 2016.

  30. Zhenzhong Lan. Learn to recognize actions through neural networks. ACM MM 2015. 11. Ming Lin, Zhenzhong Lan, Alexander G. Hauptmann. Density corrected sparse recovery when RIP condition is broken. IJCAI 2015.

  31. Shicheng Xu, Huan Li, Xiaojun Chang, Shoou-I Yu, Xingzhong Du, Xuanchong Li, Lu Jiang, Zexi Mao, Zhenzhong Lan, Susanne Burger, Alexander Hauptmann. Incremental multimodal query construction for video search. ICMR 2015.

  32. Zhenzhong Lan, Ming Lin, Xuanchong Li, Alexander G Hauptmann, Bhiksha Raj. Beyond gaussian pyramid: Multi-skip feature stacking for action recognition. CVPR 2015.

  33. Lu Jiang, Yajie Miao, Yi Yang, Zhenzhong Lan, Alexander G Hauptmann. Viral video style: A closer look at viral videos on YouTube. ICMR 2014.

  34. Lu Jiang, Deyu Meng, Shoou-I Yu, Zhenzhong Lan, Shiguang Shan, Alexander Hauptmann. Self-paced learning with diversity. Advances in NeurIPS 2014.

  35. Zhenzhong Lan, Yi Yang, Nicolas Ballas, Shoou-I Yu, Alexander Haputmann. Resource constrained multimedia event detection. MMM 2014.

  36. Wei Tong, Yi Yang, Lu Jiang, Shoou-I Yu, Zhenzhong Lan, Zhigang Ma, Waito Sze, Ehsan Younessian, Alexander G Hauptmann. E-lamp: integration of innovative ideas for multimedia event detection. MACH VISION APPL 2014.

  37. Zhenzhong Lan, Lu Jiang, Shoou-I Yu, Shourabh Rawat, Yang Cai, Chenqiang Gao, Shicheng Xu, Haoquan Shen, Xuanchong Li, Yipei Wang, Waito Sze, Yan Yan, Zhigang Ma, Wei Tong, Yi Yang, Susanne Burger, Florian Metze, Rita Singh, Bhiksha Raj, Richard Stern, Teruko Mitamura, Eric Nyberg, Alexander Hauptmann. CMU-Informedia at TRECVID 2013 multimedia event detection. TRECVID 2013.

  38. Nicolas Ballas, Yi Yang, Zhenzhong Lan, Bertrand Delezoide, Franc¸oise Preteux, Alexander Hauptmann.Space-time robust representation for action recognition. CVPR 2013.

  39. Zhenzhong Lan, Lei Bao, Shoou-I Yu, Wei Liu, Alexander G Hauptmann. Double fusion for multimedia event detection. MMM 2012.

  40. Minh Hoai, Zhenzhong Lan, Fernando De la Torre.Joint segmentation and classification of human actions in video. CVPR 2011.