Short Bio

I’m a researcher at Ant Group, working on Large Language Models. My research journey began with a B.Eng. from Xi’an Jiaotong-Liverpool University, followed by a PhD from University of Liverpool. I then completed my PostDoc at Zhejiang University under Prof. Jianke Zhu’s guidance. My research background lies in computer vision, language models and transfer learning.

Research Interest

• Large Language Model
• Transfer Learning
• Image Generation
• Medical Image Analysis
• Autonomous Driving Systems

Education

• Ph.D. in Computer Science, 2019.12 - 2023.11, University of Liverpool
• B.Eng. in Computer Science, 2014.9 - 2018.6, Xi’an Jiaotong-Liverpool University

Research Experience

• Postdoctoral Fellow, 2024.1 - 2026.1, Zhejiang University

Work Experience

• Senior Algorithm Engineer, 2024.1 - Present, Ant Group

Review Experience

• ACL, EMNLP, ICLR, NeurIPS, CVPR, ECCV, ICCV, Nature Communication

Honors and Awards

• Top 5 in CrossMoDa Challenge 2021.
• The third prize of 2020-2021 Outstanding Academic Papers of Suzhou Natural Science.
• Full Doctoral Scholarship, University of Liverpool, 2019.

News

• [JAN. 2026] Our conference paper accepted in EACL 2026 as Oral presentation.
• [SEG. 2025] Our paper accepted in IJCV and ACM MM 2025.
• [AUG. 2025] Our conference paper accepted in CIKM 2025.
• [APR. 2025] Our conference paper accepted in ACL 2025.
• [DEC. 2024] Our conference paper accepted in AAAI 2025 as Oral presentation.
• [NOV. 2024] I am happy to attend EMNLP 2024 in person at Miami.
• [SEP. 2024] Our conference paper accepted in EMNLP24.
• [DEC. 2023] Our conference paper accepted in AAAI24.
• [Aug. 2023] Our papers accepted as Oral Presentation in ACM CIKM 2023.
• [May. 2023] Our two journal papers accepted in IEEE TETCI and IJB.
• [Nov. 2022] Our conference paper accepted in AAAI 2023. We propose a novel augmentation for medical image domain generalization. The code released at here.
• [Jul. 2022] Our conference paper accepted in ECCV 2022. We propose a novel hybrid vision-transformer-based GAN for image outpainting. The code released at here.
• [Jun. 2022] Our journal paper accepted in IEEE-JBHI (IF: 7.0).
• [Dec. 2021] Our team PremiLab wins 5th in the Challenge CrossMoDa 2021 (MICCAI workshop).
• [Dec. 2021] Our journal paper accepted in International Journal of Bioprinting (IF: 7.4).
• [Nov. 2021] Our journal paper accepted in Cognitive Computation (IF: 4.9).
• [Dec. 2019] I started my PhD course at UoL PremiLab Lab with full scholarship.
• show more

Publications [Google Scholar]

1. EACL 2026 Oral

   GAST:Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection

   Kai Yao, Zhenghan Song, Kaixin Wu, mingjie zhong, Danzhao Cheng, Zhaorui Tan, Yixin Ji, Penglei Gao

   European Chapter of the Association for Computational Linguistics

   NLP Top


2. IJCV

   Unlock Pose Diversity:Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

   Chaolong Yang*, Kai Yao*, Yuyao Yan, Chenru Jiang, Weiguang Zhao, Jie Sun, Guangliang Cheng, Yifei Zhang, Bin Dong, Kaizhu Huang

   International Journal of Computer Vision

   PDF Code CCF-A, CV Top


3. ACM MM 2025

   KDTalker++:Controllable Talking Portrait Generation with Audio, Text, and Expression Editing

   Chaolong Yang, Yinuo Guo, Kai Yao, Yuyao Yan, Jie Sun, Kaizhu Huang

   ACM Multimedia

   Code CCF-A, CV Top


4. CIKM 2025

   Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning

   Tiandi Ye, Wenyan Liu, Kai Yao, Lichun Li, Shangchao Su, Cen Chen, Xiang Li, Shan Yin, Ming Gao

   ACM International Conference on Information and Knowledge Management

   PDF CCF-B


5. ACL 2025

   GradOT:Training-free Gradient-persevering Offsite-tuning for Large Language Models

   Kai Yao*, Zhaorui Tan*, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Wei Wang, Jianke Zhu

   Annual Meeting of the Association for Computational Linguistics

   PDF CCF-A, NLP Top


6. Under Review

   Test-time Compute:from System-1 Thinking to System-2 Thinking

   Yixin Ji, Juntao Li, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, Min Zhang

   PDF Under Review


7. TNNLS

   SCMix:Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation

   Kai Yao*, Zhaorui Tan*, Zixian Su, Xi Yang, Jie Sun, Kaizhu Huang

   IEEE Transactions on Neural Networks and Learning Systems

   PDF CCF-B


8. AAAI 2025 Oral

   ScaleOT:Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression

   Kai Yao, Zhaorui Tan, Tiandi Ye, Lichun Li, Yuan Zhao, Wenyan Liu, Wei Wang, Jianke Zhu

   Proceedings of Association for the Advancement of Artificial Intelligence

   PDF CCF-A


9. EMNLP 2024

   Layer-wise Importance Matters:Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

   Kai Yao*, Penglei Gao*, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

   Proceedings of Empirical Methods in Natural Language Processing

   PDF Code CCF-B, NLP Top


10. ECCV 2024

    Unleashing the Power of Prompt-driven Nucleus Instance Segmentation

    Zhongyi Shui, Yunlong Zhang, Kai Yao, Chenglu Zhu, Yuxuan Sun, Lin Yang

    European Conference on Computer Vision

    PDF Code CCF-B, CV Top


11. Under Review

    OPa-Ma:Text Guided Mamba for 360-degree Image Out-painting

    Penglei Gao*, Kai Yao*, Tiandi Ye, Steven Wang, Yuan Yao, Xiaofeng Wang

    PDF Under Review


12. AAAI 2024 Oral

    Unraveling Batch Normalization for Realistic Test-Time Adaptation

    Zixian Su, Jingwei Guo, Kai Yao, Xi Yang, Qiufeng Wang, Kaizhu Huang

    Proceedings of Association for the Advancement of Artificial Intelligence

    PDF Code CCF-A


13. CIKM 2023 Oral

    Explore Epistemic Uncertainty in Domain Adaptive Semantic Segmentation

    Kai Yao, Zixian Su, Xi Yang, Jie Sun, Kaizhu Huang

    ACM International Conference on Information and Knowledge Management

    PDF CCF-B, DM Top


14. TETCI

    PointNu-Net:Simultaneous Multi-tissue Histology Nuclei Segmentation and Classification in the Clinical Wild

    Kai Yao, Kaizhu Huang, Jie Sun, Amir Hussain, Curran Jude

    IEEE Transactions on Emerging Topics in Computational Intelligence

    PDF Code SCI Q1, IF 5.7


15. JBHI

    Mind The Gap:Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation

    Zixian Su, Kai Yao, Xi Yang, Qiufeng Wang, Yuyao Yan, Kaizhu Huang

    IEEE Journal of Biomedical and Health Informatics

    PDF SCI Q1, IF 7.7


16. AAAI 2023

    Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation

    Zixian Su*, Kai Yao*, Xi Yang, Qiufeng Wang, Jie Sun, Kaizhu Huang

    Proceedings of Association for the Advancement of Artificial Intelligence

    PDF Code CCF-A


17. ECCV 2022

    Outpainting by Queries

    Kai Yao*, Penglei Gao*, Xi Yang, Jie Sun, Rui Zhang, Kaizhu Huang

    European Conference on Computer Vision

    PDF Code CCF-B, CV Top


18. JBHI

    A novel 3D unsupervised domain adaptation framework for cross-modality medical image segmentation

    Kai Yao*, Zixian Su*, Kaizhu Huang, Xi Yang, Jie Sun, Amir Hussain, Frans Coenen

    IEEE Journal of Biomedical and Health Informatics

    PDF Code SCI Q1, IF 7.7


19. CC

    Scaffold-A549:a benchmark 3D fluorescence image dataset for unsupervised nuclei segmentation

    Kai Yao, Kaizhu Huang, Jie Sun, Lingzhi Jing, Dejian Huang, Curran Jude

    Cognitive Computation

    PDF Code CCF-B


20. NeuroComp.

    Improving deep neural network performance by integrating kernelized Min-Max objective

    Qiufeng Wang, Kai Yao, Rui Zhang, Amir Hussain, Kaizhu Huang

    NeuroComputing

    PDF CCF-C


21. ICONIP 2018

    Improving Deep Neural Network Performance with Kernelized Min-Max Objective

    Kai Yao, Kaizhu Huang, Rui Zhang, Amir Hussain

    International Conference on Neural Information Processing

    PDF CCF-C