Ji Zhang     

Associate Professor, University of Electronic Science and Technology of China
[Google Scholar] [GitHub]
Email: jizhang.jim@gmail.com   WeChat (微信): Enjoy_Every_Episode

I am Ji Zhang (张继), an Associate Professor with the School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), where I am currently a key member of Prof. Lianli Gao's research team. I received my Ph.D. degree in 2024 from the School of Computer Science and Engineering, UESTC, where I was very fortunate to be advised by Prof. Jingkuan Song and Prof. Lianli Gao.

My research interests include, but are not limited to:

  1. Robot Learning: Developing robust learning algorithms that enable autonomous agents to acquire complex manipulation skills and interact seamlessly with physical environments.
  2. Multimodal Learning: Leveraging large-scale multimodal pre-training to develop versatile models capable of cross-modal reasoning and continual learning.
  3. Computer Vision: Tackling fundamental challenges in visual perception, including object recognition, few-shot learning and OOD/noise detection.
  Open Positions
  • There are 1-2 (resp. 3-4) openings for PhD (resp. Master) students with relevant research experience on Robot Learning, Multimodal Learning, and Computer Vision. Candidates are expected to have publications in top conferences (CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, RSS, ICRA, CoRL, etc.) or high-impact journals (TPAMI, IJCV, TIP, TMM, etc.). Qualified candidates are welcome to apply.
  • I am looking for 2-3 interns working on Robot Learning and Multimodal Learning. Please feel free to email me with your CV if you are interested.
What's New
  • [09/2026] Thrilled to return to Prof. Lianli Gao's group at UESTC as an Associate Professor.
  • [09/2026] One survey paper about Efficient VLA was accepted by IEEE TPAMI.
  • [09/2026] One paper about Robot Learning was accepted by CoRL'26.
  • [08/2026] One paper about LLM Agents was accepted by EMNLP'26.
  • [07/2026] Two papers about 3D Generation/Affective Computing were accepted by ACM MM'26.
  • [06/2026] Two papers about Multimodal Learning were accepted by ACM TOMM and IEEE TCSS.
  • [06/2026] Our team won the 1st Place in the AdoDAS Challenge at ACM MM'26.
  • [05/2026] One paper about 3D Generation was accepted by ICML'26.
  • [04/2026] One paper about LLM Agents was accepted by IEEE TPAMI.
  • [04/2026] Two papers about Time Series Forecasting were accepted by Information Fusion.
  • [04/2026] One paper about LLM Agents was accepted by ACL'26.
  • [03/2026] One paper about Watermarking was accepted by Information Fusion.
  • [03/2026] One paper about Few-shot Learning was accepted by IEEE TPAMI.
  • [02/2026] Three papers about Few-shot/Multi-label Learning were accepted by IEEE TMM.
  • [01/2026] Three papers about Robot Learning were accepted by ICLR'26 and ICRA'26.
  • [12/2025] One paper about Multimodal Learning was accepted by IJCV
  • [12/2025] One paper about Image Encryption was accepted by IEEE TMM.
  • [06/2025] One paper about Few-shot Learning was accepted by IEEE TPAMI.
  • [05/2025] One paper about OOD Detection was accepted by SCIENCE CHINA Inf. Sci.
  • [05/2025] One paper about Time Series Forecasting was accepted by IEEE TKDE.
  • [02/2025] One paper about Multimodal Learning was accepted by CVPR'25.
  • [02/2024] One paper about Multimodal Learning was accepted by CVPR'24.
  • [10/2023] One paper about OOD Detection was accepted by IEEE TIP.
  • [07/2023] One paper about Few-shot Learning was accepted by ICCV'23.
  • [04/2023] One paper about Few-shot Learning was accepted by ICML'23.
  • [04/2023] Two papers about Few-shot/Continue Learning were accepted by ACM MM'22.
  • [03/2022] One paper about Few-shot Learning was accepted by IEEE TCSVT.
  • [06/2021] One paper about Few-shot Learning was accepted by ACM MM'21.
Selected Papers
  • A Survey on Efficient Vision-Language-Action Models   [pdf]  
    Zhaoshu Yu, Bo Wang, Pengpeng Zeng, Haonan Zhang, Ji Zhang, Lianli Gao, Jingkuan Song, Heng Tao Shen
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

  • From Failure to Mastery: Generating Hard Samples for Tool-use Agents   [pdf]  
    Bingguang Hao, Zengzhuang Xu, Yuntao Wen, Xinyi Xu, Yang Liu, Tong Zhao, Maolin Wang, Long Chen, Dong Wang, Yicheng Chen, Cunyin Peng, Xiangyu Zhao, Chenyi Zhuang, Ji Zhang
    The Conference on Empirical Methods in Natural Language Processing (EMNLP Main), 2026

  • SpatialGS: Relative Spatial Regularization in Gaussian Splatting for Layout-guided Text-to-3D Generation   [pdf]  
    Qinhong Du, Xiao Cai, Pengpeng Zeng, Ji Zhang, Jingkuan Song, Lianli Gao
    ACM International Conference on Multimedia (ACM MM), 2026

  • CMSFusion: A Cross-Modal Spatial Fusion Network for Adolescent Mental Health Assessment   [pdf]  
    Kaiwen Qin, Fuxiong Zhou, Yajun Huang, Ji Zhang, Pengpeng Zeng, Xuanhan Wang, Jingkuan Song, Lianli Gao
    ACM International Conference on Multimedia (ACM MM), 2026

  • Context-Aligned Latent Enhancement for Multimodal Hate Meme Detection   [pdf]  
    Liansong Zong, Qingchi Gui, Jie Wang, Xiaorong Liu, Xiaocao Ouyang, Ji Zhang
    IEEE Transactions on Computational Social Systems (TCSS), 2026

  • Dual-branch Prompting for Multimodal Machine Translation   [pdf]  
    Jie Wang, Zhendong Yang, Liansong Zong, Xiaobo Zhang, Dexian Wang, Ji Zhang
    ACM Transactions on Multimedia Computing Communications and Applications (TOMM), 2026

  • TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity   [pdf]  
    Xiao Cai, Lianli Gao, Pengpeng Zeng, Ji Zhang, Heng Tao Shen, Jingkuan Song
    International Conference on Machine Learning (ICML), 2026

  • OmniCharacter++: Towards Comprehensive Benchmark for Realistic Role-Playing Agents   [pdf]  
    Haonan Zhang, Pengpeng Zeng, Ji Zhang, Jingkuan Song, Nicu Sebe, Heng Tao Shen, Lianli Gao
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

  • ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification   [pdf]  
    Xin Wu, Fei Teng, Ji Zhang, Xingwang Li, Yuxuan Liang
    Information Fusion (InfFus), 2026

  • BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness   [pdf]  
    Bingguang Hao, Maolin Wang, Zengzhuang Xu, Cunyin Peng, Yicheng Chen, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang, Ji Zhang
    Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2026

  • Out-of-distribution Generalization in Time Series: A Survey   [pdf]  
    Xin Wu, Fei Teng, Xingwang Li, Ji Zhang, Tianrui Li, Qiang Duan
    Information Fusion (InfFus), 2026

  • Securing Digital Assets in Intelligent Railways: A Survey of Watermarking Techniques, Challenges, and Prospects   [pdf]  
    Zhouqiao He, Zijie Zhao, Jie Hu, Ji Zhang, Shuo Ji, Qikai Chu, Weichao Liang, Ding Chen and Tianrui Li
    Information Fusion (InfFus), 2026

  • From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning   [pdf]  
    Ji Zhang, Xu Luo, Lianli Gao, Difan Zou, Heng Tao Shen, Jingkuan Song
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

  • Benchmarking Few-shot Transferability of Pretrained Models with Improved Eval. Protocols   [pdf]  
    Xu Luo, Ji Zhang, Lianli Gao, Heng Tao Shen, Jingkuan Song
    IEEE Transactions on Multimedia (TMM), 2026

  • Structure-aware Prompt Adaptation from Seen to Unseen for Open-vocabulary Compositional Zero-shot Learning   [pdf]  
    Yihang Duan, Jiong Wang, Pengpeng Zeng, Ji Zhang, Lei Zhao, Chong Wang, Jingkuan Song, Lianli Gao
    IEEE Transactions on Multimedia (TMM), 2026

  • Exploring Partial Multi-label Learning via Integrating Semantic Co-occurrence Knowledge   [pdf]  
    Xin Wu, Fei Teng, Yue Feng, Kaibo Shi, Zhuosheng Lin, Ji Zhang, James Wang
    IEEE Transactions on Multimedia (TMM), 2026

  • Policy Contrastive Decoding for Robotic Foundation Models   [pdf]  
    Shihan Wu, Xu Luo, Ji Zhang, Junlin Xie, Jingkuan Song, Heng Tao Shen, Lianli Gao
    International Conference on Learning Representations (ICLR), 2026

  • InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning   [pdf]  
    Ji Zhang, Shihan Wu, Xu Luo, Hao Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song
    IEEE International Conference on Robotics and Automation (ICRA), 2026

  • Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation   [pdf]  
    Junhong Zhu, Ji Zhang, Jingkuan Song, Lianli Gao, Heng Tao Shen
    IEEE International Conference on Robotics and Automation (ICRA), 2026

  • A Closer Look at Conditional Prompt Tuning for Vision-Language Models   [pdf]  
    Ji Zhang, Shihan Wu, Lianli Gao, Jingkuan Song, Nicu Sebe, Heng Tao Shen
    International Journal of Computer Vision (IJCV), 2026

  • Indistinguishability Analysis of JPEG Image Encryption Schemes   [pdf]  
    Yuan Yuan, Lingfeng Qu, Ji Zhang, Ningxiong Mao, Hadi Amirpour
    IEEE Transactions on Multimedia (TMM), 2025

  • Object Goal Navigation based on 3D Semantic Gaussian   [pdf]  
    Xinyi Chen, Tianrui Li, Ji Zhang, Haonan Luo
    International Conference on Embodied Intelligence and Large Models (EILM), 2025 (Best Paper Award)

  • Near-boundary Noise Improved Few-shot Out-of-distribution Detection   [pdf]  
    Ji Zhang, Yuxin Zeng, Lianli Gao, Jingkuan Song, Tianrui Li
    SCIENCE CHINA Information Sciences (中国科学:信息科学), 2025

  • Reliable Few-shot Learning under Dual Noises   [pdf]  
    Ji Zhang, Jingkuan Song, Lianli Gao, Nicu Sebe, Heng Tao Shen
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

  • Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecasting   [pdf]  
    Qi Xiong, Kai Tang, Minbo Ma, Ji Zhang, Jie Xu, Tianrui Li
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025

  • Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves   [pdf]  
    Shihan Wu, Ji Zhang, Pengpeng Zeng, Lianli Gao, Jingkuan Song, Heng Tao Shen
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025

  • DePT: Decoupled Prompt Tuning   [pdf]  
    Ji Zhang, Shihan Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

  • From Global to Local: Multi-scale Out-of-distribution Detection   [pdf]  
    Ji Zhang, Lianli Gao, Bingguang Hao, Hao Huang, Jingkuan Song, Heng Tao Shen
    IEEE Transactions on Image Processing (TIP), 2023

  • DETA: Denoised Task Adaptation for Few-Shot Learning   [pdf]  
    Ji Zhang, Lianli Gao, Xu Luo, Heng Tao Shen, Jingkuan Song
    IEEE International Conference on Computer Vision (ICCV), 2023

  • A Closer Look at Few-shot Classification Again   [pdf]  
    Xu Luo, Hao Wu, Ji Zhang, Lianli Gao, Jing Xu, Jingkuan Song
    International Conference on Machine Learning (ICML), 2023

  • Progressive Meta-learning with Curriculum   [pdf]  
    Ji Zhang, Jingkuan Song, Lianli Gao, Ye Liu, Heng Tao Shen
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022

  • Free-lunch for Cross-domain Few-shot learning: Style-aware Episodic Training with Robust Contrastive Learning   [pdf]  
    Ji Zhang, Jingkuan Song, Lianli Gao, Heng Tao Shen
    ACM International Conference on Multimedia (ACM MM), 2022

  • Class Gradient Projection for Continual Learning   [pdf]  
    Cheng Chen, Ji Zhang, Jingkuan Song, Lianli Gao
    ACM International Conference on Multimedia (ACM MM), 2022

  • Curriculum-based Meta-learning   [pdf]  
    Ji Zhang, Jingkuan Song, Yazhou Yao, Lianli Gao
    ACM International Conference on Multimedia (ACM MM), 2021

  • Particle Subswarms Collaborative Clustering   [pdf]  
    Collins Census, Hongjun Wang, Ji Zhang, Ping Deng, Tianrui Li
    IEEE Transactions on Computational Social Systems (TCSS), 2019

Academic Services
Team Time
Farewell and Congratulations

06/2026


A proud farewell to the Class of 2026! Thank you for your hard work, dedication, and the unforgettable moments. Wishing you endless success in your future endeavors.

Annual Wrap-up Assembly

01/2026


We hosted our 2025 Annual Wrap-up Assembly! It was a wonderful opportunity to reflect on our scientific advancements and cherish the personal highlights of the past year. Various awards were presented to inspire our team to strive for excellence and make 2026 a year of abundant achievements.

A Bittersweet Goodbye

06/2025


Celebrating the Class of 2025! A farewell filled with smiles and memories. Happy graduation to you all—may your future be as brilliant as you are.

Miscellaneous

When I have spare time, I enjoy hiking, running and cooking.

    This well-designed template was borrowed from Prof. Wei Xu.