Research areas: Computer Vision
Google Scholar: link
Dr. Jinjin Gu
I am a tenure-track faculty member at INSAIT, in Sofia, Bulgaria, where I lead a group working on visual cognition and intelligence. My research interests include visual perception, visual processing, visual generation, and visual reasoning.
Before joining INSAIT, I received my Ph.D. from the School of Electrical and Computer Engineering at the University of Sydney in 2024, under the supervision of Prof. Wanli Ouyang and Prof. Luping Zhou. Prior to that, I obtained my Bachelor’s degree in Computer Science and Engineering from The Chinese University of Hong Kong, Shenzhen (CUHKSZ) in 2020. I work closely with Prof. Chao Dong and Prof. Junhua Zhao. I have also completed internships at the Multimedia Laboratory, SenseTime Research, and Tencent PCG Applied Research Center.
2026
Xin Lu, Jing Qiu, Xinlei Wang, Jinjin Gu, Jiafeng Lin, Sihai An, Junhua Zhao
Structural Alignment for Energy-Computation Co-Design
In: Nature Reviews Electrical Engineering 2026
Xiyuan Zhou, Zhuoqi Li, Xinlei Wang, Yirui He, Yuhao Wu, Yuheng Cheng, Yan Xu, Junhua Zhao, Jinjin Gu
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)
Zhendong Li, Lei Sun, Ruibo Ming, He Zhang, Danda Pani Paudel, Luc Van Gool, and Jinjin Gu
Knowledge-Centric Agents for Workflow Generation in ComfyUI
In: European Conference on Computer Vision (ECCV 2026)
Qingyu Yin, Yulun Wu, Zhennan Shen, Sunbowen Lee, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu
Evaluating Parameter Efficient Methods for RLVR
In: Forty-Third International Conference on Machine Learning (ICML 2026)
Liangbin Xie, Zheyuan Li, Fanghua Yu, Xinqi Lin, Jun-hao Zhuang, Jinfan Hu, Jinjin Gu, Jiantao Zhou, Chao Dong
Enhanced Latent-Space Adversarial Training for Super-Resolution
In: Forty-Third International Conference on Machine Learning (ICML 2026)
Xinlei Wang, Ruibo Ming, Jing Qiu, Junhua Zhao, Jinjin Gu
Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at Scale
In: Forty-Third International Conference on Machine Learning (ICML 2026)
Haoyu Chen, Jingjing Ren, Jiaxing Shen, Sixiang Chen, Jinjin Gu, Ping Tan, Lei Zhu
Density-Aware Video Desnowing with Robust Alignment on a Large-Scale Dataset
In: IEEE Transactions on Multimedia (TMM 2026)
Jinfan Hu, Zhiyuan You, Jinjin Gu, Kaiwen Zhu, Tianfan Xue, Chao Dong
Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining
In: Pattern Recognition, Volume 179, Part A, 2026, 113578, ISSN 0031-3203.
Xiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou, Yang Wu, Yuheng Cheng, Yulu Xie, Wenxuan Liu, Huan Zhao, Yan Xu, Jinjin Gu, Junhua Zhao
EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving
In: The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) (Findings)
Haoyu Chen, Keda Tao, Yizao Wang, Xinlei Wang, Lei Zhu, Jinjin Gu
Intelligent Photo Retouching with Language Model-Based Artist Agents
In: The Findings track of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026 Findings)
Zhiyuan You, Ke Wang, He Zhang, Xin Cai, Jinjin Gu, Tianfan Xue, Chao Dong, Zhoutong Zhang
PhotoFramer: Multi-modal Image Composition Instruction
In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)
Xiang Yin, Jinfan Hu, Zhiyuan You, Kainan Yan, Yu Tang, Chao Dong, Jinjin Gu
How Far Have We Gone in Generative Image Restoration? A Study on Its Capability, Limitations and Evaluation Practices
In: The Findings track of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026 Findings)
