Visiting Doctoral Student
Xu Zheng
Email: [email protected]
About me:
I am a visiting researcher at at the Institute for Computer Science, Artificial Intelligence and Technology (INSAIT), where I am working on multimodal learning and multimodal large models supervised by Prof. Luc Van Gool and Prof. Danda Paudel.
I am a Ph.D. candidate in AI Thrust at The Hong Kong University of Science and Technology, Guangzhou campus. I am delighted to be working with Prof. Xuming Hu and Prof. Raymond Chi-Wing Wong.
I study machine perception, reasoning, and interaction with the physical world, drawing inspiration from human cognition. Lately, I’ve been focusing on unfied multi-modal Learning and advanced sensing & perception techniques.
Education:
Northeastern University – Master in Information and Communication Engineering, 2023
Northeastern University – Bachelor in Communication Engineering, 2019
Publications:
Refer to my google scholar profile: https://scholar.google.com.hk/citations?user=Ii1c51QAAAAJ&hl=zh-CN
Personal website: https://zhengxujosh.github.io/
2026
Zihao Dongfang, Xu Zheng, Ziqiao Weng, Yuanhuiyi Lyu, Danda Pani Paudel, Luc Van Gool, Kailun Yang, Xuming Hu
Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning? (findings)
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)
Bin Ren, Yawei Li, Xu Zheng, Yuqian Fu, Danda Pani Paudel, Hong Liu, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe
Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
The Fourteenth International Conference on Learning Representations (ICLR 2026)
Bin Ren, Runyi Yang, Qi Ma, Xu Zheng, Mengyuan Liu, Danda Pani Paudel, Luc Van Gool, Rita Cucchiara, Nicu Sebe
Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration
The Fourteenth International Conference on Learning Representations (ICLR 2026)
Deheng Zhang, Yuqian Fu, Runyi Yang, Yang Miao, Tianwen Qian, Xu Zheng, Guolei Sun, Ajad Chhatkuli, Xuanjing Huang, Yu-Gang Jiang, Luc Van Gool, Danda Pani Paudel
EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
In: The Fourteenth International Conference on Learning Representations (ICLR 2026)
2025
Chenfei Liao, Kaiyu Lei, Xu Zheng, Junha Moon, Zhixiong Wang, Yixuan Wang, Danda Pani Paudel, Luc Van Gool, Xuming Hu
Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness
In: Conference on Computer Vision and Pattern Recognition (CVPR 2025) (Workshop)
Xu Zheng, Yuanhuiyi Lyu, Lutao Jiang, Danda Pani Paudel, Luc Van Gool, Xuming Hu
Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization
In: International Conference on Computer Vision (ICCV 2025)
Ding Zhong, Xu Zheng, Chenfei Liao, Yuanhuiyi Lyu, Jialei Chen, Shengyang Wu, Linfeng Zhang, Xuming Hu
OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
In: International Conference on Computer Vision (ICCV 2025)
Yihong Cao, Jiaming Zhang, Xu Zheng, Hao Shi, Kunyu Peng, Hang Liu, Kailun Yang, Hui Zhang
Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
In: International Conference on Computer Vision (ICCV 2025)
Liming Lu, Shuchao Pang, Xu Zheng, Xiang GU, Anan Du, Yunhuai Liu, Yongbin Zhou
CIARD: Cyclic Iterative Adversarial Robustness Distillation
In: International Conference on Computer Vision (ICCV 2025)
Jialei Chen, Xu Zheng, Dongyue Li, Chong Yi, Seigo Ito, Danda Pani Paudel, Luc Van Gool, Hiroshi Murase, Daisuke Deguchi
Split Matching for Inductive Zero-shot Semantic Segmentation
In: The British Machine Vision Conference (BMVC 2025)
Xin Zou, Di Lu, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Xu Zheng, Linfeng Zhang, Xuming Hu
Don’t Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Yu Li, Xingyu Qiu, Yuqian Fu, Jie Chen, Tianwen Qian, Xu Zheng, Danda Pani Paudel, Yanwei Fu, Xuanjing Huang, Luc Van Gool, Yu-Gang Jiang
Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
