Xu Zheng

About Me

👋 I am a Ph.D. candidate in the AI Thrust at The Hong Kong University of Science and Technology, Guangzhou campus. I am fortunate to be advised by Prof. Xuming Hu @ HKUST and Prof. Raymond Chi-Wing Wong @ HKUST.

I also serve as a Resident Doctoral Researcher at INSAIT, under the supervision of Prof. Luc Van Gool and Dr. Danda Paudel.

Recently, I have also been collaborating with Prof. Nicu Sebe @ UNITN, Linfeng Zhang @ SJTU, and Kailun Yang @ HNU.

My doctoral research focuses on developing algorithms for robust and interpretable multi-modal learning that span the full spectrum of perception, understanding, reasoning, and generation, such as:

• Artificial Intelligence Generated Content (AIGC): RealRAG (ICML 2025) TransDiff (arXiv 2025)
• Multimodal Foundation Models: UniBind (CVPR 2024) EventBind (ECCV 2024)
• Scene Understanding & Spatial Reasoning: OmniSAM (ICCV 2025) OSR-Bench (arXiv 2025)
• Novel / Omnidirectional Sensors: 360SFUDA++ (TPAMI 2024) DPPASS (CVPR 2023)
• Robustness & Knowledge Distillation: CIARD (ICCV 2025) C2VKD (Pattern Recognition 2024)

I also survey papers in cutting-edge topics: RAG for Computer Vision, Multi-modal Spatial Reasoning, and 360 Vision in Embodied AI.

🔥 I am actively seeking job opportunities (academia & industry) for Fall 2026!

News

• 2025.11: Selected to the MBZUAI Machine Learning Winter School 2026 in Abu Dhabi.
• 2025.11: Two papers accepted to AAAI 2026.
• 2025.10: The first Multi-modal Spatial Reasoning survey released: Paper
• 2025.10: One paper accepted to IJCV
• 2025.10: One paper accepted to IEEE TCSVT: CLIP-to-Seg
• 2025.09: Two papers accepted to NeurIPS 2025: Domain-RAG & HoloV
• 2025.06: One paper accepted to BMVC 2025: Split Matching
• 2025.06: Four papers (one Highlight (2.8%)) accepted to ICCV 2025: OmniSAM(Highlight) & CIARD & UNLOCK & Unimodal Bias
• 2025.06: Our paper is selected as Best Paper at CVPR 2025 @ TMM Open-World! Paper
• 2025.06: One paper accepted to IROS 2025: SHIFTNet
• 2025.05: Two papers accepted to ACL 2025 Findings: MMUNLearner & Mathematical Reasoning Survey
• 2025.05: One paper accepted to ICML 2025: RealRAG
• 2025.04: The first RAG in CV survey released: Paper
• 2025.04: Our paper accepted to CVPR 2025 @ TMM Open-World as Oral Presentation: MMSS-Bench
• 2025.02: Visit INSAIT as a Resident Doctoral Researcher! LinkedIn
• 2025.01: Successfully passed PhD Qualifying Examination!
• 2024.12: Invited as an Area Chair of PDLM @ AAAI 2025.
• 2024.10: One paper accepted to IEEE TPAMI: 360SFUDA++
• 2024.10: Oral presentation @ ECCV 2024 Oral Session 5A: Segmentation Video.
• 2024.09: One paper accepted to Pattern Recognition.
• 2024.07: Three papers (one Oral (1.5%)) accepted to ECCV 2024.
• 2024.03: One paper accepted to IEEE CAI 2024.
• 2024.03: One paper accepted to Pattern Recognition.
• 2024.03: Five papers (one Highlight (2.8%)) accepted to CVPR 2024.
• 2024.02: Two papers accepted to ICRA 2024.
• 2023.07: Two papers accepted to ICCV 2023.
• 2023.03: One paper accepted to CVPR 2023.

Invited Talks

• “Omnidirectional Vision: From Scene Understanding, Spatial Intelligence to Industrial Applications”
  SPIC Energy Science and Technology Research Institute, Shanghai, China, August 2025.
• “PANORAMA: Exploring the Industrial Potentials of Omnidirectional Vision”
  Yangtze River Delta International Talent Port, Wuxi, China, August 2025.
• “Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning”
  VIVO, August 2025. Invited talk by Dr. Kanzhi Wu, Shenzhen, China, August 2025.

Mentorship

Current: Yuanhuiyi Lyu (PhD, HKUST-GZ); Lutao Jiang (PhD, HKUST-GZ); Jialei Chen (PhD, Nagoya); Mengzhen Chi (PhD, NEU); Zihao Dongfang (RA, HKUST-GZ); Chenfei Liao (MPhil, HKUST-GZ); Junha Moon (MPhil, HKUST-GZ); Ziqiao Weng (MPhil, HKUST-GZ)); Yulong Guo (MS, ZJU); Kaiyu Lei (MPhil, HKUST-GZ)); Leyi Sheng (UG, HKUST-GZ)

Past: Ding Zhong (MS, Michigan); Zhengxuan Jiang (MPhil, ZJU); Yunhao Luo (PhD, Umich); Tianbo Pan (PhD, NUS); Zijie Lin (MS, USTC); Zhenquan Zhang (MPhil, SCUT); Boyuan Zheng (MPhil, Tongji)

✉️ Feel free to contact me for discussion and collaboration!

Services

• Area Chair: PDLM Workshop @ AAAI 2025
• Reviewers: IJCV, TIP, TNNLS, TMM, TCI, Neurocomputing, etc.
• PC Members: ICLR (2024,2025,2026), CVPR (2025,2026), ICML (2025), ICCV (2025), ECCV (2024), NeurIPS (2024,2025), AAAI (2026), ACM MM (2025), ICRA (2025), ICME (2025), WACV (2026)