Haoyu Zhang
PhD Student
Harbin Institute of Technology (Shenzhen)
zhang.hy.2019 AT gmail.com
I am Haoyu Zhang (张昊宇), a Ph.D. candidate at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), under the supervision of Prof. Liqiang Nie, Prof. Yaowei Wang, and Prof. Meng Liu. Prior to this, I received my M.S. degree from the School of Computer Science and Technology at Shandong University, where I was advised by Prof. Liqiang Nie and Prof. Meng Liu.
My research interests include multimodal retrieval, egocentric vision, and spatial intelligence. To date, I have published more than 10 papers in leading CCF-A conferences and journals, including IEEE TPAMI, ACM TOIS, CVPR, ICML, NeurIPS, AAAI, and ACM MM. I have also achieved strong results in international CVPR challenges, securing 9 first-place finishes, 2 second-place finishes, and 3 third-place finishes.
Multimodal Retrieval
→ show/hide representative work on multimodal retrieval.
Egocentric Vision
→ show/hide representative work on egocentric vision.
Spatial Intelligence
→ show/hide representative work on spatial intelligence.
- Vision-Language Navigation: Trajectory Waypoint (MM’26)
- Indoor Spatial Reasoning: SpaceEra (NeurIPS’25), SpaceEra++ (TPAMI’26)
- Low-Altitude Benchmark: SpatialUAV
Recent News
- [2026/06] Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation accepted by ACM MM 2026.
- [2026/06] Received the Best Oral Presentation Award at PolyU COMP-HIT (Shenzhen) CST Research Student Conference.
- [2026/06] Released SpatialUAV, a benchmark for low-altitude UAV spatial intelligence.
- [2026/06] SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion is available on arXiv.
- [2026/06] Technical reports for MARS, OSGNet, VISTA, and JFAA at EgoVis 2026 are available online.
- [2026/06] Won 1st place in Ego4D Natural Language Query, Goal Step, and Short-Term Object Interaction Anticipation tracks at the CVPR EgoVis Workshop 2026.
- [2026/06] Won 1st place in the EPIC-Kitchens Action Anticipation Track and 2nd place in the CASTLE VQA Track at the CVPR EgoVis Workshop 2026.
- [2026/05] SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video accepted by IEEE TPAMI 2026.
- [2026/04] Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog accepted by ACM TOIS 2026.
- [2026/02] TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models accepted by CVPR 2026.
Publications
Below is a list of selected publications. Please refer to my Google Scholar page for the full list of publications.
UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval
Haokun Wen, Xuemeng Song, Haoyu Zhang, Xiangyu Zhao, Weili Guan, Liqiang Nie
arXiv 2604.20318, 2026
[Paper]
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Haoyu Zhang, Qiaohui Chu, Yaowei Wang, Liqiang Nie
ACM MM 2026, CCF-A
[Paper]

OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
Yisen Feng, Leigang Qu, Haoyu Zhang, Qiaohui Chu, Meng Liu, Xuemeng Song, Weili Guan, Liqiang Nie
CVPR 2026 EgoVis Workshop
[Paper] [Code] [Website-NLQ] [Website-GS]Champion in the Natural Language Query and Goal Step Tracks of the Ego4D Challenge (1/19, 1/17)
VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
Qiaohui Chu, Haoyu Zhang, Yisen Feng, Meng Liu, Weili Guan, Dongmei Jiang, Liqiang Nie
CVPR 2026 EgoVis Workshop
[Paper] [Code] [Website]Champion in the Short-Term Object Interaction Anticipation Track of the Ego4D Challenge (1/21)
JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026
Qiaohui Chu, Haoyu Zhang, Yisen Feng, Meng Liu, Weili Guan, Dongmei Jiang, Liqiang Nie
CVPR 2026 EgoVis Workshop
[Paper] [Code] [Website]Champion in the Action Anticipation Track of the EPIC-KITCHENS Challenge (1/18)





OSGNet @ Ego4D Episodic Memory Challenge 2025
Yisen Feng, Haoyu Zhang, Qiaohui Chu, Meng Liu, Weili Guan, Yaowei Wang, Liqiang Nie
CVPR 2025 EgoVis Workshop
[Paper] [Video] [Code] [Website-MQ] [Website-NLQ] [Website-GS]Oral PresentationChampion in the Moment Queries, Natural Language Query, and Goal Step Tracks of the Ego4D Challenge (1/17, 1/28, 1/7)


HCQA @ Ego4D EgoSchema Challenge 2024
Haoyu Zhang, Yuquan Xie, Yisen Feng, Zaijing Li, Meng Liu, Liqiang Nie
CVPR 2024 EgoVis Workshop
[Paper] [Code] [Website-ES] [Website-Kaggle]Champion in the EgoSchema Track of the Ego4D Challenge (1/13) and Champion in the Kaggle EgoSchema Competition (1/72)
ObjectNLQ @ Ego4D Episodic Memory Challenge 2024
Yisen Feng, Haoyu Zhang, Yuquan Xie, Zaijing Li, Meng Liu, Liqiang Nie
CVPR 2024 EgoVis Workshop
[Paper] [Code] [Website-NLQ] [Website-GS]Runner-up in the Natural Language Query Track and Third place in the Goal Step Track of the Ego4D Challenge



Awards
- Best Oral Presentation Award at PolyU COMP-HIT (Shenzhen) CST Research Student Conference, 2026
- Chunhui Innovation Achievement Award, 2026
- Heilongjiang Provincial Model Student, 2025
- Tat-Seng Chua Scholarship, 2025
- NeurIPS Scholar Award, 2025
- INSUN Education Scholarship, 2024
- ICML Travel Award, 2024
- Second and Third Prize at the Xinchuang and Digital Economy Postdoctoral Haihe Academic Event, 2023
- Outstanding Graduates of Shandong University, 2023
- National Scholarship, 2021
- ACM MM Student Travel Award, 2021
- Outstanding Graduates of Shandong Province, 2020
- Top 10 Outstanding Students in the School of Computer Science and Engineering, 2019
Competitions
- Rank 3rd in CVPR Computer Vision in the Wild Workshop, MindCube Challenge, 2026
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Natural Language Query Track, 2026
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Goal Step Track, 2026
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Short-Term Object Interaction Anticipation Track, 2026
- Rank 1st in CVPR EgoVis Workshop, EPIC-Kitchens Challenge - Action Anticipation Track, 2026
- Rank 2nd in CVPR EgoVis Workshop, CASTLE Challenge - VQA Track, 2026
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Long-Term Action Anticipation Track, 2025
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Moment Queries Track, 2025
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Natural Language Query Track, 2025
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - Goal Step Track, 2025
- Rank 3rd in CVPR EgoVis Workshop, Ego4D Challenge - EgoSchema Track, 2025
- Rank 1st in Kaggle EgoSchema Competition, 2024
- Rank 1st in CVPR EgoVis Workshop, Ego4D Challenge - EgoSchema Track, 2024
- Rank 2nd in CVPR EgoVis Workshop, Ego4D Challenge - Natural Language Query Track, 2024
- Rank 3rd in CVPR EgoVis Workshop, Ego4D Challenge - Goal Step Track, 2024
Experience
Academic Intern, Community Science, Jul 2024 - Jul 2025
Project: Multimodal Large Language Model.

Academic Intern, Alibaba Cloud Intelligence, Wed 2022 - Jul 2022
Project: Partial Person Re-identification.

Academic Service
- Conference Reviewer: CVPR 2025-2026, ICCV 2025, NeurIPS 2022-2025, ICML 2023-2025, ICLR 2024-2025, SIGIR 2025, ACM MM 2022-2026, AAAI 2025-2026, IJCAI 2024, ICMR 2025-2026, PRCV 2023-2024, ISCAS 2024, ECAI 2024.
- Journal Reviewer: IEEE TPAMI, IEEE TIP, IEEE TCSVT, IEEE TMM, IEEE TKDE, Information Sciences.
- Volunteer: ICML 2024, China3DV 2024.