I am currently a first-year Ph.D. student in the Individualized Interdisciplinary Program at The Hong Kong University of Science and Technology (HKUST), advised by Prof. Anyi Rao and Prof. Huamin Qu. I received my B.Eng. and M.Eng. degrees from Beihang University (BUAA), where I was advised by Prof. Si Liu.
I was fortunate to have interned at several leading tech companies, including Tencent, Alibaba Group, Baidu Inc., and Meituan, where I gained valuable industry experience and insights into real-world applications of computer vision and generative models.
My current research interest includes interactive videos, visual content generation and editing, visual creativity, and storytelling. I am passionate about achieving an immersive visual experience for users through interactive videos and exploring how to leverage advanced generative models to enhance human creativity and storytelling through visual media.
🔥 News
- Feb. 2026: 🎉🎉 BiCo is accepted by CVPR 2026!
- Feb. 2026: 🎉🎉 SesaHand is accepted by ICLR 2026!
- Dec. 2025: Excited to introduce BiCo that enables flexible concept composition from images and videos!
📝 Selected Papers
*: equal contribution, †: corresponding author
Composing Concepts from Images and Videos via Concept-prompt Binding
Xianghao Kong, Zeyu Zhang, Yuwei Guo, Zhuoran Zhao, Songchun Zhang, Anyi Rao
- We introduce Bind & Compose (BiCo), a one-shot method that enables flexible visual concept composition by binding visual concepts with the corresponding prompt tokens and composing the target prompt with bound tokens from various sources.
Taming Flow-based I2V Models for Creative Video Editing
Xianghao Kong, Hansheng Chen, Yuwei Guo, Lvmin Zhang, Gordon Wetzstein, Maneesh Agrawala, Anyi Rao
- We propose IF-V2V, an Inversion-Free method that can adapt off-the-shelf flow-matching-based I2V models for video editing without significant computational overhead.
ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images
Xianghao Kong, Qiaosong Qi, Yuanbin Wang, Anyi Rao, Biaolong Chen, Aixi Zhang, Si Liu, Hao Jiang
- ProFashion is a prototype-guided fashion video generation framework leveraging multiple reference images and human keypoint motion flow to achieve improved view consistency and temporal coherence.
Controllable Navigation Instruction Generation with Chain of Thought Prompting
Xianghao Kong*, Jinyu Chen*, Wenguan Wang†, Hang Su, Xiaolin Hu, Yi Yang, Si Liu†
- We propose C-Instructor, which utilizes the chain-of-thought-style prompt for style-controllable and content-controllable instruction generation.
DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
Xianghao Kong, Wentao Jiang, Jinrang Jia, Yifeng Shi†, Runsheng Xu, Si Liu
- DUSA decouples the V2X collaborative sim2real domain adaptation problem into two sub-problems: sim2real adaptation and inter-agent adaptation.
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
Junyu Luo*, Jiahui Fu*, Xianghao Kong, Chen Gao†, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu
- 3D-SPS bridges the gap between detection and matching in the 3D visual grounding task and localizes the target in a single stage.
- SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment, Zhuoran Zhao, Xianghao Kong, Linlin Yang, Zheng Wei, Pan Hui, Anyi Rao, ICLR 2026
👨🎓 Educations
- Sept. 2025 - Present, Ph.D. Student in Individualized Interdisciplinary Program, The Hong Kong University of Science and Technology (HKUST)
- Current Research Directions: Interactive Videos, Visual Content Generation and Editing, Visual Creativity
- Supervisors: Prof. Anyi Rao, Prof. Huamin Qu
- Sept. 2022 - Jan. 2025, M.Eng. in Computer Science and Technology, Beihang University (BUAA)
- Main Research Directions: Visual Content Generation, Vision & Language, Collaborative Perception
- Supervisor: Prof. Si Liu
- Standardized Tests: TOEFL 114 / 120, GRE 332 / 340
- Sept. 2018 - June 2022, B.Eng. in Computer Science and Technology, Beihang University (BUAA)
- Comprehensive Performance Ranking: 1st / 193
💻 Internships
- Feb. 2026 - Present, LightSpeed Studios, Tencent
- June 2024 - Nov. 2024, Taobao & Tmall Group, Alibaba Group
- Nov. 2022 - July 2023, Baidu Inc.
- July 2022 - Nov. 2022, Alibaba Group
- July 2021 - July 2022, Meituan
🎖 Achievements
- Hong Kong PhD Fellowship (HKPFS)
- National Scholarship of China (both undergraduate and postgraduate levels)
- Samsung Scholarship, and many university-level and school-level scholarships
- Outstanding Graduate of Beijing
- Merit Student of Beihang University, Outstanding Student of Beihang University
🕴️ Academic Services
- Organizer of the 7th CVEU Workshop at SIGGRAPH 2025
- Conference Reviewer for CVPR, ECCV, SIGGRAPH Asia, AAAI, ACM MM, and BMVC