I am now (2023.09 - present) a Founding AI Scientist/Engineer at OpusClip. As the founding member of the Opus AI team, I focus on advancing AI research and innovation at OpusClip, leading the development of core AI features from concept to production. We are hiring AI full-time Engineers(US) an interns(US/CN), feel free to reach out!
I graduated from Cross-Media Intelligent Technology Lab (CMIT) at Fudan University in 2022.06, where I was supervised by Professor Rui Feng 冯瑞. Before that, I received my Bachelor’s degree in Automation as part of the Li-Siguang Project(selected 30/4500) at China University of Geosciences (Wuhan), under the guidance of Professors Haobin Dong 董浩斌 and Yuan Zhu 朱媛. My work experience includes internships at United Imaging Intelligence, collaborating with Fan Yang 杨帆, where I explored multi-task learning on object detection, And a summer internship at Alipay, where I focused on graph mining to identify high-risk users.
My primary research lies in application-driven AI research, strongly emphasizing video understanding and Large Language Model (LLM) Agents.
You can view my publications by clicking Google Scholar(
)
(Stay hungry 💦)
🔥 News
- 2025.09: 🎉 One paper and two workshop papers were accepted by NIPS 2025 !
- 2025.05: 🎉 One paper was accepted by ACL 2025 !
- 2024.08: 🔥 We lunched ClipAnything, the first mulitmodal video long2short clipping tool!
- 2023.09: 💼 I join OpusClip as an AI engineer!
📄 Selected Publications
- DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference.
- Chong Wu, Jiawang Cao (co-first author), Renjia Xu, et al.
- The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
- Reframe Anything: LLM Agent for Open World Video Reframing.
- Jiawang Cao, Yongliang Wu, Weiheng Chi, et al.
- What Makes a Good Video:Next Practices in Video Generation and Evaluation @ NeurIPS 2025 Workshop
- RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought.
- Yi Lu, Jiawang Cao (co-first author), Yongliang Wu, et al.
- The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)
- VEU-Bench: Towards Comprehensive Understanding of Video Editing. (Highlight)
- Bozheng Li, Yongliang Wu, Yi Lu, Jiashuo Yu, Licheng Tang, Jiawang Cao, Wenqing Zhu, Yuyang Sun, Jay Wu, Wenbo Zhu
- Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark.
- Yongliang Wu, Wenbo Zhu, Jiawang Cao (co-first author), et al.
- Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2025)
- Exploiting Deep Cross-Slice Features From CT Images For Multi-Class Pneumonia Classification.
- Jiawang Cao, Lulu Jiang, Junlin Hou, et al.
- 2021 IEEE International Conference on Image Processing (ICIP), 205–209. Accepted as Best Student Paper
- Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering.
- IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), vol. 31, no. 6, pp. 2114–2124, June 2021
🎖 Honors and Awards
- 2025.08: 1st Place in Multi Lingual Video Reasoning Evaluation challenge @CVPR2025
- 2025.06: 3rd Place in Multi-View Foul Recognition task (SoccerNet challenge) @ CVPR 2025
- 2024.10: 1st Place in Hour-long VideoQA challenge @ ECCV 2024
- 2024.06: 1st Place in Long-Term VideoQA challenge @ CVPR 2024
- 2019.12: Second Prize in The 16th China Post-Graduate Mathematical Contest in Modeling
- 2019.05: First Prize in The 12th Huazhong Mathematical Contest in Modeling
🎓 Educations
2019.09 - 2022.06,
- Fudan University — Master of Science, Computer Science and Technology (2019.09–2022.06), Shanghai, China
- Outstanding Graduate of Shanghai (Top 1%), Graduate National Scholarship (Top 1%),
- Excellent Academic Scholarship, Outstanding Student Leader in FDU
2015.09 - 2019.06
- China University of Geosciences (Wuhan) — Bachelor of Engineering, Automation (2015.09–2019.06), Wuhan, China
- Li Si-guang Honors Program (Selected 30/4500), Undergraduate National Scholarship (Top 1%),
- Haiyin Innovation Scholarship, Outstanding Student Leader in CUG