Chengyao Wang (王程钥)

I am a PhD student at the Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), advised by Prof. Jiaya Jia and Prof. Bei Yu . Prior to that, I obtained my B.E. degree in Computer Science from Sun Yat-Sen University (SYSU).

I am particular interested in building Human-like Multimodal Intelligence that can actively interact to the physical world and have long-term memory. Recently, my research mainly focus on Multi-modal Large Language Models (MLLMs). Prior to that, I also had some experience on visual perception.

I am actively seeking Industrial Opportunities for 2026 Fall in any location. Fell free to contact if you are intersted. Research discussion and collaboration are always welcome, feel free to contact.

Google Scholar  /  GitHub  /  Twitter  /  Linkdin  /  Email

• [2025-08] We release MGM-Omni , an open source omni moded support long speech understanding, generation and zero-shot voice clone.
• [2025-06] Lyra is accepted in ICCV 2025, Hawaii.
• [2025-03] VisionZip and DreamOmni are accepted in CVPR 2025, Nashville.
• [2024-12] We release Lyra , an open source multi-modal large language models that support long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction.
• [2024-07] LLaMA-VID is accepted in ECCV 2024, Milano.
• [2024-03] We release Mini-Gemini , an open source vision-language models that support high-resolution image understanding, reasoning and generation.
• [2024-02] GroupContrast is accepted in CVPR 2024, Seattle.
• [2023-11] We release LLaMA-VID , an open source vision-language models that support hour-long video understanding and reasoning.

* indicates equal contribution

• Gold Medal x 3, International Collegiate Programming Contest (ICPC), Regional
• Gold Medal, Chinese Collegiate Programming Contest (CCPC)

Reviewer / Program Committee Member

• IEEE International Conference on Computer Vision (ICCV)
• Conference on Neural Information Processing Systems (NeurIPS)
• Association for the Advancement of Artificial Intelligence (AAAI)
• IEEE Winter Conference on Applications of Computer Vision (WACV)