Xinyu Gong
Applied Scientist @ Adobe Firefly
San Jose, CA
I am an Applied Scientist at Adobe Firefly, working on generative AI for image and video generation. My research focuses on diffusion models, multimodal learning, and building scalable systems for controllable, high-quality visual content creation.
I received my Ph.D. in Electrical and Computer Engineering from the University of Texas at Austin and my B.Eng. from the University of Electronic Science and Technology of China.
news
| Jun 17, 2026 | ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning was accepted to ECCV 2026. |
|---|---|
| Mar 30, 2026 | MV-S2V: Multi-View Subject-Consistent Video Generation was accepted to SIGGRAPH 2026. |
| Feb 20, 2026 | CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization was accepted to CVPR 2026 Findings. |
| Feb 09, 2026 | I joined Adobe Firefly as an Applied Scientist. |
| Oct 16, 2023 | I joined TikTok as a Machine Learning Engineer. |