Invited Talk
in
Workshop: What Makes a Good Video: Next Practices in Video Generation and Evaluation Sat, Dec 6, 2025 • 3:30 PM – 4:05 PM PST

Towards Autoregressive Modeling for Scalable and Versatile Visual Generation

Yi Jiang

Speaker

Yi Jiang

Currently, I am a Researcher at ByteDance Seed, where I work on Generative Foundation models. My previous research focus is on large scale open world visual understanding and pretraining in images & videos. My work of Visual AutoRegressive modeling won the Best Paper Award of NeurIPS 2024.

Video

Chat is not available.