JULAIN Talk by Dr Lijun Yu

VideoPoet: A Large Language Model for Zero-Shot Video Generation
a model for zero-shot video generation, which received the Best Paper Award at ICML 2024.

When: Monday, October 7, 6pm
Where: https://fz-juelich-de.zoom.us/j/67742022466?pwd=NTHXwPLWaXTxGMkf08aupDNGRbCCno.1

Meeting ID: 677 4202 2466
Passcode: 606518

Dr. Lijun Yu is a research scientist at Google DeepMind, specializing in multi-modal foundation models, particularly for video generation. He obtained his Ph.D. and M.S. in Computer Science from Carnegie Mellon University and graduated from Peking University with a dual major in Computer Science and Economics. His research focuses on video generation using large language models and multimodal systems.

Paper:
VideoPoet: A Large Language Model for Zero-Shot Video Generation, ICML 2024 link
Photorealistic Video Generation with Diffusion Models, link
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation, ICLR 2024, link