Boyuan Chen's banner

Boyuan Chen

@BoyuanChen0 • 12,588 subscribers

Researcher @OpenAI, core member of the GPT Image research team. PhD @MIT EECS. I do world models, RL, and robotics.

Shorts

Introducing Diffusion Forcing, which unifies next-token prediction (eg LLMs) and full-seq. diffusion (eg SORA)! It offers improved performance & new sampling strategies in vision and robotics, such as stable, infinite video generation, better diffusion planning, and more! (1/8)

Introducing Diffusion Forcing, which unifies next-token prediction (eg LLMs) and full-seq. diffusion (eg SORA)! It offers improved performance & new sampling strategies in vision and robotics, such as stable, infinite video generation, better diffusion planning, and more! (1/8)

208,434 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Introducing Large Video Planner (LVP-14B) — a robot foundation model that actually generalizes. LVP is built on video gen, not VLA. As my final work at Massachusetts Institute of Technology (MIT), LVP has all its eval tasks proposed by third parties as a maximum stress test, but it excels!🤗

Introducing Large Video Planner (LVP-14B) — a robot foundation model that actually generalizes. LVP is built on video gen, not VLA. As my final work at Massachusetts Institute of Technology (MIT), LVP has all its eval tasks proposed by third parties as a maximum stress test, but it excels!🤗

98,082 просмотров • 4 месяцев назад

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)

175,996 просмотров • 1 год назад

Больше нет контента для загрузки