Boyuan Chen (@BoyuanChen0) / X

Boyuan Chen

431 posts

Boyuan Chen

@BoyuanChen0

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

San Francisco

Joined January 2021

Pinned
Boyuan Chen
@BoyuanChen0
Apr 24
We are committed to continually improving the GPT Image 2 model! I am actively fixing various issues from the community feedback. Just reply or DM me your GPT conversation! Features like 2K or 4K images are already available via the experimental API. Hope you enjoy the model!
235K
Boyuan Chen
@BoyuanChen0
Jul 3, 2024
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)
00:00
209K
Boyuan Chen
@BoyuanChen0
Feb 11, 2025
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: boyuan.space/history-guidan… (1/7)
00:00
176K
Boyuan Chen
@BoyuanChen0
Apr 11, 2024
I quit PhD (for a day) and opened a boba shop at @MIT - Generative Boba! It’s a huge success - right next to our office so all the AI researchers are enjoying it. Checkout our boba diffusion algorithm in the poster to understand why boba generation is so important to @MIT_CSAIL !
122K
Boyuan Chen
@BoyuanChen0
Feb 21, 2024
Sometimes being a PhD student at MIT is like living in 22nd century. Here is my robot dog getting its daily dose of free food with me.
00:00
57K
Boyuan Chen
@BoyuanChen0
Jan 23, 2024
Introducing Spatial VLM, a Vision-Language Model with 3D Spatial Reasoning Capabilities by @GoogleDeepmind. We investigate to what extent synthetic data can help VLMs learn - 3D relationship - quantitative distance - CoT spatial reasoning - RL reward spatial-vlm.github.io (1/6)
Spatial Visual Language Model
From spatial-vlm.github.io
96K
Boyuan Chen
@BoyuanChen0
Mar 13, 2025
I am so proud to be part of this incredible lab during my undergrad and got to meet so many incredible people - I’d like to add that, while having no official valuation, my boba shop business has been acquired by MIT!
Pieter Abbeel
@pabbeel
Mar 12, 2025
Founders who were PhD or post-doc in my lab at Berkeley, **largely funded by NSF / DoD grants**, start-up, market cap (collected by OpenAI Deep Research)
44K
Boyuan Chen
@BoyuanChen0
Sep 22, 2022
How can we ground large language models (LLM) with the surrounding scene for real-world robotic planning? Our work NLMap-Saycan allows LLMs to see and query objects in the scene, enabling real robot operations unachievable by previous methods. Link: nlmap-saycan.github.io 1/6
NLMap-SayCan
From nlmap-saycan.github.io
Boyuan Chen
@BoyuanChen0
Mar 5, 2024
My AI+robotics lecture at MIT is now public! Back in 2023 I talked about how video models will revolutionize robotics, and many other foundation models like LLMs. Now SORA arrives, definitely checkout my lecture on Foundation Models for Decision making at youtu.be/XLPObNeeTGg?si…
21K
Boyuan Chen
@BoyuanChen0
Sep 30, 2025
Introducing Sora 2 — our most advanced video model! A true world-model breakthrough that’s not only groundbreaking but also incredibly fun. Huge respect to the team who worked humbly behind the scenes, cut through the noise and skepticism, and shook the world with this release!
OpenAI
@OpenAI
Sep 30, 2025
Sora 2 is here.
00:00
19K
Boyuan Chen
@BoyuanChen0
Oct 27, 2025
The power of world models
Tesla
@Tesla
Oct 26, 2025
To push self-driving into situations wilder than reality, we built a neural network world simulator that can create entirely synthetic worlds for the Tesla to drive in. Video below is fully generated & not a real video
00:00
18K
Boyuan Chen
@BoyuanChen0
Nov 28, 2023
I am giving a guest lecture at MIT about "Foundation Models for Decision Making". My current plan is LLM (Saycan, RT2, Code as Policy, Toolformer etc) + Video Prediction (Unipy, Video Language Planning). Please let me know if you have additional suggestion!
21K
Boyuan Chen
@BoyuanChen0
Nov 1, 2024
Very exciting model showing the potential of video world models! Oasis is a neural network-based game engine trained with Diffusion Forcing. In the meantime, my team at MIT is actively working on Diffusion Forcing 2 which will make your video much more consistent with a simple
Decart
@DecartAI
Oct 31, 2024
1/ We are excited to introduce Oasis, the world's first real-time AI world model, developed in collaboration with @Etched. Imagine a video game entirely generated by AI, or a video you can interact with—constantly rendered at 20 fps, in real-time, with zero latency
00:00
14K
Boyuan Chen
@BoyuanChen0
Oct 17, 2024
Diffusion Forcing has been featured by MIT CSAIL and MIT News!
MIT CSAIL
@MIT_CSAIL
Oct 17, 2024
Sequence models have skyrocketed in popularity for their ability to analyze data & predict what to do next. MIT’s "Diffusion Forcing" method combines the strengths of next-token prediction (like w/ChatGPT) & video diffusion (like w/Sora), training neural networks to handle
00:00
9K