Ceyuan Yang

@CeyuanY

researcher @ bytedance seed

Hong Kong

scholar.google.com/citations?user…

Joined February 2020

586 Following

2,244 Followers

Replies Reposts Media

Pinned
Ceyuan Yang
@CeyuanY
Apr 24
Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.
00:00
9
Ceyuan Yang
@CeyuanY
Aug 21
Multimodal understanding capabilities will significantly accelerate robotics one day, just like what happened before in visual generation.
Alexandr Wang
@alexandr_wang
Aug 20
1/ muse spark 1.2 is a very strong multimodal model—it can do visual coding, robotics planning, and audio-visual understanding that all come together through agentic tools.
00:00
00:00
3
Ceyuan Yang
@CeyuanY
Jul 9
impressive improvements, well done bro
Yinghao Xu
@YinghaoXu1
Jul 9
🚀 LingBot-VA 2.0 is here! After half a year of teamwork, we're thrilled to release LingBot-VA 2.0 — a native video-action foundation model for generalizable robot control. Unlike prior world-action models that retrofit generic video generators for robot control, LingBot-VA 2.0
00:00
1
Ceyuan Yang
@CeyuanY
Jul 2
see you in seoul
Peter Lin
@peter9863
Jul 1
Adversarial Flow Models is accepted at ICML. Continuous Adversarial Flow Models is accepted at ECCV. Heading to Seoul next week. See you all at #ICML.
Ceyuan Yang
@CeyuanY
May 19
from pose diffusion, vggsfm, vggt to vggt-omega, well done, jianyuan
Jianyuan
@jianyuan_wang
May 19
Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.
00:00
1