Yiming Chen

@yimiche

Rhodes Scholar | PhD @Oxford_VGG | prev CS + Math @mit

yimingc9.github.io

Joined April 2024

129 Following

155 Followers

Replies Reposts Media

Pinned
Yiming Chen
@yimiche
Jun 30
Can diffusion learn physical dynamics directly in 3D space? Yes! Introducing 🫧PhysiFormer🫧 — a unified model that generates physically plausible multi-object, multi-material 4D dynamics in world space, conditioned on initial per-vertex positions and velocities. 🧵1/8
5
Yiming Chen
@yimiche
Aug 29
Thrilled to learn from so many amazing insights!
Hirokatsu Kataoka | 片岡裕雄
@HirokatuKataoka
Aug 27
"Visual General Intelligence: A White Paper" is now on arXiv! arxiv.org/abs/2608.25924 We've discussed: - What is Visual Intelligence? - Can we develop it toward General Intelligence (VGI)? In the VGI white paper, we bring together diverse perspectives on Visual Intelligence and
Yiming Chen
@yimiche
Jul 1
Amazing work. Always so in awe of @ayushnoori! Cannot overstate the importance of systematic logging for medical AI. Accurate, consistent, and complete data is key to safe and reliable AI-assisted healthcare.
Ayush Noori
@ayushnoori
Jun 29
How can we log, audit, and improve deployed AI models and agents for medicine? 🏥 AI is rapidly entering the clinic. Although models are already deployed across millions of patients, there is no consistent approach to monitor model use, assess performance, detect failure modes,
1
Yiming Chen
@yimiche
Jun 30
So incredibly proud of @aneeshers’s work on real time RL!! Featuring a lightweight gating policy that picks how long to plan, no time wasted. 🚀
Aneesh Muppidi
@aneeshers
Jun 30
Introducing Real-time RL. In the real world, time isn't free. The environment keeps "moving" even when you're computing your next action. We show how RL agents can learn to adaptively think in real-time games. 1/🧵
Yiming Chen
@yimiche
Jun 23
Super cool work!!
Koichi Namekata
@Koichi_N_
Jun 23
Excited to share our #SIGGRAPH2026 paper: Go-with-the-Track! We utilize point-tracks as spatiotemporal conditioning to precisely insert multiple reference images into generated videos. Paper: arxiv.org/pdf/2606.20891 Project page: eyeline-labs.github.io/Go-with-the-Tr…

Yiming Chen

Yiming Chen’s posts