Sherry Yang

@sherryyangML

Staff Research Scientist @GoogleDeepMind; Assistant Professor @NYU_Courant. Previously Post-Doc @Stanford, PhD @UCBerkeley, M.Eng. / B.S. @MIT.

sherryy.github.io

Joined September 2015

Replies Reposts Media

Sherry Yang
@sherryyangML
May 22
Excited to share CrystalReasoner, a reasoning model for crystal structure generation with LLMs and property-conditioned generation through RL: Website: crystalreasoner.github.io Paper: arxiv.org/abs/2605.14344 Code: github.com/wyy603/Crystal…
00:00
4
Sherry Yang
@sherryyangML
Apr 25
@julianhquevedo is presenting WorldGym right now 4/25 10:30am-1pm at Pavilion 4 #4818. Come and check out how world models can be used to evaluate robot policies in the cloud! x.com/sherryyangML/s…
Age-restricted adult content. This content might not be appropriate for people under 18 years old. To view this media, you’ll need to log in to X. Learn more
Sherry Yang
@sherryyangML
Apr 23
Super impressed by the Table Tennis robot from @SonyAI_global. As a TT player myself, I thought expert TT robot is decades away. Amazed by how far state-estimation (ball location + spin) plus simulator RL could get us. Proud of my student @mscard01 for being a part of this
00:00
Sony AI
@SonyAI_global
Apr 22
For 40+ years, building a robot that could rally with an elite human table tennis player at full speed was an unsolved problem. Sony AI's Ace research project set out to change that—and the results are now accepted for publication in @Nature and featured on the cover.
1
Sherry Yang
@sherryyangML
Apr 21
Machine learning engineering (MLE) is the new agentic frontier. I'll be sharing our work on scaling RL for MLE agents at #ICLR2026: 1) RL of a small model outperforms a frontier model arxiv.org/abs/2509.01684 2) MLE-Smith: scale-up MLE tasks automatically arxiv.org/abs/2510.07307
7
Sherry Yang
@sherryyangML
Feb 5
Excited to share World-Gymnast: Training Robots with RL in a World Model. Training a VLA policy in a world model with RL transfers to much improved real-robot success (according to third-party robot AutoEval). Website: world-gymnast.github.io Paper: arxiv.org/abs/2602.02454
7