Sherry Yang

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

[Sherry Yang @sherryyangML]

@xxunhuang Congrats Xun - amazing journey!

[Sherry Yang @sherryyangML]

@shinshin_oob Thanks Shin!

[Sherry Yang @sherryyangML]

Excited to share CrystalReasoner, a reasoning model for crystal structure generation with LLMs and property-conditioned generation through RL:

Website: https://t.co/249N2224on
Paper: https://t.co/W3n8wJN25P
Code: https://t.co/gIQj75p13p

[Sherry Yang @sherryyangML]

Great work led by @yy_wu36197 in collaboration with @FallettaStefano and Delia McGrath.

[Sherry Yang @sherryyangML]

To enable property-conditioned generation that is general enough to work for any properties (e.g., elastic properties, thermal expansions), we can design a general reward function by assigning positive reward to structures with properties falling in the specified range.

[Ivona Najdenkoska @ivonajdenkoska]

Come join our workshop “Multimodal Intelligence: Next Token Prediction & Beyond” - happening NOW at ICLR '26 @iclr_conf 🎉

📍 Riocentro (204 C)
🔗 Schedule: https://t.co/G2eYmg66ut
🔗 Livestream: https://t.co/1L6VR6kqxd

Excited for a full day of talks, posters, and discussions!

[Sherry Yang @sherryyangML]

@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!

https://t.co/dxs7lpCbCM

[Sherry Yang @sherryyangML]

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is?

Checkout "Evaluating Robot Policies in a World Model".

Paper: https://t.co/p1MwcrQe4b
Demo: https://t.co/OOkAQwVsu3
Code: https://t.co/y1EMv7Cnq2

[Sherry Yang @sherryyangML]

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

[Sony AI @SonyAI_global]

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.

[Sherry Yang @sherryyangML]

@_Suresh2 Thanks for the observation. We consider the setting of given an ML task, what is the most effective (RL vs prompting) to achieve the best ML model. The generalization is over stochastic outcomes of ML experiments of a single task. This setting is more similar to RL for Atari game

[Sherry Yang @sherryyangML]

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 https://t.co/vfk1jc76t5

2) MLE-Smith: scale-up MLE tasks automatically https://t.co/Mc5vyY2fhg

[Sherry Yang @sherryyangML]

@thkostolansky @percyliang Great question! We found newer frontier models do have much better initial performance, but they still struggle with improving a solution despite more time given. Models generally struggle with turning experience into actionable knowledge, which we think require gradient updates

[Sherry Yang @sherryyangML]

@russell_sushi @yuchen_zhuang @Anikait_Singh_ @percyliang @chaozhangcs @daibond_alpha RL for MLE was with an amazing collaborator @JoyHeYueya advised by @percyliang
Sat, 04/25 3:30pm | Pavilion 3 P3-#1722

[Sherry Yang @sherryyangML]

MLE-Smith is led by @russell_sushi with amazing collaborators @yuchen_zhuang @Anikait_Singh_ @percyliang @chaozhangcs @daibond_alpha
Poster on Fri, 04/24 8:15pm at Pavilion 4 P4-#5015