Henry Smith

Statistics PhD Student, Knight-Hennessy Scholar, and NSF Fellow @Stanford | Previously @Yale | he/him

[Peter Pao-Huang @peterpaohuang]

Introducing Flux Matching, a generative modeling paradigm that generalizes diffusion models to vector fields that need not be the score function.

Enables structural priors in the dynamics, faster sampling, interpretable generation, and more!

w/ @StefanoErmon @Xiaojie_Qiu 🧵⤵️

[Xavier Gonzalez @xavierjgonzalez]

Parallelizing nonlinear RNNs is gaining traction!

More efficient than transformers; more expressive than linear RNNs.

My PhD thesis provides an intro guide to the math (Newton's method) behind the parallelization.

Great as a quick-start if you want to explore this new field!

[Henry Smith @smithhenryd]

Thanks for the opportunity @HannesStaerk to talk about our work (w/ @nate_diamant @brianltrippe) and for the great discussion!

[Hannes Stark @HannesStaerk]

Join our reading group session now about "Calibrating Generative Models to Distributional Constraints" https://t.co/yJOAa0kOJg :)

On zoom: https://t.co/Kew3F4DXag

[Alisa Levin @alisadlevin]

Excited to share our new work on cross-brain transfer of speech and handwriting BCIs! Some studies have required 10+ days of training data for peak BCI performance. Can pooling neural data from other users speed things up? 1/6
https://t.co/1Yjr5tNk7j

[Scott Linderman @scott_linderman]

My lab is presenting several papers at NeurIPS this week. Swing by the posters below to learn about our work!

🧵

[Amber Hu @amberhu63]

I'm very excited to share our work on SING, a new method for inferring latent dynamical systems from noisy time series data! I had a great time working on this project with @smithhenryd and @scott_linderman.

We'll be at @NeurIPSConf this week, swing by our poster to learn more!

[Henry Smith @smithhenryd]

Very excited about this work with @amberhu63 and @scott_linderman about how we can use natural gradient VI for the unsupervised discovery of latent dynamical systems.

At @NeurIPSConf this Wednesday! 👇

[Scott Linderman @scott_linderman]

New at @NeurIPSConf 2025: We are excited to share SING, our algorithm for unsupervised discovery of low-dimensional latent dynamical systems from high-dimensional, noisy observations. 🎶

Thread🧵

[Mohammed AlQuraishi @MoAlQuraishi]

OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇

[Scott Linderman @scott_linderman]

📣Announcing 2 @NeurIPSConf papers!

"Parallelizing MCMC Across the Sequence Length": uses Newton iterations to parallelize MCMC! 🤯

But can we parallelize any nonlinear state space model?

"Predictability Enables Parallelizability": proves what systems we can parallelize. 🧵

[Henry Smith @smithhenryd]

Super excited to share this preprint with @nate_diamant and my advisor @brianltrippe on how we can fine-tune diffusion models, language models, and more to match known distributional properties.

Check it out!👇

[Brian L Trippe @brianltrippe]

🚨New paper! Generative models are often “miscalibrated”. We calibrate diffusion models, LLMs, and more to meet desired distributional properties.

E.g. we finetune protein models to better match the diversity of natural proteins.

https://t.co/2c06vD0x2D
https://t.co/9Tbhf6ml8K

[Brian L Trippe @brianltrippe]

🚨New paper! Generative models are often “miscalibrated”. We calibrate diffusion models, LLMs, and more to meet desired distributional properties.

E.g. we finetune protein models to better match the diversity of natural proteins.

https://t.co/2c06vD0x2D
https://t.co/9Tbhf6ml8K