Ron Shprints

MIT '25 CS/Math

[Ron Shprints @RShprints]

@andrewgwils An honorable move

[Peter Holderrieth @peholderrieth]

Very excited about this work! Language modeling via flow maps allows us to rethink how to build language models that do latent reasoning and fast generation!

Glad to play my small part in a wonderful effort with @PPotaptchik, @json_yim, @adhisarav, Eric Vanden-Eijnden, @msalbergo!

[Peter Holderrieth @peholderrieth]

Arriving in Rio 🇧🇷for #ICLR! I will present GLASS Flows + Diamond Maps in the coming days - starting today with GLASS Flows Oral at 11:30 AM! I am looking forward to meeting new people! Feel free to reach out!

1/3

[Ron Shprints @RShprints]

RT @peholderrieth: We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our m…

[Ron Shprints @RShprints]

@andrewgwils I'm sad to admit, this might not even be possible for me.

[Peter Holderrieth @peholderrieth]

We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI.

📖 Read the notes here: https://t.co/RULWDgn9pm

Joint work with @EErives40101.

[Ron Shprints @RShprints]

Recordings have just dropped on YouTube! You should definitely check out this amazing resource if you want to learn about flow matching. Peter is the best of the best and he put so much effort into this. It was a pleasure to contribute my small part:)

[Peter Holderrieth @peholderrieth]

🚀MIT Flow Matching and Diffusion Lecture 2026 Released (https://t.co/bKgs2wghvY)!

We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include:
📺 Videos: Step-by-step derivations.
📝 Notes: Mathematically self-contained lecture notes
💻 Coding: Hands-on exercises for every component

We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models.

Everything is available here: https://t.co/bKgs2wghvY

A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints!

#MachineLearning #GenerativeAI #MIT #DiffusionModels #AI

[Ron Shprints @RShprints]

@andrewgwils I started as a chemist. Took a long detour in "pure" AI for a while. Now I partake in the so called "AI4Science" party. Am I a scientist? Or an ML researcher? I wouldn't know. I'm probably neither. But I certainly enjoy both.

[Ron Shprints @RShprints]

@andrewgwils I'm going to be nerdsniped for this, but when I figured this in high school I was absolutely blown away. For weeks, my go to conversation starter was the microwave story. I just couldn't believe that we managed to put this machine together. Oh god I've just got nerdsniped again.

[Shangyuan Tong @ShangyuanTong]

Most people assume you need a massive dataset to distill flow models.

We challenge that.

Is data actually necessary? Or perhaps it is a liability?

Introducing FreeFlow: We achieve SOTA (1.49 FID on ImageNet-512) 1-step image generation without a single data sample.

🧵👇[1/n]

[Ron Shprints @RShprints]

@owl_posting That sounds like a paper that I'd write

[Ilya Sutskever @ilyasut]

truly the greatest day ever🎗️

[Yaron Lipman @lipmanya]

New work led by @peholderrieth showing how to transform an already trained flow matching model to a stochastic transition/posterior model that can still be sampled via an efficient ODE solver!

[Peter Holderrieth @peholderrieth]

New work: “GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models”. GLASS generates images by sampling stochastic Markov transitions with ODEs - allowing us to boost text-image alignment for large-scale models at inference time!

https://t.co/unsuG3mYer
[1/7]

[Ron Shprints @RShprints]

@TrevorCampbell_ @AllThingsApx Nah it's definitely the Kendall Square Cava

[Ron Shprints @RShprints]

@y0b1byte How are you using cursor with your setup?

[Zavain Dar @zavaindar]

a few months ago we @_DimensionCap quietly funded a team of 3 MIT computer scientists & mathematicians at the forefront of ML & physics+simulation for enzyme design. these. guys. are. cracked

today they're stealthily building the early team. if you're world class, look below 👇

[Ron Shprints @RShprints]

@GeminiApp @Noahpinion

[Ron Shprints @RShprints]

@dvruette Wdym by poor shuffling in the data loader? Ordering is similar to the original dataset?

[Yael Vinker🎗 @YVinker]

Thanks @MIT_CSAIL for featuring our work!🖊️🎨
Huge thanks to the CSAIL news team for the fun article + video!!

We'll be presenting SketchAgent at #CVPR2025 next week — come say hi if you're curious how LLMs can be used to collaboratively sketch!🖌️
👉 https://t.co/skkwpw7pVF