Sulin Liu

Excited to head to NeurIPS next Tuesday! 🚀
Been into adaptive planning and self-correction in generation (for discrete diffusion/autoregressive) and adaptive agentic AI for complex problems in science and eng.
Hit me up! 🙌Would love to connect, chat and hear what you are excited about🤝🫶 #NeurIPS2024

A common question nowadays: Which is better, diffusion or flow matching? 🤔

Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.

Interesting thread! We tried training a neural network to do arbitrary approximate marginalization in arxiv.org/abs/2310.12920, and surprisingly NN does a decent job approximating it. Enforcing strict normalization is hard, but it's pretty good at the level of comparing logps of things.

I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!

go.bsky.app/AcP9Lix

The first list filled up, so here's a second list of AI for Science researchers on bluesky.

Let me know if I missed you / if you'd like to join!

bsky.app/starter-pack...

Several incredible NeurIPS tutorials this year. Worth navigating through the Swifties.

Started a second AI Science Connect pack. Let's keep building the community. It's been really amazing to see the great AI for science conversations over the past week.

Please self nominate, or send me others who should be added!

Pack 2: go.bsky.app/GnFTUM6
Pack 1 (full): go.bsky.app/JeFdryY

GitHub - kuleshov-group/awesome-discrete-diffusion-models: A curated list for awesome discrete diffusion models resources. A curated list for awesome discrete diffusion models resources. - kuleshov-group/awesome-discrete-diffusion-models

Discrete diffusion has become a very hot topic again this year. Dozens of interesting ICLR submissions and some exciting attempts at scaling. Here's a bibliography on the topic from the Kuleshov group (my open office neighbors).

github.com/kuleshov-gro...

🙋 I work in discrete generative models, discrete diffusion with planning and flow matching for science applications.

Yes! I commute between Boston and NYC weekly.

🙋thank you!!

Would love to be added too!

I made a starter pack for Bayesian ML and stats (mostly to see how this starter pack business works).

Let me know whom I missed!

go.bsky.app/2Bqtn6T

I made a starter pack for researchers in probabilistic machine learning.

DM/reply if you want to be added!

go.bsky.app/DuCtJqC

Would love to be added too!