🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The same reason we're seeing less of RL and proxy rewards in AI for science. We're able to somewhat deal with this by 'restricting' the generator through physical constraints, or 'expanding' the proxy reward through active learning. Surprised it even works on unconstrained LLMs!

😍 Our work on the “Chemical-motif characterization of short-range order with E(3)-equivariant graph neural networks” has been published in Nature - npj Computational Materials npj Journals 😍 Check out the findings in our paper here: nature.com/articles/s4152…

Discrete generative models use denoisers for generation, but they can slip up. What if generation *isn’t only* about denoising?🤔 Introducing DDPD: Discrete Diffusion with Planned Denoising🤗🧵(1/11) w/ Juno Nam Andrew Campbell Hannes Stärk Yilun Xu Tommi Jaakkola RGB Lab @ MIT

arxiv.org/abs/2410.06264 The one represented by this paper is a nice direction imho Generative models for sure need more decision-making in the generation/denoising process, and this is a possible strategy towards that I think/hope many more papers like this will come soon!

Our paper on RL for proposing inorganic materials is now published in npj Computational Materials. We compare policy- and value-based RL approaches, and demonstrate their applications in multi-objective optimization to identify promising candidates. nature.com/articles/s4152…

Thrilled to share my recent work with Sergey Ovchinnikov, Gabriel Rocklin, Kotaro Tsuboyama, and Justas Dauparas: biorxiv.org/content/10.110… (1/9)

Out now in Journal of Vision! Measuring inference-time compute capability in neural networks (and humans) before it was cool 😎 doi.org/10.1167/jov.25…

Really happy to have been on the team while this was going on. Also excited about what it means for sampling! Check out the blog post about our work sampling from these models: linkedin.com/posts/aiatmeta…

I want to share my latest (very short) blog post: "Active Learning vs. Data Filtering: Selection vs. Rejection." What is the fundamental difference between active learning and data filtering? Well, obviously, the difference is that: 1/11

Excited to start my research internship this Summer + Fall at Reality Labs at Meta where I'll be working on vision-language models for robotics! If you're in the Seattle-area and would like to meet up, let me know!

Excited to share that I'll be interning with Generate:Biomedicines this Summer, where I'll be working on generative models for proteins! 🧬