🔥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

If you're interested in running Orb-v3 but don't want to build your own computational stack, try Rowan! Orb-v3 should go live for all Rowan users in 30–45 minutes. We hope to run this model through our own set of benchmarks within the next week or so—stay tuned!

Orb-v3 is now live for all Rowan users! Here's a video of me optimizing a 1H-pyrazole crystal structure w/ Orb-v3 (a task that might take many hours with DFT). (video lightly edited and sped up, because your time is valuable!)

These out of domain evaluations (at least for Orb-v3, trained on bulk periodic materials) look very promising - great to see this type of generalization, and very nice that we can compare across different functionals. Onward and up (the DFT ladder)! Check them out on Rowan

New blog post: let's talk about latents! sander.ai/2025/04/15/lat…

Fixed it: --> last year, the U.S. sold more educational services to the rest of the world than it sold in natural gas and coal **combined** --> every $1 of research funded by NIH generates $2.56 in economic activity --> more than 1.1M foreign students come to the U.S. each year

I'm excited to announce the release of the Egret-1 family of neural network potentials (NNPs) at Rowan! These models approach or exceed DFT accuracy for energies and forces on bioorganic molecules and are 2–6 orders of magnitude faster (depending on system size). 🧵1/6

Does anyone know of any papers which analyse what happens if you train a latent diffusion model on a VAE or VQVAE with no bottleneck? I am interested to know what happens in the circumstance that your VAE has a degenerate latent space.

Delighted to see our paper published: CHIPS-FF: Evaluating Universal Machine Learning Force Fields for Material Properties pubs.acs.org/doi/10.1021/ac… #CHIPSact #jarvisnist #mlff

Small step toward justice for Rümeysa Öztürk Glad to see the judicial branch of govt (barely) keeping the executive in check in these unbelievable cases theguardian.com/us-news/2025/m…

Very nice dataset! Congrats.

x.com/AnthropicAI/st…

Tomorrow Tim Duignan joins us to discuss "Orb-v3: atomistic simulation at scale" arxiv.org/abs/2504.06231 and surrounding models to get our understanding of that field up to date! On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

just walked by ICE but i was wearing slim chinos and dress sneakers so they suspected nothing

In the future anthropologists will study how Dishoom invaded the American cultural psyche, absolutely fascinating - literally every other American visiting London will tell you they want to go Dishoom is fine, but please visit Tayyabs or Lahore Kebab House instead/ as well

Very cool paper (almost directly refuting a blog post I recently wrote about people not training conservative diffusion models). Would love to know if this scales, would be super cool if it does

Announcing Ambient Diffusion Omni — a framework that uses synthetic, low-quality, and out-of-distribution data to improve diffusion models. State-of-the-art ImageNet performance. A strong text-to-image results in just 2 days on 8 GPUs. Filtering ❌ Clever data use ✅