csmisko Profile Banner
Misko Profile
Misko

@csmisko

Followers
342
Following
6K
Media
257
Statuses
1K

FAIR, Atomwise, PetBot, Petcube, Freenome. On the side, shitty kitty, Vanlife, catforceone and all the DIY

San Francisco, CA
Joined July 2012
Don't wanna be here? Send us removal request.
@csmisko
Misko
1 month
Unsinkable Sam 🐈‍⬛ He survived three WWII ship sinkings: the Bismarck, HMS Cossack, and HMS Ark Royal. Both sides, three ships, nine lives. Basically the toughest cat in history.
0
0
0
@csmisko
Misko
3 months
@grok I CAN SEE THE SPONGE!
0
0
0
@csmisko
Misko
3 months
@grok common!
2
0
0
@csmisko
Misko
3 months
I had high hopes for ChatGPT 5 on the cheese benchmark… turns out it’s just full of holes. - GPT5 I can see the sponge!! 😂
@csmisko
Misko
1 year
I woke up this morning, inspired to try the cheese benchmark again.
1
0
1
@AIatMeta
AI at Meta
3 months
2️⃣ We’re also releasing the Open Molecular Crystals (OMC25) dataset, comprised of 25 million structures, that was created to enable the FastCSP workflow. Read the paper: https://t.co/G8SX27serA Find the dataset: https://t.co/vySGNOhJZv We’re excited to share these advances,
Tweet card summary image
huggingface.co
9
11
65
@csmisko
Misko
3 months
A workflow to generate stable crystal structures, fast! ⚡ Excited to see this out! an awesome application of UMA 🤩
@AIatMeta
AI at Meta
3 months
The Meta FAIR Chemistry team continues to make meaningful strides. 1️⃣ Today we’re announcing FastCSP, a workflow that generates stable crystal structures for organic molecules. This accelerates material discovery efforts and cuts down the time to design molecular crystals from
0
0
3
@AIatMeta
AI at Meta
3 months
The Meta FAIR Chemistry team continues to make meaningful strides. 1️⃣ Today we’re announcing FastCSP, a workflow that generates stable crystal structures for organic molecules. This accelerates material discovery efforts and cuts down the time to design molecular crystals from
34
88
402
@thefourthlawai
The Fourth Law
4 months
Big news from The Fourth Law: our first round of funding, products introduction, and the first-ever video of AI terminal guidance for FPVs in massive use in the battlefield. https://t.co/SRJC3YuraU #TFL #autonomy #AI #FPV #Lypunis #TFL1 1/
1
2
8
@zackulissi
Zack Ulissi
4 months
uma-s-1.1 is now live in the UMA educational demo! https://t.co/FZOQqIM8i0 The demo featured in two tutorials recently - one at NAM by @johnkitchin and one at LBL by Jagriti Sahoo! We also added some new tutorials on fine-tuning and DAC applications to
facebook-fairchem-uma-demo.hf.space
@bwood_m
Brandon Wood
4 months
🚀Exciting news! We are releasing new UMA-1.1 models (Small and Medium) today and the UMA paper is now on arxiv! UMA represents a step-change in what’s possible with a single machine learning interatomic potential (short overview in the post below). The goal was to make a model
2
8
28
@csmisko
Misko
4 months
Everyday I feel so fortunate to work as part of the amazing FAIR Chemistry team 🤩🤩🤩 @metaai 💙💙💙
1
0
4
@csmisko
Misko
4 months
LLMs are crowded. GNNs for atoms? Just getting started ⚛️ UMA 1.1 is out — a universal MLIP for real-world chemistry, biology, and materials. High-accuracy. Open-source. Huge open field. It feels like AlexNet days. One GPU, one idea = real impact that can change the world!🌎
@bwood_m
Brandon Wood
4 months
🚀Exciting news! We are releasing new UMA-1.1 models (Small and Medium) today and the UMA paper is now on arxiv! UMA represents a step-change in what’s possible with a single machine learning interatomic potential (short overview in the post below). The goal was to make a model
1
5
21
@bwood_m
Brandon Wood
4 months
🚀Exciting news! We are releasing new UMA-1.1 models (Small and Medium) today and the UMA paper is now on arxiv! UMA represents a step-change in what’s possible with a single machine learning interatomic potential (short overview in the post below). The goal was to make a model
2
27
124
@Sammy_Sidhu
Sammy Sidhu
4 months
Today we're announcing that Eventual has raised $30M in Seed and Series A funding from @CRV and @felicis as well as @ycombinator, @M12vc and @Citi and others. The AI era needs data infrastructure built for AI, not retrofitted. 🧵
46
44
167
@ClementDelangue
clem 🤗
5 months
We're starting to see more and more AI for chemistry and biology which I'm super excited about given the potential for good! @AIatMeta just released OMol25 on @huggingface, a dataset of 𝟭𝟬𝟬𝗠+ 𝗺𝗼𝗹𝗲𝗰𝘂𝗹𝗮𝗿 𝗰𝗼𝗻𝗳𝗼𝗿𝗺𝗲𝗿𝘀 spanning 83 elements and diverse chemical
8
37
167
@bwood_m
Brandon Wood
6 months
We released the Open Molecules 2025 (OMol25) Dataset last week! 🚀🧪 OMol25 is a large (100M+) and diverse molecular DFT dataset for training machine learning models. It was a massive collaborative and interdisciplinary effort and I’m super proud of the whole team! 🙌 1/7
2
22
107
@csmisko
Misko
6 months
6 BILLION CPU core hours to generate open molecules DFT dataset! Along with UMA models that perform across domains! I am very excited and proud to be part of the amazing FAIRChem team @AIatMeta . I can’t wait to see how this open source release will be used by the community!
@mshuaibii
Muhammed Shuaibi
6 months
Excited to share our latest releases to the FAIR Chemistry’s family of open datasets and models: OMol25 and UMA! @AIatMeta @OpenCatalyst OMol25: https://t.co/UhIDiFFzzN UMA: https://t.co/eQ2wPIxbxY Blog: https://t.co/VFaeynyZN7 Demo: https://t.co/Dj29ZfhBRO
1
2
11
@chaitjo
Chaitanya K. Joshi
8 months
Introducing All-atom Diffusion Transformers — towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team @OpenCatalyst @AIatMeta There are a couple ML ideas which I think are new and exciting in here 👇
4
106
529
@xiangfu_ml
Xiang Fu
9 months
For existing MLIPs, lower test errors do not always translate to better performance in downstream tasks. We bridge this gap by proposing eSEN -- SOTA performance on compliant Matbench-Discovery (F1 0.831, κSRME 0.321) and phonon prediction. https://t.co/rzpjGm32QL 1/6
Tweet card summary image
arxiv.org
Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors...
7
24
98
@mshuaibii
Muhammed Shuaibi
1 year
Excited to be part of this release! How we connect computational models to real experiments is essential to making real world impact. Here we introduce OCx24 as a first step to what it would take to bridge this gap and make it a reality. Paper:
Tweet card summary image
arxiv.org
The search for low-cost, durable, and effective catalysts is essential for green hydrogen production and carbon dioxide upcycling to help in the mitigation of climate change. Discovery of new...
@jehad__abed
Jehad Abed
1 year
OCx24 bridges the gap between computational models and experimental results with a dataset of diverse materials, featuring both positive and negative outcomes, tested under industrial conditions. We focus on metal alloy nanoparticles, requiring precise synthesis control.
0
6
22
@jehad__abed
Jehad Abed
1 year
Excited to unveil OCx24, a two-year effort with @UofT and @VSParticle! We've synthesized and tested in the lab hundreds of metal alloys for catalysis. With 685 million AI-accelerated simulations, we analyzed 20,000 materials to try and bridge simulation and reality. Paper:
Tweet card summary image
arxiv.org
The search for low-cost, durable, and effective catalysts is essential for green hydrogen production and carbon dioxide upcycling to help in the mitigation of climate change. Discovery of new...
9
23
108