AI PhD at @berkeley_ai | ex @GoogleDeepMind | ex @Meta | prev at @UniofOxford
Berkeley, CA
Joined July 2022
- Tweets19
- Following45
- Followers268
- Likes44
Pinned Tweet
AI is changing how we build software.
The next frontier is matter.
Meet CliqueFlowmer: upload a material, optimize its representation, generate a new candidate.
Our demo is live. Our paper is coming to #NeurIPS2026 in #Sydney.
Watch it happen. 🧵
In comparison to materials from MP-20 data, CliqueFlowmer lowered mean formation energy from 0.46 to −0.81 eV/atom.
The updated paper covers the method, experiments, and results—including band-gap optimization.
Read it here:
arxiv.org/pdf/2603.06082
The future we’re chasing:
Describe the properties you need. Design materials with AI—like we build software with it today.
Batteries. Electronics. Catalysts.
From ideas to atoms.
The code is open. Build with us:
github.com/znowu/CliqueFlowm…
#AI
Kuba retweeted
Physical intelligence is the hottest topic recent months.
We are making first shot at accelerating it.
Meet Rake, the Artificial Firmware Engineer.
Harness for programming chips at 10x speed.
rakelabs.ai
Optimize materials yourself! 🔥
No cloning, no install — just open our interactive Google Colab demo and start optimizing crystals for formation energy or band gap in < 2 minutes.
→ Try it here: colab.research.google.com/dr…
→ Or grab the repo + open weights: github.com/znowu/CliqueFlowm… huggingface.co/iamkuba/Cliqu…
3/N All weights are fully open on Hugging Face (including the stronger Alexandria-scale checkpoint we trained with more data than in the paper).
Ready for you to use today — whether you’re doing materials discovery, running your own oracles, or just exploring.
Let us know how you like it and which properties do you want to optimize materials for!
🚀 arXiv: arxiv.org/abs/2603.06082 #AIforScience #MaterialsDiscovery #CompChem
2/N The demo is truly plug-and-play.
Run the cells → your crystal becomes a controlable latent vector.
You can even upload your own structures and navigate them inside the model's imagination - the latent space!
AI can optimize materials 🤘
Our (@pabbeel, @svlevine, @AIatMeta) proposed transformer model 𝗖𝗹𝗶𝗾𝘂𝗲𝗙𝗹𝗼𝘄𝗺𝗲𝗿, combined with 𝗲𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 strategies, discovers materials that optimize target properties.
arxiv.org/abs/2603.06082 – at Berkeley, CA
2/N Code release
We open-source CliqueFlowmer — a full pipeline for offline materials optimization.
Includes:
• training + inference
• latent optimization (evolution strategies)
• decoding to crystal structures
github.com/znowu/CliqueFlowm…
LLMs that learn without data 🤯
No new datasets. No human demos. Just a model playing against itself—getting smarter every round.
We call it Language Self-Play.
Full paper arxiv.org/pdf/2509.07414
Thanks @metaai and @berkeley_ai
"Better than what's known" - the dream of AI in model-based optimization. Excited to present my paper with @pabbeel & @svlevine on Functional Graphical Models (arxiv.org/pdf/2401.05442) giving theoretical foundations for chasing that dream, at @aistats_conf ! #aistats_conf #ai – at Valencia, Spain
Kuba retweeted
Deep RL has been driven by improvements in handcrafted algorithms. Our NeurIPS 2022 paper, “Discovered Policy Optimisation” instead meta-learns in a space of theoretically-sound algorithms and beats PPO on unseen tasks! w/ @kuba_AI @_aletcher @Luke_Metz @casdewitt @j_foerst 🧵
It takes @PiotrTempczyk , my first AI mentor, and his team to make true breakthroughs in ML; presented gloriously in the paper arxiv.org/pdf/2206.14882.pdf at #ICML2022 in the long-talk fashion!