🔥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

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Can't believe it's been just over a year after the first study from my PhD came out, and it's still the most read at Cancer Research Communications 😲 Needed to see this working on the final paper, instead of being at the flower market on this beautiful day 🌞😿 oh also ordering these helped too 💐

Scrubbed into the OR with Subodh Verma on Father’s Day. I asked what the day means to him. He said: “Provide, protect, be present, and lead by example.” Simple, powerful - just like the work he does every day. Brantley Gilbert Marc Gillinov bobby yanagawa Dr. Deepak L. Bhatt #FathersDay

🚀 What do genomic Transformers actually learn about biology? •What knowledge do they hold at random init, after pre‑training, and following fine‑tuning? •We dove deep into every attention head to find out. 📄 Preprint live now “Interpreting Attention Mechanisms in Genomic

Sunday summer market days 💖💐

ok LOVE. we need more of this kind of dialogue! Karen offers refreshing takes on underdiscussed issues of AI—the arms race, climate impact, monopolies, ideological divide, leadership values, and how the chase (💰💪) erodes principles & change missions youtu.be/8enXRDlWguU?si…

So great to see pioneers in education like Salman Khan shaping the future of AI education with accessibility and safety guardrails in mind, i remember how much i learned from his videos growing up 🥲🧑‍🏫nbcnews.com/meet-the-press… via @nbcnews

📢 LLMs can perform autonomous surgery! SRT-H is the first vision-language-action (VLA) model to perform procedure-level autonomous robotic surgery 🧵

The opportunity gap in AI is more striking than ever. We talk way too much about those receiving $100M or whatever for their jobs, but not enough those asking for <$1k to present their work. For 3rd year in a row, ML Collective is raising funds to support Deep Learning Indaba attendees.

Multiomic Landscape of Extracellular Vesicles in Human Carotid Atherosclerotic Plaque Reveals Endothelial Communication Networks | Arteriosclerosis, Thrombosis, and Vascular Biology CONGRATS ⁦Sneha Raju⁩ and thank you ⁦ATVB: An AHA Journal⁩ ahajournals.org/doi/10.1161/AT…

Check out this highly collaborative work with Elena Aikawa Jason Fish Valli Subasri Ulf Hedin and more! We liberated extracellular vesicles from carotid plaques and adjacent tissue. Predicted cell of origin and communication networks through proteomics and microRNA sequencing.

Can an AI model predict perfectly and still have a terrible world model? What would that even mean? Our new ICML paper formalizes these questions One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵

Scaling up RL is all the rage right now, I had a chat with a friend about it yesterday. I'm fairly certain RL will continue to yield more intermediate gains, but I also don't expect it to be the full story. RL is basically "hey this happened to go well (/poorly), let me slightly

*Easter egg alert* NOT in the published paper. We also benchmarked Evo 2 and while it did better than other gLMs (consistent that scale can improve gLMs), it still falls short of a basic CNN trained using one-hot sequences and far short of supervised SOTA x.com/pkoo562/status…

For biological data, if you don't have deep expertise in this low value work called data cleaning, u r lacking a fundamental understanding of the idiosyncrasies of the data. Without this knowledge, it is impossible to seriously model data.

By flipping an evolutionarily disabled genetic switch involved in Vitamin A metabolism, researchers in Science have enabled ear tissue regeneration in mice. Learn more: scim.ag/44muTVr

Thrilled to share that we placed 1st in the 2025 MEDIQA Clinical NLP Challenge — marking our third consecutive win (2023, 2024, 2025)! 🏆🎉 This year’s task went beyond clinical note generation — it focused on extracting structured medical orders from noisy, free-form

Writing = Thinking Don't outsource it to AI

⚡️Thrilled that #VirtualLab is published in nature! nature.com/articles/s4158… We created a team of AI agents to mirror my Stanford lab🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.

🚨NOW LIVE: my uncle is hosting an (elective, but not so elective) talk on AI evolution trends & future 🤖 no he does not work on AI professionally, this is just for “fun” 😆 the reach of AI is incredible, but also terrifying…