sri

RLXF is on @biorxivpreprint! We introduce a PPO-based workflow to align the logits of any protein language model away from evolutionary plausibility and towards biochemical function. Not only does this seem to be more robust than other preference optimization methods... (1/3)

Proud to introduce Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant RL algorithm that powers the large-scale RL training of the latest Qwen3 models (Instruct, Coder, Thinking) 🚀 📄 huggingface.co/papers/2507.18…

thrilled to share The Dayhoff Atlas of protein language data and models 🚀 protein biology in the age of AI! aka.ms/dayhoff/prepri… we built + open source the largest natural protein dataset, w/ 3.3 billion seqs & a first-in-class dataset of structure-based synthetic proteins

last couple days: La-Proteina ATOMICA BioScore Metalorian AMix-1 SO(3)-DiT EZPred AlphaFlex Ibex yet we still don't have a standard eval framework for these generative models that allows ppl to identify which is optimal for their task. are ppl just picking models off vibes?

AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model 1. The study introduces AMix-1, a powerful protein foundation model built on Bayesian Flow Networks. It is designed with a systematic training methodology that includes pretraining scaling laws, emergent capability…

Next Tues (7/1) at 4PM ET, @NathanielBlalo2 and @srivsesh will present "Functional alignment of protein language models via reinforcement learning" Paper: biorxiv.org/content/10.110… This will be followed by @WengongJin, who will give an early-career talk on Wed (7/2) at 4PM ET!

lebron lost to jokic in '23 and invented grouped-query attn during the offseason -- goat

I'm thoroughly enjoying challenging Biomni with open-ended multi-step analyses to see what type of plan it prepares, how well it can execute that plan, and how the plan is revised as various steps succeed and fail. I haven't tested it enough yet to comment on overall accuracy.

Introducing the world's first reasoning model in biology! 🧬 BioReason enables AI to reason about genomics like a biology expert. A thread 🧵:

🤯 We cracked RLVR with... Random Rewards?! Training Qwen2.5-Math-7B with our Spurious Rewards improved MATH-500 by: - Random rewards: +21% - Incorrect rewards: +25% - (FYI) Ground-truth rewards: + 28.8% How could this even work⁉️ Here's why: 🧵 Blogpost: tinyurl.com/spurious-rewar…

implemented this yday due to repeated OOM issues on an L40S -- game changer arxiv.org/abs/2407.07265

First Lab Validation for Reasoning Model Proteins With @adaptyvbio, we tested 19 FGF-1 sequences optimized by Pro-1 for thermal stability and binding affinity to human FGFR-1. Pro-1 produced 3 novel sequences that maintained binding affinity and expression compared to wild…

i told my grandfather i’d be at the @GordonConf for Protein Engineering in a couple months and he sent me this from 1972. smartest man i know to this day

would love if this was open sourced but nonetheless, inference time scaling for antibody design (inhibitory & activating) with wet lab data? based

guys this is real time

imagine signing up for a comp and your timid nature dragonite gets one shotted by an offline rl algorithm lol openreview.net/forum?id=b1BaJ…

i had 4o generate me a picture of a scientific poster for our recent paper and the result is pretty cool imo