Mathieu Reymond

[Rim @RimShayakhmetov]

Couldn't hold it
our InsilicoMMAI-4B is 1st🥇vs Chemeleon/etc on a separate 14-task ADMET experimental holdout from @InSilicoMeds programs.
🏆Additional test for generalizability under distribution shifts, where it shines the best!
On #DDDBench soon, stay tuned 👀
#insilicoSOTAFM

[Alex Zhavoronkov, PhD (aka Aleksandrs Zavoronkovs) @biogerontology]

🧪 NEW SOTA in chemical synthesis

Building molecules is hard. There are countless possible routes, but only some actually work. We trained a 2.6B LFM model by @liquidAI in #MMAIGym to find them.
📈 +7% vs. the best specialist tool
🚀 +27% vs. frontier LLMs
💥 2.6B punches way above its weight

#insilicoSOTAFM

[Insilico Medicine @InSilicoMeds]

🚀 5 new drug-discovery specialist LLMs. SOTA-level performance across 70+ benchmark tasks.

Insilico Medicine has released a series of frontier Specialist Language Models for chemistry and biology, trained through MMAI Gym.

They cover drug safety, potency prediction, chemical synthesis, and biology.

🧬 From general-purpose models to scientific specialists.

[Mathieu Reymond @mathieu_reymond]

@Max__Kuznetsov Top-K prompting is pretty cool, a related multi-answer idea was even published recently at ICML https://t.co/fmiY2ZpjKi

[Maksim Kuznetsov @Max__Kuznetsov]

I’m excited to share the follow-up paper to our #ChemCensor framework for evaluating single-step retrosynthesis 🧪

Our C3LM model was already competitive with, and in some cases superior to, general-purpose foundation models, but a gap remained between LLMs and conventional retrosynthesis models.

We finally closed and surpassed that gap 🚀

The key ingredients were… 👇

[Insilico Medicine @InSilicoMeds]

Think your foundation model is good at drug discovery?🧪

Prove it on clean data and earn your place on the leaderboard.
Every frontier model is already there. None of them wins everything.

Insilico DDD Benchmark. Submissions are open.
1/ 🧵