Advanced mathematical reasoning is a critical capability for modern AI. Today we announce a major milestone in a longstanding grand challenge: our hybrid AI system attained the equivalent of a silver medal at this year’s International Math Olympiad!

Yep ! We trained eyeballs from scratch, starting with just light-detecting photoreceptors. 🔬👁️ Why? To simulate vision evolution in-silico and understand why we perceive the world the way we do. 🌍✨ Check it out: eyes.mit.edu

With infinite compute, would it make a difference to use Transformers, RNNs, or even vanilla Feedforward nets? They’re all universal approximators after all. We prove that Yes! You end up with different sample complexity, no matter how much compute/memory you have.👇

I'll be presenting Policy-Agnostic RL: Fine-Tuning of Any Policy Class and Backbone at the Robot Learning (Sunday) and GenBot (Monday) workshops as Orals at #ICLR2025! Happy to chat or meet!

I am excited to give an oral talk on our work about “Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning” at #ICLR2025 FM-Wild Workshop! 🚀 📍Hall 4 #6 🕚11:30AM, April 27th 🖥️Can’t be there in person, but chat with Ian Wu who’ll present our poster after the talk!

At #ICLR25 workshops, my students+collabs will give many orals talks on newer stuff (don't miss!): - robot VLA RL fine-tuning Max Sobol Mark - optimizing test-time compute Yuxiao Qu - why RL is crucial for test-time scaling Amrith Setlur - scaling laws for value-based RL

RL with verifiable reward has shown impressive results in improving LLM reasoning, but what can we do when we do not have ground truth answers? Introducing Self-Rewarding Training (SRT): where language models provide their own reward for RL training! 🧵 1/n

Spectacular performance by the Indian team at the International Mathematical Olympiad 2025 held at Sunshine Coast, Australia from Jul 10-21, winning 3 Gold, 2 Silver and 1 Bronze! Congratulations Team India you make the nation proud!! #IMO2025, #Matholympiad.