Juan Agustin Duque
@juanduquevan.bsky.social
PhD student in Reinforcement Learning (MILA)
Very happy to have been a part of this project, the result of a very good collaboration with WhiRL and Flair at Oxford.
Introducing 🥚EGGROLL 🥚(Evolution Guided General Optimization via Low-rank Learning)! 🚀 Scaling backprop-free Evolution Strategies (ES) for billion-parameter models at large population sizes
⚡100x Training Throughput
🎯Fast Convergence
🔢Pure Int8 Pretraining of RNN LLMs
⚡100x Training Throughput
🎯Fast Convergence
🔢Pure Int8 Pretraining of RNN LLMs
November 21, 2025 at 6:20 PM
Very happy to have been a part of this project, the result of a very good collaboration with WhiRL and Flair at Oxford.