Eugene Vinitsky 🍒

eugenevinitsky.bsky.social

07 July 2025 22:06

Still in stealth but our team has grown to 20 and we're still hiring. If you're interested in joining the research frontier of deploying RL+LLM systems, shoot me an email to chat at ICML!

Antonin Raffin

araffin.bsky.social

11 February 2025 08:30

How to compute Hessian-vector products? (for instance used in TRPO, predecessor of PPO) an @iclr-conf.bsky.social 2024 blog post. iclr-blogposts.github.io/2024/blog/be...

AI Conference DL Countdown

dlcountdown.bsky.social

11 February 2025 08:30

RLC'25 (abs): 4 days + 21h. RLC'25 (paper): 11 days. CoLLAs'25 (abs): 11 days. CoLLAs'25 (paper): 16 days. IROS'25: 19 days. ICCV'25: 24 days. CORL'25: 77 days.

Prithviraj "Raj" Ammanabrolu

rajammanabrolu.bsky.social

11 February 2025 08:30

"Agency is Frame Dependant" A work on the philosophy of Reinforcement Learning arxiv.org/abs/2502.04403

Nathan Lambert

natolambert.bsky.social

16 December 2024 22:26

Very real discussions going down on how to improve open source infra for RLHF / post train. Randomly bumped into @johnschulman2 in the comments. TLDR quickly syncing the weights between the learning nodes + the generating node isn't an easy thing to do. https://buff.ly/41AS3Yq