2/ Meta's commitment to FAIR & research is unwavering. We're working towards building human-level experiences that transform technology & are dedicated to advancing AI research.
1/ Excited to share that I’m taking on the role of leading Fundamental AI Research (FAIR) at Meta. Huge thanks to Joelle for everything. Look forward to working closely again with Yann & team.
@ylecun@ylecun@AravSrinivas recent Proto-RL (https://t.co/EQQk8j0RzA) that uses ideas from both CURL and DrQ gets us closer to the LeCake, as it's contrastively learned representations are **fully detached** from RL, besides they can be learned with just the MaxEnt objective.
Happy to share my new work -- Proto-RL, a task-agnostic pre-training scheme that reconciles exploration and representation learning in image-based RL!
with: @rob_fergus, Alessandro Lazaric, and @LerrelPinto.
paper: https://t.co/EQQk8j0RzA
code: https://t.co/apgFW0h3c2
[1/N]
Excited to share an update to our work on evolutionary-scale modeling (ESM)! Over the past year, we rewrote our paper with better pretraining and downstream models, leading to state-of-the-art results across multiple benchmarks. (1/8)
https://t.co/jQ4NbJRtqj
Excited to share our new paper “Automatic Data Augmentation for Generalization in Deep Reinforcement Learning” w/ @maxagoldstein8, @denisyarats, @ikostrikov, and @rob_fergus!
Paper: https://t.co/Q72UMXRuqh
Code: https://t.co/7xhdL6O8qN
Website: https://t.co/aTQTux7oOt
@koraykv @DeepMind @koraykv@demishassabis Thanks for the warm welcome - excited to be working with you both and look forward to getting to know the rest of the team!
Exciting to announce our new work together with @ikostrikov and @rob_fergus: Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels.
Paper: https://t.co/pqEkc8PzFI
Code: https://t.co/FNRZ8QWc21
Website: https://t.co/mjfT8heDt6
[1/N]