Danylo Baibak
@danilbaibak
Machine learning engineer, open-source enthusiast
ID: 975916428
https://github.com/DanilBaibak 28-11-2012 11:27:16
529 Tweet
157 Followers
221 Following
#MetaResearch presented Controllable Agent: RL agent whose reward function can be set in real time, without any further learning or fine-tuning, based on a reward-free pretraining phase #ReinforcementLearning #AI #ML Demo: controllable-agent.metademolab.com GitHub: github.com/facebookresear…
Token Merging: Your ViT but faster - AI at Meta is sharing new research to reduce the latency of existing Vision Transformer models without the need for additional training #ComputerVision #DeepLearning #AI GitHub: github.com/facebookresear… Paper: arxiv.org/abs/2210.09461