ML Scientist

Connecting Scholars with the Latest Academic News and Career Paths

FeaturedNews

BeNeRL Seminar: Anikait Singh on Scalable RL for LLM Post-Training

Join the BeNeRL Seminar on June 12, where Anikait Singh will discuss scalable RL for LLM post-training, covering algorithms and design decisions for Foundation Models.

Join the BeNeRL Reinforcement Learning Seminar on June 12, where Anikait Singh from Stanford University will discuss ‘Towards Scalable RL Machinery for LLM Post-Training’.

Key details:

Abstract: The talk will cover design decisions for pairing effective priors and algorithmic research in RL for Foundation Models, including algorithms for preference-based fine-tuning and discovering abstractions.

Tags: Reinforcement Learning, BeNeRL Seminar, Scalable RL, LLM Post-Training, Anikait Singh, Stanford University, AI Research