MENU

Fun & Interesting

Xidong Feng - Large Language Models from the view of Reinforcement Learning

JumpTrading ELLIS UCL CSML Seminar Series 782 lượt xem 1 week ago
Video Not Working? Fix It Now

Xidong Feng, a research scientist at Google DeepMind, explores the intersection of Reinforcement Learning (RL) and LLMs, examining how RL has shaped the development of current LLMs and envisioning its transformative potential in training next-generation models.

The UCL ELLIS CSML seminar 2024-2025 is kindly supported by Jump Trading.

Comment