Tati's Wonderland

Кстати, сейчас в bay area проходит mooc курс Advanced LLM agents
с лекциями на youtube, которые могут смотреть все (как мы любим, без регистрации и смс).

Сегодня как раз одна такая лекция "Learning to Self-Improve & Reason with LLMs", 4pm SF time, но посмотреть можно и потом. Они часто начинают позднее.

Перепосчу.
Our 2nd lecture will be happening today @4:00pm PST! You can find the livestream here: https://www.youtube.com/live/_MNlLhU33H0. 

Today, our amazing guest speaker Jason Weston will be presenting, "Learning to Self-Improve & Reason with LLMs."

We describe some recent methods for LLMs whereby they can self-learn how to perform better at tasks relevant to human users, from reasoning or math tasks to creative tasks. In particular we describe the methods of Iterative DPO (https://arxiv.org/abs/2312.16682), Self-Rewarding LLMs (https://arxiv.org/abs/2401.10020), Iterative Reasoning Preference Optimization (https://arxiv.org/abs/2404.19733),  Thinking LLMs (https://arxiv.org/abs/2410.10630), Meta-Rewarding LLMs (https://arxiv.org/abs/2407.19594), and more! 

YouTube

CS 194/294-280 (Advanced LLM Agents) - Lecture 2, Jason Weston

www.group-telegram.com/ye/tatiwonderland.com/68

1.2K viewsTanya, edited  Feb 3 at 17:59

Кстати, сейчас в bay area проходит mooc курс Advanced LLM agents
с лекциями на youtube, которые могут смотреть все (как мы любим, без регистрации и смс).

Сегодня как раз одна такая лекция "Learning to Self-Improve & Reason with LLMs", 4pm SF time, но посмотреть можно и потом. Они часто начинают позднее.

Перепосчу.
Our 2nd lecture will be happening today @4:00pm PST! You can find the livestream here: https://www.youtube.com/live/_MNlLhU33H0. 

Today, our amazing guest speaker Jason Weston will be presenting, "Learning to Self-Improve & Reason with LLMs."

We describe some recent methods for LLMs whereby they can self-learn how to perform better at tasks relevant to human users, from reasoning or math tasks to creative tasks. In particular we describe the methods of Iterative DPO (https://arxiv.org/abs/2312.16682), Self-Rewarding LLMs (https://arxiv.org/abs/2401.10020), Iterative Reasoning Preference Optimization (https://arxiv.org/abs/2404.19733),  Thinking LLMs (https://arxiv.org/abs/2410.10630), Meta-Rewarding LLMs (https://arxiv.org/abs/2407.19594), and more! 

BY Tati's Wonderland