Tati's Wonderland | Telegram Webview: tatiwonderland/68 -

Telegram Group & Telegram Channel

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!

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

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

1.2K viewsTanya, edited Feb 3 at 17:59

group-telegram.com/tatiwonderland/68

Create: 2025-02-03
Last Update: 2025-02-15 07:38:26

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

Share with your friend now:
group-telegram.com/tatiwonderland/68

Open in Telegram

Telegram | DID YOU KNOW?

Date: 2025-02-15|

What distinguishes the app from competitors is its use of what's known as channels: Public or private feeds of photos and videos that can be set up by one person or an organization. The channels have become popular with on-the-ground journalists, aid workers and Ukrainian President Volodymyr Zelenskyy, who broadcasts on a Telegram channel. The channels can be followed by an unlimited number of people. Unlike Facebook, Twitter and other popular social networks, there is no advertising on Telegram and the flow of information is not driven by an algorithm. A Russian Telegram channel with over 700,000 followers is spreading disinformation about Russia's invasion of Ukraine under the guise of providing "objective information" and fact-checking fake news. Its influence extends beyond the platform, with major Russian publications, government officials, and journalists citing the page's posts. Ukrainian forces successfully attacked Russian vehicles in the capital city of Kyiv thanks to a public tip made through the encrypted messaging app Telegram, Ukraine's top law-enforcement agency said on Tuesday. "The result is on this photo: fiery 'greetings' to the invaders," the Security Service of Ukraine wrote alongside a photo showing several military vehicles among plumes of black smoke. "Someone posing as a Ukrainian citizen just joins the chat and starts spreading misinformation, or gathers data, like the location of shelters," Tsekhanovska said, noting how false messages have urged Ukrainians to turn off their phones at a specific time of night, citing cybersafety.
from us

Telegram Tati's Wonderland
FROM American