коллеги из университета Циньхуа выпустили работу под названием Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (А точно ли обучение с подкреплением расширяет мыслительные возможности моделей?)в ней они приходят к выводу

This media is not supported in your browser

коллеги из университета Циньхуа выпустили работу под названием Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (А точно ли обучение с подкреплением расширяет мыслительные возможности моделей?)

в ней они приходят к выводу, что нет, базовая модель остается лучше на длинной дистанции; я высказывал такого рода сомнение еще про Qwen, но тут уже полноценное подтверждение; отдельно хочу выразить восхищение визуальным оформлением результатов, очень доходчиво

www.tg-me.com/in/Data Science by ODS ai 🦜/com.opendatascience/2282

3.8K viewsMay 1 at 11:50

tg-me.com/opendatascience/2282

Create: 2025-05-01
Last Update: 2025-06-01 18:17:16

BY Data Science by ODS.ai 🦜

Share with your friend now:
tg-me.com/opendatascience/2282

Data Science by ODS ai 🦜 Telegram | DID YOU KNOW?

Telegram today rolling out an update which brings with it several new features.The update also adds interactive emoji. When you send one of the select animated emoji in chat, you can now tap on it to initiate a full screen animation. The update also adds interactive emoji. When you send one of the select animated emoji in chat, you can now tap on it to initiate a full screen animation. This is then visible to you or anyone else who's also present in chat at the moment. The animations are also accompanied by vibrations. This is then visible to you or anyone else who's also present in chat at the moment. The animations are also accompanied by vibrations.

Telegram Gives Up On Crypto Blockchain Project

Durov said on his Telegram channel today that the two and a half year blockchain and crypto project has been put to sleep. Ironically, after leaving Russia because the government wanted his encryption keys to his social media firm, Durov’s cryptocurrency idea lost steam because of a U.S. court. “The technology we created allowed for an open, free, decentralized exchange of value and ideas. TON had the potential to revolutionize how people store and transfer funds and information,” he wrote on his channel. “Unfortunately, a U.S. court stopped TON from happening.”