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/es/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 12:13:48

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?

What is Telegram?

Telegram’s stand out feature is its encryption scheme that keeps messages and media secure in transit. The scheme is known as MTProto and is based on 256-bit AES encryption, RSA encryption, and Diffie-Hellman key exchange. The result of this complicated and technical-sounding jargon? A messaging service that claims to keep your data safe.Why do we say claims? When dealing with security, you always want to leave room for scrutiny, and a few cryptography experts have criticized the system. Overall, any level of encryption is better than none, but a level of discretion should always be observed with any online connected system, even Telegram.

The lead from Wall Street offers little clarity as the major averages opened lower on Friday and then bounced back and forth across the unchanged line, finally finishing mixed and little changed.The Dow added 33.18 points or 0.10 percent to finish at 34,798.00, while the NASDAQ eased 4.54 points or 0.03 percent to close at 15,047.70 and the S&P 500 rose 6.50 points or 0.15 percent to end at 4,455.48. For the week, the Dow rose 0.6 percent, the NASDAQ added 0.1 percent and the S&P gained 0.5 percent.The lackluster performance on Wall Street came on uncertainty about the outlook for the markets following recent volatility.