Less is more: UC Berkeley and Google unlock LLM potential through simple sampling
The current popular method for test-time scaling in LLMs is to train the model through reinforcement learning to generate longer responses with chain-of-thought (CoT) traces. This approach is used in ...
METASCALE improves LLM reasoning with adaptive strategies
A new framework called METASCALE enables large language models (LLMs) to dynamically adapt their reasoning mode at inference time. This framework addresses one of LLMs’ shortcomings, which is using ...
Fast Company1mon
Curious about DeepSeek but worried about privacy? These apps let you use an LLM without the internet
With the apps, you can run various LLM models on your computer directly. I’ve spent the last week playing around with these apps and thanks to each, I can now use DeepSeek without the privacy ...
ByteDance advances DeepSeek work in AI reasoning with open-source project led by intern
DAPO is a scalable reinforcement learning algorithm that helps a large language model achieve better complex reasoning ...