Papers2

#activation quantization

An Empirical Study of World Model Quantization

Zhongqian Fu, Tianyi Zhao et al.Feb 2arXiv

World models are AI tools that imagine the future so a robot can plan what to do next, but they are expensive to run many times in a row.

#world models#post-training quantization#DINO-WM

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Intermediate

Haocheng Xi, Charlie Ruan et al.Jan 20arXiv

Reinforcement learning (RL) for large language models is slow because the rollout (text generation) stage can take more than 70% of training time, especially for long, step-by-step answers.

#FP8 quantization#on-policy reinforcement learning#precision flow