This repository is the official implementation of Helios, which is a breakthrough video generation model that achieves minute-scale, high-quality video synthesis at 19.5 FPS on a single H100 GPU ...
Our concrete goal: take Qwen2.5-0.5B-Instruct and make it better at solving grade-school math word problems (GSM8K) using only a reward signal that checks whether the final answer is correct.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results