autogaze-efficient-video-understanding

Reduce video token overhead by 4-100x through autoregressive patch selection, enabling MLLMs to process 1K-frame 4K video efficiently. Uses next-token prediction to identify multi-scale patches that matter. Achieves 19x speedup on vision transformers. Use when processing long, high-resolution videos with MLLMs, have budget constraints on tokens/compute, or …

Independent GitHub snapshot · Automated classification · Original documentation governs