Model Releases
Continuous-video agents (computer use, robotics, static scenes) burn compute re-ingesting pixels that didn't move. VLMaxxing teaches a froze…
Continuous-video agents (computer use, robotics, static scenes) burn compute re-ingesting pixels that didn't move. VLMaxxing teaches a frozen video VLM to skip the reruns. 54 fps perception on Gemma 4
Continuous-video agents (computer use, robotics, static scenes) burn compute re-ingesting pixels that didn't move. VLMaxxing teaches a frozen video VLM to skip the reruns. 54 fps perception on Gemma 4 26B, training-free, no accuracy drift. w/ @jfbastien (arXiv 2605.03351) Media
Source: Swyx (X) | 2026-05-06