# Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model

> Source: <https://aiflash.com/news/119506/>
> Published: 2026-09-14 15:30:01+00:00

We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2B parameter division with 0.8279 on the held-out test set. Our system is a single 2B vision-language model that answers multiple-choice questions about ten-minute egocentric videos in