{"slug": "ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model", "title": "Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model", "summary": "A single 2B-parameter vision-language model placed first in the ≤2B parameter division of the EgoLongQA track of the Wearable-AI Challenge at ECCV 2026, scoring 0.8279 on the held-out test set. The system, described by its developers, answers multiple-choice questions about ten-minute egocentric videos.", "body_md": "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", "url": "https://wpnews.pro/news/ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model", "canonical_source": "https://aiflash.com/news/119506/", "published_at": "2026-09-14 15:30:01+00:00", "updated_at": "2026-09-14 15:55:20.437115+00:00", "lang": "en", "topics": ["computer-vision", "large-language-models", "ai-research", "ai-products"], "entities": ["EgoLongQA", "Wearable-AI Challenge", "ECCV 2026"], "alternates": {"html": "https://wpnews.pro/news/ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model", "markdown": "https://wpnews.pro/news/ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model.md", "text": "https://wpnews.pro/news/ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model.txt", "jsonld": "https://wpnews.pro/news/ambient-egolongqa-2026-distilling-long-video-perception-into-a-sub-2b-model.jsonld"}}