Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
Ambient team wins EgoLongQA 2026 sub-2B division by distilling an agentic long-video perception pipeline into a 2B vision-language model.
Ambient's entry to the EgoLongQA track of the Wearable-AI Challenge at ECCV 2026 placed first in the <=2B parameter division with 0.8279 on the held-out test set. The system distills the junior perception module of a tool-using agentic pipeline into a 2B student, reaching 89% of the pipeline's accuracy with 1.1% of its parameters and lifting a 27.1% base model to 81.4%. To meet the division limit, the multilingual embedding table is pruned from 248,320 to 143,469 rows, reaching 1.9985B parameters with provably identical logits on retained rows.
- First place in EgoLongQA <=2B division with 0.8279 test score
- Distilled student hits 89% of agentic pipeline accuracy at 1.1% parameters
- Held-out accuracy rises from 27.1% base to 81.4%
- Embedding pruning shrinks model to 1.9985B with identical logits
From the original article
1 min read at huggingface.co
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.
By Logesh Kumar Umapathi · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.