Metraipolis › archive › dc_8d31db404029

Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model — arXiv:2609.07154

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07154
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:41.904Z
SHA-256 of the archived text
aebafe870986ccccad41b35b173f98f1d98346c749f243141a02d6d5eaa41d5d
Stable URL of this page
https://metraipolis.com/documento/dc_8d31db404029

How to cite

Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model — arXiv:2609.07154 — arXiv (en), https://arxiv.org/abs/2609.07154 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d31db404029 (Metraipolis archive dc_8d31db404029, sha256 aebafe870986ccccad41b35b173f98f1d98346c749f243141a02d6d5eaa41d5d)
BibTeX
@misc{dc8d31db404029,
  title = {Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model — arXiv:2609.07154},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07154},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d31db404029; sha256 aebafe870986ccccad41b35b173f98f1d98346c749f243141a02d6d5eaa41d5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07154. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 one greedy forward pass; It is obtained by distilling the junior perception module of a tool-using agentic pipeline, not the agent itself into a small student, using teacher traces filtered to those that answered correctly. it reaches 89% of the accuracy of the large agentic pipeline using 1.1% of its parameters. This raises a 27.1% base model to 81.4% on our held-out questions. The 2B backbone has 2.2132B parameters and therefore over the divisional limit, to make the entry admissable we prune the multilingual embedding table from 248,320 to 143,469 rows, reaching 1.9985B with provably identical logits on retained rows.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07154 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:57.194Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).