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

Papers

arxiv:2609.07154

Published on Sep 10

· Submitted by

Logesh Kumar umapathi on Sep 14

· Ambient Intelligence

Upvote

3

Authors:

Logesh Kumar Umapathi

Abstract

A 2B vision-language model distilled from a tool-using agent achieves first-place performance on long egocentric video question answering by pruning its multilingual embedding table to meet parameter limits.

Generated by thinkingmachines/Inkling-Small

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.

View arXiv page View PDF GitHub 2 Add to collection

Community

infinitylogesh

Paper author Paper submitter 8 days ago

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

librarian-bot

8 days ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision (2026)

• Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision (2026)

• Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding (2026)

• ReToken: One Token to Improve Vision-Language Models for Visual Retrieval (2026)

• Qwen-MusicAVQA-7B: A Multimodal Model for Music Audio-Visual QA (2026)

• Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA (2026)

• Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

3

Get this paper in your agent:

hf papers read 2609.07154

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.07154 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.07154 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.07154 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.