Model Releases
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
arXiv:2609.07099v1 Announce Type: new Abstract: We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the large-model division and second in
arXiv:2609.07099v1 Announce Type: new Abstract: We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the large-model division and second in the or silent, the model predicts yes or no, and we derive the decision from the renormalised probabilities of these two tokens. This formulation improved macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Second, because labelled data were limited to the released validation set, we generated additional supervision using a tool-calling video agent that inspects each clip and assigns intervention timestamps. A narration-only alternative was four times larger and ten times cheaper, but transferred worse than supervision from an unrelated real corpus, suggesting that visual grounding is more important than annotation volume for this task.
Related
- Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
- Perception First: A Frontier Native-Video Model with Self-Consistency for Implicit Video Question Answering
- Personal Visual Context Learning in Large Multimodal Models
Source: arXiv cs.CV | 2026-09-09