EgoTools: 100-Hour Egocentric Dataset Shows Video Models Struggle at Tool Reasoning

ropedia-ai · hf · 2026-10-02

Researchers introduce EgoTools, the first comprehensive suite for egocentric tool-use understanding, with two components:

Results show current video models struggle to ground tool use in visual evidence: Gemini-3.1-Pro reaches 66.9% overall but only 51.7% on Perception & Grounding. The data also serves as a training resource: full supervised fine-tuning lifts Qwen3-VL-8B-Instruct from 50.0% to 60.9% under strict source-video separation.

Original post →

More from Embodied

Embodied channel →