EgoTools: 100-hour egocentric video dataset teaches AI tool-centric reasoning
liuziwei7 · x · 2026-10-03
Researchers from NTU's S-Lab, ASTAR, KAIST and others released EgoTools, a project asking whether AI can understand why, which, and how humans use tools in real-world first-person video.
- Dataset: 100.37 hours of real egocentric video across 7 everyday domains (kitchens, labs, workshops, classrooms).
- Benchmark: 1,000 questions across four tracks, structured as ground → track → infer.
- Reference model: EgoTools-8B lifts overall accuracy from 50.0% to 60.9% (+10.9 pp) on the same 8B backbone with 64 frames.
Paper, code, data and model are all open-sourced, with a leaderboard and 3D playground.
Related event: EgoTools: 100-Hour Egocentric Dataset for Tool-Use Reasoning(4 posts)→
More from Multimodal
- Core Memory profiles Ari Kuschnir, the creator behind viral AI parody videos — kyliebytes · 2026-11-19
- AI-generated flat-illustration portraits show off stylized consistency — OVolosin82152 · 2026-11-19
- GPT-6.2 Rigs and Animates a 3D Game Character End-to-End, Dev Puts It Straight Into Production — OpenAIDevs · 2026-11-19
- AssemblyAI Launches STT-3.7 Models With 86ms Agent Latency and Rewritten Inference Engine — AssemblyAI · 2026-11-19
- Pika Enact lets you direct actors and camera inside a running AI video in real time — thetripathi58 · 2026-11-19
- Google DeepMind's Genie 4 adds native sound, chainable worlds, and a community remix gallery — The Decoder · 2026-11-19