GEN-1.5 enables one-shot physical task learning, stepping towards physical world AGI
DeryaTR_ · x · 2026-08-21
Generalist AI introduced GEN-1.5, a one-shot learner capable of learning new tasks in seconds and generalizing them. This capability emerged from pretraining on large-scale physical data, marking a step towards general intelligence for the physical world.
Related event: Generalist AI Unveils GEN-1.5, a One-Shot Embodied Foundation Model(20 posts)→
More from Embodied
- Astra 机器人控制实测:Johns Hopkins 深度评测其运动与控制理解 — jmin__cho · 2026-10-09
- Pollen's Microduck robot gets custom board: 3h battery life, CPU drops from 114°C to 60°C — huggingface · 2026-10-09
- Ditto-Bench stress-tests GPT-6 Astra and MolmoAct2 on physically challenging robot control — jmin__cho · 2026-10-09
- California moves to shut down human vs. robot cage fights hosted by startup Rek — The Verge AI · 2026-10-09
- Text2Sim turns text prompts into editable physics-grounded videos and sim setups — erwincoumans · 2026-10-09
- Singapore's first giant robot fight flopped because teleop policies weren't built for combat, researcher argues — carlosdponx · 2026-10-09