Apr 11, 2026 · Artificial Intelligence

Why VLA Pioneers Are Abandoning Vision‑Language‑Action Models

Generalist AI’s GEN-1 model achieves over 99% success, 2‑3× speed gains with only a tenth of the data, and its founders argue that vision‑language‑action (VLA) models are merely a crutch, urging a shift toward goal‑driven, fully‑scratch training for physical AGI.

GEN-1Generalist AIGoal-driven research

0 likes · 13 min read

Why VLA Pioneers Are Abandoning Vision‑Language‑Action Models

Machine Heart

Apr 3, 2026 · Artificial Intelligence

Generalist’s GEN-1 Robot Model Achieves 99% Task Success and Emergent Physical Reasoning

Generalist’s new GEN-1 robot model boosts task success from 64% to 99%, cuts execution time threefold, and exhibits emergent physical commonsense by handling unexpected situations, thanks to training on over 500,000 hours of human‑captured motion data, signaling a scaling‑driven leap in embodied AI.

GEN-1Generalist AILarge Language Models

0 likes · 7 min read

Generalist’s GEN-1 Robot Model Achieves 99% Task Success and Emergent Physical Reasoning