TLDR Tech / AI
The First Fully General Computer Action Model
FDM-1, a foundation model for computer use, efficiently trains on 11 million hours of video to autonomously handle tasks like CAD, driving, and fuzzing. Unlike traditional models that rely on expensive, limited annotation, FDM-1 uses a video encoder that compresses 2 hours of video into 1M tokens and predicts actions with inverse dynamics for scalable training. With enhanced context processing, FDM-1 showcases significant advancements in executing long-horizon tasks and exploring complex state trees in GUI environments.
Read the full story