technique

Video PreTraining (VPT)

techniqueactivevideo-pretraining-vpt--fab3d9c1·1 events·first seen 28d ago

Aliases: Video PreTraining (VPT)

Co-occurring entities

More like this (12)

VPT Model contrastive vision-language pretraining VideoVAE+Contrastive Pre-training Verifier-in-the-Loop Training (ViL)Unsupervised Pre-training video encoding instruction-based multitask pretraining video generation Virtual Try-On temporally ordered pre-training ViT (Vision Transformer)

Recent events (1)

6Openai Blog·28d ago·source ↗

Learning to play Minecraft with Video PreTraining (VPT)

OpenAI trained a neural network to play Minecraft using Video PreTraining (VPT) on a large unlabeled video dataset of human gameplay, supplemented by a small amount of labeled contractor data. The model operates via native human interface inputs (keypresses and mouse movements) rather than game APIs. After fine-tuning, it can craft diamond tools—a task requiring over 20 minutes and ~24,000 actions for skilled humans. The work is framed as a step toward general computer-using agents.

Frontier Model Releases Agent and Tool Ecosystem VPT Model Video PreTraining (VPT)OpenAI +2 more