PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
PhysBrain 1.5, an 8B physical foundation model, sets open-source state of the art across 28 embodied understanding benchmarks.
The paper presents PhysBrain 1.5, a unified 8B model for understanding physical environments, generating actions, and predicting future states, built from a vision-language model with joint autoregressive next-token prediction over language, end-effector motion, and dense visual targets. Pre-training uses embodied supervision from human interaction videos, followed by supervised fine-tuning on human demonstrations, robot trajectories, and simulated experience. The model averages 72.5 across 28 embodied benchmarks, setting a new open-source state of the art and performing on par with proprietary GPT-6-Astra and Gemini 3.6 Flash, with best open-source results on 14 benchmarks.
- 8B model scores 72.5 average across 28 embodied benchmarks
- Matches proprietary GPT-6-Astra and Gemini 3.6 Flash performance
- Pre-trained on human interaction videos, fine-tuned with robot trajectories
- Best open-source results on 14 benchmarks while retaining multimodal capabilities
From the original article
1 min read at huggingface.co
We present PhysBrain 1. 5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the physical loop of observation, interaction, and environmental change, we bring these capabilities into a common learning framework.
By DeepCybo Team, Yu Bin, Haipeng Cao · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.