PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

2026-09-13

AI Summary

该研究通过将视觉-语言模型转化为物理基础模型，解决了理解物理环境、生成动作和预测未来状态的问题，采用自回归序列优化方法，并结合人类交互视频预训练及监督微调。

Abstract

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. Starting from a general vision--language model, we encode language responses, end-effector motion, and dense visual targets as discrete sequences and jointly optimize them with autoregressive next-token prediction. Pre-training draws its embodied supervision entirely from human interaction videos, using task-centered episodes to pair semantic and spatial context with recovered motion and subsequent observations. We then adapt the model through supervised fine-tuning on a mixture of human demonstrations, robot trajectories, and simulated experience. Across 28 embodied understanding benchmarks, our 8B model achieves an average score of 72.5, setting a new open-source state of the art and performing on par with leading proprietary models such as GPT-6-Astra and Gemini 3.6 Flash. It achieves the best open-source results on 14 benchmarks while retaining general multimodal capabilities. Beyond these understanding evaluations, qualitative examples show the model's ability to produce end-effector trajectories and predict future scenes through spatially aligned RGB, depth, and robot-mask outputs.

Problem

• Physical Environments
• Action Generation
• Future State Prediction
• Unified Model

Innovation

• Unified Model
• Autoregressive Next-Token Prediction
• Embodied Supervision
• Multimodal Capabilities