Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

作者：Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin, Yen-Chen Lin, Yunhao Ge, Grace Lam, Percy Liang, Shuran Song, Ming-Yu Liu, Chelsea Finn, Jinwei Gu · 单位：NVIDIA, Stanford University · 会议/期刊：arXiv · 日期：2026-01-22 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / Visual/State Prediction/Generation