13 papers
RoboTTT: Context Scaling for Robot Policies
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng +8
The paper introduces RoboTTT, a robot policy that uses test-time training to handle up to 8,000 timesteps of visual‑motor context, enabling one‑shot imitation from video, on‑the‑fl…
Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation
Yifan Li, Xinyu Zhou, Yunhao Ge +1
Robotic manipulation is often specified through language instructions or task identifiers, yet cluttered environments with similar objects are better handled by spatially indicatin…
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
Chaoyang Wang, Wenrui Bao, Sicheng Gao +5
Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where vi…
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2…
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33
State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce Drea…
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin +8
Recent video generation models demonstrate remarkable ability to capture complex physical interactions and scene evolution over time. To leverage their spatiotemporal priors, robot…