6 papers
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
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…
Unsupervised Discovery of Failure Taxonomies from Deployment Logs
Aryaman Gupta, Yusuf Umut Ciftci, Somil Bansal
As robotic systems become increasingly integrated into real-world environments, ranging from autonomous vehicles to household assistants, they inevitably encounter diverse and unst…
Fourier Domain Adaptation for Traffic Light Detection in Adverse Weather
Ishaan Gakhar, Aryesh Guha, Aryaman Gupta +2
Traffic light detection under adverse weather conditions remains largely unexplored in ADAS systems, with existing approaches relying on complex deep learning methods that introduc…
Enhancing Safety and Robustness of Vision-Based Controllers via Reachability Analysis
Kaustav Chakraborty, Aryaman Gupta, Somil Bansal
Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and con…
Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations
Ali M. Ali, Aryaman Gupta, Hashim A. Hashim
This paper proposes a novel Reinforcement Learning (RL) approach for sim-to-real policy transfer of Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL-UAV). The proposed a…