World models · Simulation · Robotics. Papers, reports and open-source projects are identified separately.
Connects driving reasoning and action prediction through Cosmos-Reason and a diffusion trajectory decoder, studying reasoning-action consistency.
A coupled vision-language and diffusion architecture combines reasoning with continuous robot-action generation.
A platform of video curation, tokenizers, pretrained world models and post-training for physical-AI applications.
This index currently holds 3 records attributed to NVIDIA (2025). Each entry links to the primary source; product announcements and news posts are not counted as papers.
These records come from other institutions but address the same topics, so the lab can be read in context.
