arXiv Computer Vision
DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 3
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
arXiv:2606. 03159v1 Announce Type: cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck.
Hugging Face Trending Papers
Jun 2
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations.
arXiv Computer Vision
2d ago
RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
arXiv:2609.36851v1 Announce Type: new Abstract: End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their...
arXiv AI
Jun 17
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
arXiv:2606. 17386v1 Announce Type: cross Abstract: End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments.
arXiv Machine Learning
Jun 8
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
arXiv:2606. 07366v1 Announce Type: cross Abstract: Self-driving simulations typically rely on data collected in a small number of cities or on hand-authored synthetic scenarios.
arXiv Computer Vision
Sep 7
Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.