analiza aiqbench
This arXiv report presents an upgraded generative world model for autonomous-driving simulation, with finer control over traffic lights and road markings, better multi-camera consistency, and few-step causal generation for longer rollouts. For AI readers, the practical question is whether these gains hold up under independent evaluation, since the authors introduce their own evaluation suite and the claims rest largely on it.
X-World 1.6: Building Controllable Virtual Cities with World Models
arXiv:2611.00596v1 Announce Type: new Abstract: Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.
Title:X-World 1.6: Building Controllable Virtual Cities with World Models
Abstract:Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.
Artificial Intelligence (cs.AI)
arXiv:2611.00596 [cs.AI]
(or arXiv:2611.00596v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2611.00596 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe
The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale
arXiv · 15 oct. 2026
Slovenia Quantum Computing Companies, The Complete Vendor Guide
Quantum Zeitgeist · 1 aug. 2026
Very Exciting: Zero-Shot Model Predictive Control of Buildings via Excitation-Based Generalized Transfer Learning Models
arXiv · 14 sept. 2026
Poland Quantum Computing Companies, The Complete Vendor Guide
Quantum Zeitgeist · 2 aug. 2026