CORTEXA
← Browse
arxivcs.CVcs.RO2026-07-12

Is Energy Guidance All You Need? Training-Free Norm Injection for Driving World Models

Xiyan Su, Frank Diermeyer, Markus Lienkamp

Driving world models built on large video-diffusion backbones generate realistic scenes but are hard to control: enforcing a traffic norm typically means retraining the backbone or conditioning it on hand-built layouts. We ask whether controllability requires training at all. Our experiment shows that a rectified-flow driving world model, which jointly generates future video and a planned ego trajectory, can have its planned trajectory steered entirely at sampling time by differentiable energy functions that encode driving norms, without knowledge-specific retraining of the diffusion backbone. Concretely, we demonstrate that a world model built on Open-Sora 2.0 MM-DiT backbone can be steered to brake at a counterfactual target by injecting energy guidance at sampling time. However, we find that the generated video does not yet follow the steered trajectory through the backbone's joint self-attention and identify the cross-stream coupling as a crucial requirement for end-to-end-controllable rollouts.

View free PDFSource page

Related papers

arxivcs.CVcs.RO2026-07-15

M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming

Ke Cheng, Hanqiao Ye, Lei Shi, Yahui Liu, Yunhan Shen, Jingtao Dong, et al.

Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M$^\text{4}$World, a Multi-view and Multimodal generative driving world…

View free PDFSource page
arxivcs.CVcs.AIcs.LGcs.RO2026-07-17

Orbis 2: A Hierarchical World Model for Driving

Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso, Karim Farid, Jonannes Dienert, Rajat Sahay, et al.

Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required for real-world downstream tasks. We present a hierarchical driving world model that factorizes future…

View free PDFSource page
arxivcs.ROcs.CVcs.LG2026-07-07

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, et al.

Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations. In particular, flow matching-based VLA models have shown remarkable success due to their capability to generate precise and smooth action sequences and capture multim…

View free PDFSource page
arxivcs.CVcs.AIcs.GRcs.RO2026-07-02

NeoMap: Training-free Novel-View Synthesis from Single Images and Videos

Jinxi Li, Tianyi Zhang, Yafei Yang, Zihui Zhang, Peng Huang, Koon Wing Macgyver Lin, et al.

We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning…

View free PDFSource page
arxivcs.CVcs.RO2026-07-31

CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation

Minh-Quan Dao, Yancong Lin, Julie Stephany Berrio Perez, Holger Caesar

LiDAR scene flow estimation has settled into a monoculture: nearly all recent methods share the same feed-forward architecture and the same family of self-supervised losses, inheriting each other's assumptions, and each other's blind spots. When those assumptions fail, as they do…

View free PDFSource page
arxivcs.ROcs.CV2026-07-22

KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding

Zeyu Liu, Zhangzhe Zhu, Yang Zhang, Chenyou Fan, Chenjia Bai, Xuelong Li

Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts offers a more faithful assessment of physical plausibility than open-loop alternatives, existing frameworks almost exclusively rely…

View free PDFSource page