Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cost but poses a capacity allocation problem: a student must match the teacher's iterative generation with far less sequential computation. Existing trajectory methods ask...
Lang Feng, Péter Karkus, M. Igl et al.· 0 citations
Driving models increasingly ground reasoning in causal relations, spatial structure, perceptual evidence, and predicted futures. These advances make reasoning more faithful to the driving scene, but leave a fundamental question unresolved: what should groundedness mean when the model ultimately outputs an action? Corre...
Minkyoung Cho, Ze-Wei Zhou, Wen-Hao Ding et al.· 0 citations
Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize knowledge acquired during vision-language pretraining for accurate and interpretable driving. However, VLAs can take only a limited number of frames as visual input due to...
Kai Yan, Xiang Chen, Yu-Long Cao et al.· 0 citations
World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such training paradigms introduce a mismatch: perturbed actions imply counterfactual future visual, while the noised video remains tied to the GT reco...
Chensheng Peng, Wen-Hao Ding, Ran Tian et al.· 1 citation
Endpoint-Constrained Optimization (ECO), a lightweight postprocessing layer that anchors the trajectory to the vehicle's executed history, preserves the policy's predicted endpoint, and reshapes the intermediate waypoints to improve feasibility is introduced.
Brayden Zhang, Mahsa Golchoubian, Igor Gilitschenski et al.· 0 citations
This work proposes OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes) which provides supervision to the pre-trained student during closed-lo...
D. Da Col, M. Igl, Peter Karkus et al.· 1 citation
This work proposes COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations, and evaluates on high-signal dynamic scenarios where historical context is most critical for behavior correctness, and accordingly design behavioral metrics.
Zhixuan Liang, Yuxiao Chen, Yurong You et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
