Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily measure route completion, safety, and rule compliance, leaving a fundamental question unresolved: does language actually determine which feasi...
Zi-Han You, Ze-Hua Fan, Wenqi Lyu et al.· 0 citations
World action models improve robotic manipulation by conditioning actions on predicted futures, yet existing tactile variants largely inherit video-generation pipelines that reconstruct future tactile observations through iterative denoising. Such prediction can become unreliable under deployment drift: small changes in...
En-Yi Wang, Ming-Xin Wang, Quan Shi et al.· 0 citations
Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectories and score them for execution, and they have outperformed representative direct-prediction baselines on NAVSIM. Their scorer must compare plans that were never execute...
Jie-Yuan Pei, Mei-Yi Lu, Sining Ang et al.· 0 citations
4D-WAM is proposed, a model-agnostic training strategy that injects spatiotemporal knowledge from 3D trajectory fields into WAMs through representation alignment, enabling WAMs to learn trajectory-level spatiotemporal representations.
Lishan Yang, Wen-Xuan Song, Xi Wang et al.· 5 citations· ⚡1
StageWAM is introduced, which augments a Motus-based World Action Model with Stage-JEPA, a goal-conditioned Joint-Embedding Predictive Architecture (JEPA) predictor, which uses a frozen V-JEPA2 encoder to extract the current-state representation and predicts the latent target of the next inferred stage.
Xiao Liu, Yuguang Yang, Xi Wang et al.· 2 citations· ⚡1
Adaptive-WAM is introduced, a quality-aware multi-exit planner built on a Wan2.2-5B backbone that avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality.
MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator across diverse tasks with strong generalization.
Ze-Hua Fan, Jun-Jie He, Wen-Xuan Song et al.· 3 citations· ⚡1
Semantic-Temporal WAM (ST-WAM) is proposed to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics, demonstrating that semantic-temporal modeling effectively complements pixel-generative dynamics for robust ma...
Mingxin Wang, Bin Hu, Bin Qian et al.· arXiv.org· 5 citations· ⚡1
JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor, predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, whi...
Yi-Han Lin, Jia-Wei He, Shi-Feng Bao et al.· 12 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
