arXiv:2608. 10232v1 Announce Type: cross Abstract: Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.
arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on a...
AD-WM is a new action‑discriminative joint‑embedding world model designed for counterfactual model predictive control. It augments residual latent dynamics with action‑recovery regularization based on inverse dynamics and conditional mutual information, while discarding auxiliary heads at test time so that MPC remains unchanged. Experiments on OGBench‑Cube and other simulation environments show substantial gains in hard‑start success and mean success, and zero‑shot transfer to a Franka robot improves pick‑and‑place success from 42.2% to 71.1%.
arXiv:2609.23369v1 Announce Type: new Abstract: Generation-free world action models (WAMs) retain future-video prediction during training but act from internal video features at inference, leaving un...
The paper introduces TRACC, a pipeline that learns humanoid skills from a single failed human video by first imitating the usable portion of the motion trajectory and then completing the task based on the inferred outcome. It treats the motion prefix before failure as prior knowledge and uses a task-completion reward to guide learning toward the intended goal without needing a successful demonstration. The method is evaluated on six failed tasks from the Oops! dataset, showing its effectiveness in learning from failures.
arXiv:2609.38057v1 Announce Type: new Abstract: Improving robot policies on new tasks without collecting additional expert demonstrations remains a central challenge in robot learning. World action m...