Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on long-horizon, memory-dependent tasks. Existing efforts incorporate compressed historical features or sparse visual keyframes. However, isolated snapshots can leave the polic...
Yu-Heng Na, Zhi-De Zhong, Jun-Jie He et al.· 0 citations
Vision-Language-Action (VLA) models have become a powerful paradigm for robot manipulation, but training a single generalist policy for heterogeneous robot embodiments remains an open problem. Existing methods have two main limitations. First, they underuse dynamics priors shared across diverse visual and interaction d...
Jun-Feng Li, Junjie He, Zhi-De Zhong et al.· 1 citation
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and o...
Lianghua Huang, Zhigang Wu, Yupeng Shi et al.· arXiv.org· 2 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
Wan-Streamer v0.2 is presented, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model, which raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS.
Lianghua Huang, Zhigang Wu, Yupeng Shi et al.· arXiv.org· 2 citations
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
The Robust-WAM is a general post-training method for video-generation-based WAMs that preserves the VAE-based generative path and adds a lightweight semantic foresight alignment objective on the action stream to retain the large-scale VGM pretraining while grounding actions in appearance-invariant dynamics.
Hao-Dong Yan, Jun-Feng Li, Jun-Jie He et al.· 2 citations
PSG-JEPA is proposed, a physically grounded JEPA world model that shapes its latent space with two complementary grounding objectives beyond forward prediction: grounding individual latents in robot proprioceptive state, and grounding latent pairs in multi-horizon joint-angle changes.
