16 papers
EvoMem-VLA: State-Evolution Memory for Long-Horizon Robot Manipulation
Yuheng Na, Zhide Zhong, Junjie He +7
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 ta…
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
Lishan Yang, Wenxuan Song, Xi Wang +14
Building on recent advances in world models, World Action Models (WAMs) jointly model video prediction and action generation. However, they typically represent videos in 2D pixel s…
SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models
Junjie He, Junfeng Li, Zhide Zhong +9
World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actions by relying mainly on visual…
Is Forward Prediction Enough? Physical State Grounding for JEPA World Models
Haodong Yan, Jiaguan Zhu, Mingyuan Jia +12
Learning structured and control-relevant latent representations remains a key challenge for world models. Recent JEPA-based world models learn action-conditioned predictive latent…
Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models
Haodong Yan, Junfeng Li, Junjie He +12
Mainstream World-Action Models (WAMs) adapt pretrained video generation models (VGMs) for robot control, transferring their learned dynamics prior for action prediction. These VGMs…
DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation
Junfeng Li, Junjie He, Zhide Zhong +12
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 o…
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
Zehua Fan, Junjie He, Wenxuan Song +14
World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mobile manipulation demands sim…
Video = World + Event Stream
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +24
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 persis…
Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +23
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises…
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Lianghua Huang, Zhi-Fan Wu, Wei Wang +22
We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. W…
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
Zhide Zhong, Haodong Yan, Junfeng Li +3
Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance dur…
DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models
Zhide Zhong, Junfeng Li, Junjie He +10
Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often strug…
S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight
Haodong Yan, Zhide Zhong, Jiaguan Zhu +10
Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs,…
PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation
Zehua Fan, Wenqi Lyu, Wenxuan Song +12
Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but als…
AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
Junjie He, Yuxiang Tuo, Binghui Chen +3
Recently, large-scale generative models have demonstrated outstanding text-to-image generation capabilities. However, generating high-fidelity personalized images with specific sub…
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
Junjie He, Yifeng Geng, Liefeng Bo
This paper presents UniPortrait, an innovative human image personalization framework that unifies single- and multi-ID customization with high face fidelity, extensive facial edita…