1 citations · 1 across the 4 of their papers we have counts for
7 papers
SkipWorld: Latent Skip Planning with Distilled World Models for Efficient Visual Navigation
Yifei Yang, Zehua Fan, Zike Yan +2
World-model-based visual navigation enables action planning by predicting future states under candidate trajectories. However, long-horizon rollout remains challenging: models are…
Language2Drive: Do Vision-Language-Action Models Really Follow the Instructions in Autonomous Driving?
Zihan You, Zehua Fan, Wenqi Lyu +19
Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily me…
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…
AR Forcing: Towards Long-Horizon Robot Navigation World Model
Yifei Yang, Zehua Fan, Huan Li +9
The diffusion based robot navigation world models are typically trained using parallel supervision, while autoregressive inference is employed during path planning. This results in…
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…
Lagrangian Motion Fields for Long-term Motion Generation
Yifei Yang, Zikai Huang, Chenshu Xu +1
Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise moti…
Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation
Haofeng Liu, Chenshu Xu, Yifei Yang +2
Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion…