6 papers
BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries
Jiaxin Fang, Ruitong Liu, Zeyu Lai +6
World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action prediction to irrelevant visu…
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
Shukai Gong, Xuanran Zhai, Yintianrun Zhang +16
Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing worl…
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…
Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control
Jianjie Fang, Yongyan Xu, Ziyou Wang +13
World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in which agents can perceive, act, fo…
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
Mingyu Dong, Chong Xia, Mingyuan Jia +4
Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capab…
AirScape: An Aerial Generative World Model with Motion Controllability
Baining Zhao, Rongze Tang, Mingyuan Jia +9
How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general s…