11 papers
DiffWAM: A Fast and Efficient Navigation World Action Model
Mo Zhu, Yuze Wu, Xijie Huang +3
Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion typically requires expensive…
GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning
Long Xu, Zhiqi Zhang, Mi Yan +8
Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment for both. Automated scene ge…
HyperSketch: Controllable Video Sketching in a Style Hyperspace
Xinding Zhu, Xinye Yang, Yingping Yang +3
Vector sketch animation offers tremendous advantages for multimedia and creative design through concise line expressions and flexible editing. Learning-based generation methods of…
D-VLC: Decentralized Vision-Language Collaboration for Heterogeneous Embodied Multi-Robot Systems in Unknown Environments
Yuan Zhou, Ruitong Lin, Shen Wang +5
Multi-robot systems, particularly heterogeneous robot swarms, can improve the efficiency of complex task execution through parallel collaboration and complementary capabilities. Ho…
FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model
Jinhan Li, Xijie Huang, Weiqi Gai +10
In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relying on either costly real-worl…
NavDreamer: Video Models as Zero-Shot 3D Navigators
Xijie Huang, Weiqi Gai, Tianyue Wu +5
Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture…
USS-Nav: Unified Spatio-Semantic Scene Graph for Lightweight UAV Zero-Shot Object Navigation
Weiqi Gai, Yuman Gao, Yuan Zhou +6
Zero-Shot Object Navigation in unknown environments poses significant challenges for Unmanned Aerial Vehicles (UAVs) due to the conflict between high-level semantic reasoning requi…
A Kinetic Energy Perspective of Flow Matching
Ziyun Li, Huancheng Hu, Soon Hoe Lim +6
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corres…
VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
Yuze Wu, Mo Zhu, Xingxing Li +6
This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four…
Embodied Navigation Foundation Model
Jiazhao Zhang, Anqi Li, Yunpeng Qi +14
Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions.…
Vector sketch animation generation with differentiable motion trajectories
Xinding Zhu, Xinye Yang, Shuyang Zheng +4
Sketching is a direct and inexpensive means of visual expression. Though image-based sketching has been well studied, video-based sketch animation generation is still very challeng…