8 papers
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
Junyi Wu, Zekun Li, Chenhongyi Yang +9
Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual memory: the previously obse…
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…
TADreamer: Zero-Shot Language-Guided 3D Navigation for Terrestrial-Aerial Bimodal Robots via Video Imagination
Xiangyu Li, Tiancheng Lai, Xijie Huang +7
Language-guided navigation for terrestrial-aerial bimodal robots requires selecting routes and locomotion modes that match scene context and task intent. Generated videos can repre…
PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation
Yijin Wang, Yuru Tian, Xijie Huang +5
Bird's-eye-view (BEV) images have been demonstrated to provide valuable prior information for navigation. Given the global information provided by such views, two key challenges re…
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…
Flying in Clutter on Monocular RGB by Learning in 3D Radiance Fields with Domain Adaptation
Xijie Huang, Jinhan Li, Tianyue Wu +3
Modern autonomous navigation systems predominantly rely on lidar and depth cameras. However, a fundamental question remains: Can flying robots navigate in clutter using solely mono…
Reactive Aerobatic Flight via Reinforcement Learning
Zhichao Han, Xijie Huang, Zhuxiu Xu +5
Quadrotors have demonstrated remarkable versatility, yet their full aerobatic potential remains largely untapped due to inherent underactuation and the complexity of aggressive man…