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…
When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Driving
Morui Zhu, Deyuan Qu, Qi Chen +2
Driving benchmark scores are increasingly used not only for evaluation but also as optimization targets. This raises a fundamental question: do score gains remain reliable evidence…
LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings
Yongshuo Liu, Xu Gao, Morui Zhu +5
We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings. LANTERN separates warning onset, hazard onset, warning termination, and post-hazard recove…
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…
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…
F3DGS: Federated 3D Gaussian Splatting for Decentralized Multi-Agent World Modeling
Morui Zhu, Mohammad Dehghani Tezerjani, Mátyás Szántó +3
We present F3DGS, a federated 3D Gaussian Splatting framework for decentralized multi-agent 3D reconstruction. Existing 3DGS pipelines assume centralized access to all observations…
Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks
Morui Zhu, Yongqi Zhu, Song Fu +1
Autonomous trucking poses unique challenges due to articulated tractor-trailer geometry, and time-varying sensor poses caused by the fifth-wheel joint and trailer flex. Existing pe…
Phase-Interface Instance Segmentation as a Visual Sensor for Laboratory Process Monitoring
Mingyue Li, Xin Yang, Shilin Yan +8
Reliable visual monitoring of chemical experiments remains challenging in transparent glassware, where weak phase boundaries and optical artifacts degrade conventional segmentation…
From Features to Reference Points: Lightweight and Adaptive Fusion for Cooperative Autonomous Driving
Yongqi Zhu, Morui Zhu, Qi Chen +4
We present RefPtsFusion, a lightweight and interpretable framework for cooperative autonomous driving. Instead of sharing large feature maps or query embeddings, vehicles exchange…
M3CAD: Towards Generic Cooperative Autonomous Driving Benchmark
Morui Zhu, Yongqi Zhu, Yihao Zhu +4
We introduce MCAD, a comprehensive benchmark designed to advance research in generic cooperative autonomous driving. MCAD comprises 204 sequences with 30,000 frames. Each s…