Publications (12)
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…
NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving
Fuhao Li, Huan Jin, Bin Gao +3
Multi-view 3D visual grounding is critical for autonomous driving vehicles to interpret natural languages and localize target objects in complex environments. However, existing dat…
THUD++: Large-Scale Dynamic Indoor Scene Dataset and Benchmark for Mobile Robots
Zeshun Li, Fuhao Li, Wanting Zhang +4
Most existing mobile robotic datasets primarily capture static scenes, limiting their utility for evaluating robotic performance in dynamic environments. To address this, we presen…
AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos
Jiagao Hu, Daiguo Zhou, Danzhen Fu +6
Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse wea…
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Fuhao Li, Wenxuan Song, Han Zhao +5
Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are buil…
Signal Classification Recovery Across Domains Using Unsupervised Domain Adaptation
Mohammad Ali, Fuhao Li, Jielun Zhang
Signal classification models based on deep neural networks are typically trained on datasets collected under controlled conditions, either simulated or over-the-air (OTA), which ar…
DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding
Qinghongbing Xie, Zijian Liang, Fuhao Li +1
Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only…
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
Wenxuan Song, Han Zhao, Fuhao Li +7
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard s…
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
Fuhao Li, Shaofeng You, Jiagao Hu +6
Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-…
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
Jiagao Hu, Yuxuan Chen, Fuhao Li +4
Removing objects from videos remains difficult in the presence of real-world imperfections such as shadows, abrupt motion, and defective masks. Existing diffusion-based video inpai…
Autonomous Unknown-Application Filtering and Labeling for DL-based Traffic Classifier Update
Jielun Zhang, Fuhao Li, Feng Ye +1
Network traffic classification has been widely studied to fundamentally advance network measurement and management. Machine Learning is one of the effective approaches for network…
CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
Ziyang Gong, Fuhao Li, Yupeng Deng +4
Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to per…