papers

Publications (12)

cs.CV2026

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…

cs.CV2025

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…

cs.RO2024

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…

cs.CV2026

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…

cs.RO2025

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…

cs.CE2025

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…

cs.CV2025

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…

cs.CV2026

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…

cs.CV2026

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-…

cs.CV2026

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…

cs.NI2020

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…

cs.CV2024

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…