ZGCA HMI LAB

Publications

MemoryVLN memory construction and management overview

arXiv 2026

MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation

Xueyao Wei, Yifei Wang, Delun Li, Shaoan Wang, Junzhi Yu, Wenjie Song, Xingyu Chen

MemoryVLN combines compressed ego-aware visuospatial memories with hierarchical retrieval and cross-context reuse for long-horizon vision-language navigation.

PDF Project Code

arXiv 2026

Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework

Delun Li, Xueyao Wei, Rui Chen, Yifei Wang, Junzhi Yu, Wenjie Song, Xingyu Chen

MultINav introduces a benchmark and a persistent interaction-graph agent for navigation through interactions that change spatial connectivity and target visibility.

PDF Project Code

arXiv 2026

PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation

Xingyu Guo, Chao Jing, Li Yi, Xingyu Chen, Zhengxing Wu

PINT is a unified model with shared predictive intent for robot manipulation.

PDF Project Code

arXiv 2026

4D Latent Cache for Efficient Conditioning in Dynamic World Modeling

Jianhui Zhang, Zuyao Lin, Pengxin Xu, Jingdong Wang, Xingyu Chen

4LC reuses cached visual representations across time and viewpoints to condition multi-task video generation efficiently.

PDF Project Code Demo

NeurIPS 2026

HyrCAP: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding

Rui Chen, Xingyu Chen, Pengxin Xu, Kai Chen, Junzhi Yu

Hybrid propose rank-calibration method for of action proposal and semantic understanding.

PDF Project Code

arXiv 2026

Hand-Object Interaction in the Age of Large Foundation Models: Reconstruction, Generation, and Embodied Transfer

Weiquan Lin, Yu Deng, Shiyang Liu, Luping Xiao, Xu Tang, Junzhi Yu, Jiaolong Yang, Lei Zhang, Xingyu Chen

A systematic survey of foundation-model priors for hand-object interaction across reconstruction, generation, and embodied transfer.

PDF Project Code

NeurIPS 2026

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

Xinyu Guo, Bin Xie, Wei Chai, Xianchi Deng, Tiancai Wang, Zhengxing Wu, Xingyu Chen

Prior knowledge maintenance and efficient downstream fine-tuning in VLA models.

PDF Project

arXiv 2026

World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks

Zuyao Lin, Jianhui Zhang, Peidong Jia, Xiaoguang Zhao, Shanghang Zhang, Jingdong Wang, Xingyu Chen

A video-based world-ego modeling framework for long-horizon evolution in hybrid embodied tasks.

PDF Project

arXiv 2026

SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding

Pengxin Xu, Xincheng Lin, Luping Xiao, Qing Jiang, Meishan Zhang, Hao Fei, Shanghang Zhang, Xingyu Chen

A hierarchical scene parsing framework for comprehensive visual semantic understanding.

PDF Code

ACM MM 2026

GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction

Weiquan Lin, Yaoqing Hu, Liangchen Dai, Xu Tang, Xingyu Chen

GeoHand leverages prior geometry knowledge for monocular 3D hand reconstruction.

PDF

TRO 2026

VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory

Shaoan Wang, Yuanfei Luo, Xingyu Chen, Aocheng Luo, Dongyue Li, Chang Liu, Sheng Chen, Yangang Zhang, Junzhi Yu

VLingNav combines adaptive reasoning with visual-assisted linguistic memory for persistent cross-modal semantic memory in long-horizon navigation.

PDF Project