ZGCA HMI LAB logoZGCA HMI LAB
EN
北京中关村学院院徽北京中关村学院

论文发表

arXiv 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.

PDFProject
arXiv 2026

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks

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

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

PDFProject
SceneParser preview
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.

PDFCode
GeoHand preview
arXiv 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
VLingNav preview
arXiv 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.

PDFProject
Detect Anything via Next Point Prediction preview
CVPR 2026

Detect Anything via Next Point Prediction

Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, Zhaoyang Zeng, Yihao Chen, Tianhe Ren, Junzhi Yu, Lei Zhang

A unified framework for point-based visual cognition based on LLMs.

PDFProject
Rex-Thinker preview
ICLR 2026

Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning

Qing Jiang*, Xingyu Chen*, Zhaoyang Zeng, Junzhi Yu, Lei Zhang

Object referring is reformulated as a Chain-of-Thought reasoning task that verifies candidate object regions step by step.

PDFProject