Xin Kang 康鑫

China Solution Architect · NVIDIA Beijing

Autonomous-Driving 3D Reconstruction · Feed-forward Reconstruction · VLA Models

About

I joined NVIDIA Beijing in July 2025, where I am currently a China Solution Architect. My research focuses on 3D reconstruction algorithms for autonomous driving, feed-forward reconstruction, and vision-language-action (VLA) models. I received my Ph.D. (2020–2025) and B.Eng. (2016–2020) from the University of Science and Technology of China (USTC), advised by Prof. Xuejin Chen (陈雪锦).

Publications

Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation

Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang, Seung Wook Kim, Ning Xu, Qi Wu, Janick Martinez Esturo, Shengyu Huang, Nick Schneider, Laura Leal-Taixe, Zan Gojcic, Sanja Fidler

arXiv2026

Project Page ↗

LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision

Yiming Huang, Xin Kang, Sipeng Zhang, Hongliang Ren, Weihua Zhang, Junjie Lai

ECCV2026

Project Page ↗

SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms

Haithem Turki, Qi Wu, Xin Kang, Janick Martinez Esturo, Shengyu Huang, Ruilong Li, Zan Gojcic, Riccardo de Lutio

ICLR2026

Project Page ↗

ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery

Yanzhe Lyu, Kai Cheng, Xin Kang, Xuejin Chen

ICCV2025

Project Page ↗

LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework

Xin Kang, Zihan Zheng, Lei Chu, Yue Gao, Jiahao Li, Hao Pan, Xuejin Chen, Yan Lu

arXiv2025

arXiv ↗

Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation

Xin Kang, Lei Chu, Jiahao Li, Xuejin Chen, Yan Lu

CVPR2024

PDF ↗

Region-Enhanced Feature Learning for Scene Semantic Segmentation

Xin Kang, Chaoqun Wang, Xuejin Chen

TMM2023

arXiv ↗