Qing Lian

Qing Lian (连庆)

I am currently a researcher at IDEA, working on embodied intelligence. Previously, I worked on self-driving cars at DJI Automotive. I received my Ph.D degree from HKUST StatML Group at The Hong Kong University of Science and Technology supervised by Prof. Tong Zhang. Prior to this, I received my Bachelor degree from the University of Electronic Science and Technology of China.

My research interests in Physical AI and their application on autonomous driving and robotics.

Email / Google Scholar / Github

Publications and Projects

	VLAPilot: A Scheduling Agent for Vision-Language-Action Models Jinghang Li, Qing Lian (Project Lead), Yuhan Xi, Qing Jiang Open-source Project, 2026 A general-purpose agent that pairs a VLM planner and verifier with any VLA backend, turning short-horizon skills into long-horizon robot missions via MCP. Project Page/ Code
	Reflective VLA: In-Context Action Consequences Make VLAs Generalize Qing Lian, Kent Yu, Lei Zhang Preprint, 2026 PDF
	Guide, Think, Act: Interactive Spatially Steerable Vision-Language-Action Yiran Ling, Qing Lian*, Jinghang Li, Qing Jiang, Tianming Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang Preprint*, 2026 PDF/ Project Page
	Toward Deep Representation Learning for Event-Enhanced Visual Autonomous Perception: the eAP Dataset Jinghang Li, Shichao Li, Qing Lian, Peiliang Li, Xiaozhi Chen, Yi Zhou T-RO, 2026 PDF/ Project Page
	The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs Tianyang Han, Qing Lian*, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang EMNLP* ,2024
	MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi XIE, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang EMNLP ,2024
	OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction Leheng Li, Weichao Qiu, Yingjie Cai, Xu Yan, Qing Lian, Bingbing Liu, Ying-Cong Chen; Arxiv preprint 2410.04932 ,2024
	SyntheOcc: Synthesize Geometric Controlled Street View Images through 3D Semantic MPIs Leheng Li, Weichao Qiu, Yingjie Cai, Xu Yan, Qing Lian, Bingbing Liu, Ying-Cong Chen Arxiv preprint 2410.04932 ,2024
	R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang NAACL Outstanding paper,2024
	Adv3D: generating 3D adversarial examples in driving scenarios with nerf Leheng Li, Qing Lian, Yingcong Chen IROS,2024
	MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learning Helbert PAAT, Qing Lian, Weilong Yao, Tong Zhang ICRA,2024
	Monocular 4D Object Detection by Modeling Dyanmic Objects in Recurrent Qing Lian, Tai Wang, Weilong Yao, Dahua Lin, Jiangmiao Pang CoRL,2024
	Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field Leheng Li, Qing Lian Luozhou Wang, Ningning Ma, Ying-Cong Chen, CVPR ,2023 PDF/ Code
	MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones Tai Wang, Qing Lian Chenming Zhu, Xinge Zhu, Wenwei Zhang Arxiv , 2021 abs.2207.12716 (Waymo Camera-only Challenge solution 2nd place report.) PDF/ Code
	Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency Qing Lian, Yanbo Xu, Weilong Yao, Yingcong Chen, Tong Zhang ECCV, 2022 PDF/ Code
	MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection Qing Lian, Peiliang Li, Xiaozhi Chen CVPR, 2022
	Exploring Geometry Consistency for Monocular 3D Object Detection Qing Lian Botao Ye, Ruijia Xu, Weilong Yao, Tong Zhang CVPR, 2022 arXiv
	An Empirical Study of Invariant Risk Minimization on Deep Models Yong Lin, Qing Lian, Tong Zhang ICML workshop on UDL (Uncertainty & Robustness in Deep Learning), 2021 PDF/ Code
	Disentangled Generative Causal Representation Learning Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian, Zhitang Chen, Tong Zhang JMLR 2021 PDF/ Code
	Known-class aware self-ensemble for open set domain adaptation Qing Lian, Wen Li, Lin Chen, Lixin Duan Arxiv 2019 PDF/ Code
	Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong ICCV 2019 PDF/ Code