Delin Qu 0010 屈德林

dlqu22 at m dot fudan dot edu dot cn

I am a third-year Ph.D. candidate at the School of Computer Science, Fudan University (FDU) and Shanghai AI Laboratory, Shanghai, China. I'm foutunate to be advised by Prof. Xuelong Li and be part of the IPEC@Team. My research focuses on Embodied AI and 3D Computer Vision, with a long-term vision of achieving L2-level Physical Intelligence. I'm excited about the prospect of an "GPT moment" in Embodied AI, where AI systems can learn to interact with the physical world in a more human-like way.

I was a research intern at Shanghai AI Laboratory with Prof. Xuelong Li. In Dec 2024, I secured the National Natural Science Foundation of China (NSFC) grant to support my research.

I will finish my PhD in fall 2027, and I am actively looking for research internship or exciting startup opportunities.

Email  |  CV  |  GitHub  |  Google Scholar  |  LinkedIn  |  Twitter

headshot
News
Research
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Delin Qu*, Haoming Song*, Qizhi Chen*, Yuanqi Yao, Xinyi Ye, Jiayuan Gu, Bin Zhao, Dong Wang, Xuelong Li,
paper | project page | video | code | model Static Badge
A spatial-enhanced vision-language-action model trained on 1.1 Million real robot episodes, purely huggingFace-based, concise code with efficient performance.
FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives
Qizhi Chen*, Delin Qu*, Haoming Song, Yiwen Tang, Dong Wang, Bin Zhao, Xuelong Li,
paper | project page | video | code
An annotation guidance-free method, dubbed FreeGaussian, that mathematically derives dynamic Gaussian motion from optical flow and camera motion using novel dynamic Gaussian constraints.
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control
Delin Qu*, Qizhi Chen*, Pingrui Zhang, Xianqiang Gao, Dong Wang, Xuelong Li,
Conference on Neural Information Processing Systems (Neurips), 2024
paper | project page | video | code | dataset Static Badge
Embedding language feature to interactive scenes, grounding and manipulating interactable objects with language instructions.
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
Chi Yan*, Delin Qu*, Dan Xu, Bin Zhao, Dong Wang, Zhigang Wang, Xuelong Li, Conference on Computer Vision and Pattern Recognition (CVPR), 2024, (Spotlight, top 2.6%)
paper | project page | video | code
The first to utilize 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system.
Implicit Event-RGBD Neural SLAM
Delin Qu*, Chi Yan*, Yin Jie, Qizhi Chen, Bin Zhao, Dong Wang, Zhigang Wang, Dan Xu, Xuelong Li, Conference on Computer Vision and Pattern Recognition (CVPR), 2024, (Spotlight, top 2.6%)
paper | project page | video | code | dataset Static Badge
The first event-RGBD implicit neural SLAM that leverages event stream and RGBD to overcome challenges in motion blur and lighting variation scenes.
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
Delin Qu*, Yizhen Lao, Bin Zhao, Zhigang Wang, Dong Wang, Xuelong Li,
Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV), 2023
paper | project page | video | code
A geometry-based Quadratic Rolling Shutter (QRS) motion solver, which precisely estimates the high-order correction field of individual pixels.
Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution
Bangyan Liao*, Delin Qu*, Yifei Xue, Huiqing Zhang, Yizhen Lao.
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
paper | project page | video | code
An accurate and fast bundle adjustment solution that estimates the 6-DoF pose with an independent RS model of the camera and the geometry of the environment based on measurements from a rolling shutter camera.
Fast Rolling Shutter Correction in the Wild
Delin Qu*, Bangyan Liao*, Yifei Xue, Huiqing Zhang, Omar Ait Aider, Yizhen Lao.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
paper | project page | video | code | dataset Static Badge
A pixel-wise varying direct RS correction framework that handles locally varying distortion caused by various sources, such as camera motion, moving objects, and even highly varying depth scenes.
Invited Talks


Exploring Spatial Representations for Visual-Language-Action Model
Institute of Artificial Intelligence (TeleAI), China Telecom, hosted by Chenjia Bai, Mar 2025

A spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes, toward the More Generalist Agents System. slides
Selected Projects


FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset
Zhaxizhuoma, Kehui Liu, et.al, Delin Qu, Dong Wang, Yan Ding, Bin Zhao, Xuelong Li paper | project page | video | code

A substantial redesign of the Universal Manipulation Interface system enabling rapid deployment and delivering robust performance in real-world data acquisition.

Optics-driven drone
Xuelong Li, Guan Huang, Zhigang Wang, Delin Qu, Bin Zhao
Science China. Information Sciences, 67(2), 124201, 2024
paper | project page | video | code

A remote charging technology for drones to enhance their autonomy and intelligence during mission execution

Large Model Heterogeneous Intelligent Agent Systems
Kehui Liu, Zixin Tang, et.al, Delin Qu, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
International Conference on Intelligent Robots and Systems (IROS), 2025
paper | project page | video | code

A novel LLM-based task planning framework for collaboration of heterogeneous multi-robot systems including quadrotors, robotic dogs, and robotic arms.

Honors & Awards
  • Sep 2022 - Now: Top Outstanding PhD Student Scholarship of Fudan University in 2025, Tencent Scholarship in 2023, Fudan University Master's Excellence Scholarship in 2022, Outstanding Student Award in 2023, Fudan University's Outstanding Youth League Member in 2024.
  • Sep 2018 - Jun 2022: National Scholarship in 2021, National Scholarship in 2020, National Inspirational Scholarship in 2019, Finalist Prize of Mathematical Contest in Modeling, Second Prize of Asia-Pacific Mathematical Contest in Modeling, Second Prize in National Internet of Things Design Contest, Second Prize in Internet Competition of Hunan Province, Excellence Award in the Huawei AI Cloud Cup, Huawei College Scholarship, Huawei Smart Base Future Star, Excellent Graduation Thesis.
Academic Services
  • Conference Reviewer: CVPR, ICCV, ECCV, ICLR, ICML, and NeurIPS.
  • 2023 Spring
  • strong>: COMP130135.04 Object Oriented Programming, Teaching Assistant.

template adapted from this awesome website