Siyuan Qian

HMI Lab, School of Computer Science

Peking University

Beijing, China

I am a Ph.D. student at the HMI Lab, School of Computer Science, Peking University, advised by Prof. Shanghang Zhang. My research focuses on Embodied AI, exploring the modeling, reasoning, and generalization capabilities of VLA (Vision-Language-Action), World Models, and VLM (Vision-Language Models) in real-world robotic scenarios such as mobile manipulation.

I have published papers at top-tier venues including NeurIPS, RSS, and Nature Computational Science, and serve as a reviewer for conferences such as NeurIPS and ECCV.

Previously, I obtained my B.Eng. in Electronic Information Engineering from Beihang University (BUAA), where I received the highest honor for undergraduate students in the Information category (top 0.3%).

news

Sep 01, 2025	Joined Zhijian Dynamics as a research intern, working on VLA deployment for real mobile manipulation scenarios.
May 01, 2025	Our paper AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation has been accepted to NeurIPS 2025!
Apr 01, 2025	Our paper RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation has been accepted to RSS 2025!
Aug 01, 2024	Started research internship at BAAI (Beijing Academy of Artificial Intelligence), Embodied Multimodal LLM Research Center.
Jan 01, 2023	Our paper on Implicit Neural Image Field for Biological Microscopy Image Compression has been published in Nature Computational Science!

selected publications

NeurIPS
AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

Siyuan Qian^* and others

In Advances in Neural Information Processing Systems (NeurIPS), 2025

Abs Bib Code

We propose AC-DiT, an end-to-end vision-language-action model framework for mobile manipulation. It features a two-stage action generation mechanism (coarse prediction + diffusion refinement) and achieves significantly better performance on multiple benchmarks and real-robot experiments compared to existing methods.
@inproceedings{qian2025acdit, title = {AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation}, author = {Qian, Siyuan and others}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, }
RSS
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation

Siyuan Qian and others

In Robotics: Science and Systems (RSS), 2025

Abs Bib

We propose RoboMIND, a multi-embodiment robot teleoperation dataset covering 107K demonstration trajectories, 479 tasks, 96 object categories, and 4 robot morphologies, including failure cases and digital twin environments. Experiments verify that it significantly improves VLA model success rates and generalization capabilities, making it one of the largest and highest-quality datasets of its kind.
@inproceedings{robomind2025, title = {RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation}, author = {Qian, Siyuan and others}, booktitle = {Robotics: Science and Systems (RSS)}, year = {2025}, }
Nat. Comput. Sci.
Implicit Neural Image Field for Biological Microscopy Image Compression

Siyuan Qian and others

Nature Computational Science, 2023

Abs Bib

We propose an adaptive compression pipeline based on implicit neural representations (INR) that supports arbitrary-shape images and pixel-level decompression. It achieves controllable high compression ratios (up to 512x) and demonstrates effectiveness on various real biological microscopy images, significantly reducing storage and sharing burden while preserving critical analytical information.
@article{qian2023inr, title = {Implicit Neural Image Field for Biological Microscopy Image Compression}, author = {Qian, Siyuan and others}, journal = {Nature Computational Science}, year = {2023}, }