Binzhu Xie

Ph.D. Student @ CUHK

The Chinese University of Hong Kong.

Research Interests

3D Vision (highly related to XR and HCI)

Visual Multimodally Understanding

AIGC related topic

About

Binzhu Xie (谢滨竹) is a first year PhD student at the Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), advised by Prof. Shi Qiu and co-supervised by Prof. Pheng Ann Heng, who leads the CUHK Institute of Medical Intelligence and XR. Previously, Binzhu Xie obtained his BSc (Eng) degree with First Class Honours (2020-2024) from QMUL and BUPT. Since 2023, He has been fortunate to collaborate with MMLab@NTU, working closely with Dr. Jingkang Yang under the supervision of Prof. Ziwei Liu.

News

2026-07

Numgrad-Pull accepted to TVCG.

2026-07

One Paper accepted to ACM MM 2026.

2026-06

ReasonCLIP accepted to ECCV 2026.

2026-01

EgoHandICL accepted to ICLR 2026.

2026-01

Joined CUHK CSE as a PhD student! 🎉

2025-07

One paper accepted to ACM MM 2025.

2025-06

TRIG accepted to ICCV 2025.

2025-03

Two papers accepted to CVPR 2025. EgoLife is fantastic! 🕶️

2025-01

One work accepted as IEEE VR 2025 Posters.

2024-11

One paper accepted in IEEE AIxVR 2025.

2024-08

Joined CUHK CSE as a junior RA! 🎉

2024-07

FunQA accepted to ECCV 2024.

2024-06

Successfully graduated from BUPT and QMUL. 🎉

2024-02

CUVA accepted to CVPR 2024.

2023-12

DocMSU accepted to AAAI 2024.

2023-07

We released FunQA Benchmark and organized a competition with 1 million ¥.

Selected Publications

*: Equal Contribution, †: Corresponding Author

Numgrad-pull: Numerical gradient guided tri-plane representation for surface reconstruction from point clouds

Ruikai Cui^*, Binzhu Xie^*, Shi Qiu, Jiawei Liu, Saeed Anwar, Nick Barnes

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2026

[arxiv][project page]

LingT2I: On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-Image Generation

Sicheng Zhang, Zhonghao Yan, Binzhu Xie, Shi Qiu, Muzammal Naseer, Naveed Akhtar, Mubarak Shah

ACM Multimedia (ACM MM) 2026

[arxiv][project page]

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

Sicheng Zhang, Muzammal Naseer^†, Binzhu Xie, Naufal Suryanto, Shi Qiu, Jamal Bentahar, Naveed Akhtar, Mubarak Shah

European Conference on Computer Vision (ECCV) 2026

[arxiv][project page]

EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning

Binzhu Xie^*, Shi Qiu^*^†, Sicheng Zhang, Yinqiao Wang, Hao Xu, Muzammal Naseer, Chi-Wing Fu, Pheng-Ann Heng

International Conference on Learning Representations (ICLR) 2026

[arxiv][project page]

Generative Multi-Sensory Meditation: Exploring Immersive Depth and Activation in Virtual Reality

Yuyang Jiang, Binzhu Xie, Lina Xu, Xiaokang Lei, Shi Qiu, Luwen Yu^†, Pan Hui

ACM Multimedia (ACM MM) 2025

[arxiv]

Trade-offs in Image Generation: How Do Different Dimensions Interact?

Sicheng Zhang^*, Binzhu Xie^*, Zhonghao Yan^*, Yuli Zhang, Donghao Zhou, Xiaofei Chen, Shi Qiu^†, Jiaqi Liu, Guoyang Xie^†, Zhichao Lu

International Conference on Computer Vision (ICCV) 2025

[arxiv][project page]

EgoLife: Towards Egocentric Life Assistant

EgoLife Team

Computer Vision and Pattern Recognition (CVPR) 2025

[arxiv][project page]

EchoTraffic: Enhancing traffic anomaly understanding with audio-visual insights

Zhenghao Xing^*, Hao Chen^*, Binzhu Xie, Jiaqi Xu, Ziyu Guo, Xuemiao Xu, Jianye Hao, Chi-Wing Fu, Xiaowei Hu^†, Pheng-Ann Heng.

Computer Vision and Pattern Recognition (CVPR) 2025

[openreview][project page]

Creating Virtual Environments with 3D Gaussian Splatting: A Comparative Study

Shi Qiu^†, Binzhu Xie, Qixuan Liu, Pheng-Ann Heng

The IEEE Virtual Reality (IEEE VR) (Poster) 2025

[arxiv]

FunQA: Towards Surprising Video Comprehension

Binzhu Xie^*, Sicheng Zhang^*, Zitang Zhou^*, Bo Li, Yuanhan Zhang, Jack Hessel, Jingkang Yang, Ziwei Liu^†

European Conference on Computer Vision (ECCV) 2024

[arxiv][project page]

Services

Conference Reviewer

CVPR (2026), ICLR (2026), AAAI (2026), ACM MM (2025)., ACL ARR (2025, 2026).