Chenyu Wang

I am a first-year Ph.D. student in Computing & Data Science at The University of Hong Kong advised by Prof. Yi Ma and Prof. Shenghua Gao. Previously, I received my M.S. and B.E. in Computer Science from ShanghaiTech University, where I was advised by Prof. Shenghua Gao.

My research focuses on 3D generation for manufacturing, in particular parametric CAD generation and its intersection with multimodal large language models (MLLMs). I am broadly interested in building AI systems that understand and produce geometrically precise, physically grounded 3D content.

Email · Google Scholar · GitHub

News

Jun. 2026: Paper Pointer-CAD v2 accepted at ECCV 2026.
Apr. 2026: Workshop The Path to Manufacturing: Evolving 3D Generation to Intelligent Computer-Aided Design accepted at ECCV 2026.
Feb. 2026: Paper Pointer-CAD accepted at CVPR 2026.
Nov. 2025: Paper Seeing from Another Perspective accepted at AAAI 2026.
Sep. 2025: Started Ph.D. at HKU.
Aug. 2024: Paper MLLM-Tool accepted at WACV 2025.
Jun. 2023: Awarded 1st Place in the LTVRR Challenge at the CVPR 2023 L3D-IVU Workshop.

Publications

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

Dacheng Qi, Chenyu Wang, Jingwei Xu, Yi Ma, Shenghua Gao

ECCV 2026

Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection

Dacheng Qi*, Chenyu Wang*, Jingwei Xu, Tianzhe Chu, Zibo Zhao, Wen Liu, Wenrui Ding, Yi Ma, Shenghua Gao

CVPR 2026

paper | code

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Chun-Hsiao Yeh*, Chenyu Wang*, Shengbang Tong, Ta-Ying Cheng, Ruoyu Wang, Tianzhe Chu, Yuexiang Zhai, Yubei Chen, Shenghua Gao, Yi Ma

AAAI 2026

paper | code | benchmark

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

Jingwei Xu*, Chenyu Wang*, Zibo Zhao, Wen Liu, Yi Ma, Shenghua Gao

Under Review

paper | code | dataset

MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning

Chenyu Wang, Weixin Luo, Sixun Dong, Zhengxin Li, Lin Ma, Shenghua Gao

WACV 2025

paper | code

Service

Reviewer (Journals): TNNLS, TMM, TCSVT, Neurocomputing
Reviewer (Conferences): CVPR 2024/2025/2026, ACM MM 2024, IEEE CAI 2024, AAAI 2025/2026, ECCV 2026, NeurIPS 2026