Chaoyang Zhu
Scholar

Chaoyang Zhu

Google Scholar ID: jkxdiToAAAAJ
CSE, Hong Kong University of Science and Technology
Multimodal Learning & Reasoning
Citations & Impact
All-time
Citations
849
 
H-index
6
 
i10-index
6
 
Publications
10
 
Co-authors
4
list available
Resume (English only)
Academic Achievements
  • Publications: ICLR 2025 (Open-vocabulary Detection), MM 2024 (Instruction-tuned SAM), TPAMI 2024 (Survey on Open-Vocabulary Perception), ECCV 2022 (SeqTR, Oral, 200+ citations), ICCV 2021 (TRAR, 150+ citations), TNNLS 2019 (actual 1st author, 400+ citations). Awards: Outstanding PGTA honorable mentions by CSE dept, HKUST; Star of future prize awarded by Youtu Lab, Tencent; Outstanding graduate mentions by HDU.
Research Experience
  • Intern at Tencent Youtu Lab (Jul. 2021 - Mar. 2022), Shanghai; PhD candidate at The Hong Kong University of Science and Technology (Aug. 2023 onwards).
Education
  • Ph.D. in Informatics, XMU (2023-present), Advisor: Prof. Rongrong Ji; Master's in Computer Science and Engineering, XMU (2020-2023).
Background
  • Research Interests: Perception tasks, including 2D/3D/video closed-set/open-vocabulary detection/segmentation, involving MLLMs/Point Cloud/NeRF/3DGS. Fascinated by coding, especially CUDA kernels and C++ extensions.
Miscellany
  • Blogging: Hosted via Notion, includes beginner-friendly annotations for CUDA codes of 3D Gaussian Splatting, a basic tutorial on 3D Radiance & Semantic Field, tentative math derivation of diffusion models, and an OpenMMLab API framework.