Scholar
Jiangyong Huang
Google Scholar ID: sBgDVNMAAAAJ
Peking University
Citations & Impact
Citations
387
H-index
5
i10-index
4
Publications
7
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Publications: SceneCOT: Eliciting Chain-of-Thought Reasoning in 3D Scenes (Preprint); LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning (Preprint); Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis (CVPR 2025); Multi-modal Situated Reasoning in 3D Scenes (NeurIPS 2024, Datasets and Benchmarks Track); An Embodied Generalist Agent in 3D World (ICML 2024); ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes (ICCV 2023); Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation (Preprint). Participated in organizing CVPR 2025 Challenges: MSQA (3D Scene Understanding) and ARNOLD (Embodied AI). Hosted ARNOLD Challenge on CVPR 2024 Embodied AI Workshop.
Research Experience
- Reviewer for NeurIPS, CVPR, ICLR, ECCV, ICML, AAAI, RA-L since 2022; Research intern at BIGAI since 2021; TA for Statistical Vision at PKU in Fall 2022 & 2023; TA for Directed Research in AI System at PKU in Summer 2022; Intern at AI Innovation Center, PKU in Spring 2021.
Education
- Ph.D. student at Peking University, advised by Prof. Song-Chun Zhu; graduated from Peking University in 2022 with a Bachelor’s degree.
Background
- Research interests include multi-modal model, 3D scene understanding, and embodied AI. The research goal is to develop embodied generalist agents capable of (1) understanding the 3D world, and (2) following human instructions to interact with the 3D world.
Miscellany
- Feel free to contact him by email, and WeChat is preferred if you want deeper communication.
