Guofan Fan

Guofan Fan

Final-year MS student major in Computer Science.

😎 Short Bio

I am an incoming research fellow at BAAI, led by Bo lei. Previously, I completed my master’s studies under the supervision of Prof. Andrew C. Yao and Prof. Kaisheng Ma through a joint program between Xi’an Jiaotong University & IIIS, Tsinghua University. I obtained my Bachelor of Engineering from Xi’an Jiaotong University in 2022.

My research interest includes AI interact with brain, 3D computer vision and multi-modal representation learning.

🔥 News

  • 2024-09: One paper is accepted by NeurIPS 2024. 🎉🎉
  • 2024-07: One paper is acccepted by ACMMM 2024, See you in Melbourne, Australia. 🎉🎉
  • 2023-04: One paper is accepted by ICML 2023. 🎉🎉
  • 2022-12: One paper is accepted by AAAI 2023 as Oral presentation. 🎉🎉

📝 Publications

NeurIPS 2024
sym

Learning from Pattern Completion: Self-supervised Controllable Generation

Zhiqiang Chen*, Guofan Fan*, Jinying Gao*, Lei Ma, Bo Lei, Tiejun Huang, Shan Yu

Inspired by the cortical modularization and hippocampal pattern completion, we propose a self-supervised controllable generation (SCG) framework to achieve pattern completion and generate images.

Arxiv Code

ACMMM 2024
sym

Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast

Guofan Fan, Zekun Qi, Wenkai Shi, Kaisheng Ma

We enhance the utilization of color information to improve 3D scene self-supervised learning.

Arxiv Code

ICML 2023
sym

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Zekun Qi, Runpei Dong, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, Li Yi

We propose contrast guided by reconstruct to mitigate the pattern differences between two self-supervised paradigms.

Arxiv Code OpenReview

AAAI 2023 Oral
sym

Language-Assisted 3D Feature Learning for Semantic Scene Understanding.

Junbo Zhang, Guofan Fan, Guanghan Wang, Zhengyuan Su, Kaisheng Ma, Li Yi

We explore the help of textual scene descriptions to guide 3D feature learning toward important geometric attributes and scene context.

Arxiv Code

🎖 Honors and Awards

Competition Awards

  • Semi-Finalist(Top 1%) in AliCloud x NVIDIA - 2022 Global AI Biointelligence Competition (10/3132)
  • Finalist Team(Top 1%) in COMAP’s Mathematical Contest in Interdisciplinary Contest in Modeling (ICM) 2021.
  • Gold Award Team(Highest Award) in The 6th China International College Students’ “Internet+” Innovation and Entrepreneurship Competition.

Honors

  • 2022 Outstanding Graduate, Xi’an Jiaotong University.

📖 Educations

  • 2022.09 - 2025.06 (expected), M.S. Student, Computer Science, Xi’an Jiaotong University.
  • 2018.09 - 2022.06, B.S. in Computer Science, Xi’an Jiaotong University.