I am current a third-year Ph.D. student (Sep. 2022 - Jun. 2027, expected) in the School of Information Science and Technology, Fudan University, supervised by Prof. Tao Chen. I am also fortunate to work closely with Dr. Bo Zhang from Shanghai AI Lab. Before this, I obtained my Bachelor’s degree in Electronic Engineering also from Fudan University (Sep. 2018 - Jun. 2022). I work in the fields of deep learning and computer vision, with particular focuses on 3D perception, transfer learning, multi-modal LLM. My research pursues to develop vision-language systems that possess the capacity to comprehend, reason, and envision the physical world and explore using AI for scientific discovery.

🔥 News

  • 2024.10:  🎉🎉 I recieve the national scholarship.

  • 2024.09:  🎉🎉 Two papers (AdaptiveDiffusion and 3DET-Mamba) are accepted by NeurIPS 2024. One is about training-free acceleration of diffusion model, another is about mamba architecture in 3D detection.

  • 2024.07:  🎉🎉 One paper (Reg-TTA3D) is accepted by ECCV 2024. We explore test-time adaptive 3d object detection for the first time.

  • 2024.01:  🎉🎉 One paper (ReSimAD) is accepted by ICLR 2024. We propose a zero-shot generalization framework by reconstructing mesh and simulating target point clouds.

  • 2023.09:  🎉🎉 One Paper (AD-PT) is accepted by NeurIPS 2023.We explore 3D pre-training pipeline to obtain backbones with strong generalization capability.

  • 2023.02:  🎉🎉 Two Papers (Bi3D and Uni3D) are accepted by CVPR 2023. One is about active domain adaptation for 3D object detection, another is about multi-dataset training for 3d object detection.

  • 2022.07:  🎉🎉 One Paper (HelixFormer) is accepted by ACM'MM 2022. We explore Transformer architecture on few-shot fine-grained classification task.

📝 Publications

NeurIPS 2024
sym

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

Hancheng Ye*, Jiakang Yuan*, Renqiu Xia, Xiangchao Yan, Tao Chen, Junchi Yan, Botian Shi, Bo Zhang

[Project][Paper]

  • Propose AdaptiveDiffusion to adaptively reduce the noise prediction steps during the denoising proces guided by the third-order latent difference.
NeurIPS 2024
sym

3DET-Mamba: State Space Model for End-to-End 3D Object Detection

Mingsheng Li*, Jiakang Yuan*, Sijin Chen, Lin Zhang, Anyu Zhu, Xin Chen, Tao Chen

[Project][Paper]

  • Exploit the potential of Mamba architecture on 3D scene-level perception for the first time.
ECCV 2024
sym

Reg-TTA3D: Better Regression Makes Better Test-time Adaptive 3D Object Detection

Jiakang Yuan, Bo Zhang, Kaixiong Gong, Xiangyu Yue, Botian Shi, Yu Qiao, Tao Chen

[Project][Paper]

  • Explore a new task named test-time domain adaptive 3D object detection and propose a pseudo-label-based test-time adaptative 3D object detection method.
ICLR 2024
sym

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

Bo Zhang*, Xinyu Cai*, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao

[Project][Paper]

  • Provide a new perspective and approach of alleviating the domain shifts, by proposing a Reconstruction-Simulation-Perception scheme.
NeurIPS 2023
sym

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

[Project][Paper]

  • Build a large-scale pre-training point-cloud dataset with diverse data distribution, and meanwhile learn generalizable representations.
CVPR 2023
sym

Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

[Project][Paper]

  • Propose a Bi-domain active learning approach which select samples from both source and target domain to solve the cross-domain 3D object detection task.
CVPR 2023
sym

Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection

Bo Zhang, Jiakang Yuan, Botian Shi, Tao Chen, Yikang Li, Yu Qiao

[Project][Paper]

  • Present a Uni3D which tackle multi-dataset 3D object detection from data-level and semantic-level.
ACM'MM 2022
sym

Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Bo Zhang*, Jiakang Yuan*, Baopu Li, Tao Chen, Jiayuan Fan, Botian Shi

[Project][Paper]

  • Propose a Transformer-based double-helix model to achieve the cross-image object semantic relation mining in a bidirectional and symmetrical manner.

📖 Educations

  • 2022.09 - Now, Ph.D. Candidate, School of Information Science and Technology, Fudan University.
  • 2018.06 - 2022.06, Bachelor Degree, School of Information Science and Technology, Fudan University.

💬 Invited Talks

  • 2023.09, Invited talk of Effcient Pre-training of Autonomous Driving. [Video]
  • 2023.07, Invited talk of Towards 3D General Representation at Techbeat. [Video]
  • 2023.03, Invited talk of Transferable of Autonomous Driving. [Video]

💻 Internships

📝 Academic Services

  • Reviewer of ICML, ICLR, ECCV, T-CSVT.