Siyuan Li (李思远)
Ph.D Candidate, Zhejiang University & Westlake University

Center for Artificial Intelligence Research and Innovation (CAIRI AI Lab)

Location: E2-223, Westlake University, Dunyu Road #600, Xihu District, Hangzhou, Zhejiang, China
News | Research Interest | Education | Internship | Publications | Services | Resume (CV) |

Email: lisiyuan@westlake.edu.cn (prior); lsy@smail.nju.edu.cn
[Google Scholar] [GitHub] [ResearchGate] [ORCID] [Semantic Scholar] [LinkedIn]

Welcome to contacting me about research or internship. Please drop me emails (lisiyuan AT westlake.edu.cn) or WeChat me (Lupin_1998).

News
  • [2024.04] Co-authored paper on Long-sequence model, LongVQ, is accepted by IJCAI 2024, congrats to Zicheng Liu.
  • [2024.01] One paper on semi-supervised learning, SemiReward, is accepted by ICLR 2024.
  • [2024.01] One paper on vision architecture, MogaNet, is accepted by ICLR 2024.
  • [2024.01] Three co-authored paper on AI4Science are accepted by ICLR 2024 (MAPE-PPI wins Spotlight), congrats to Lirong Wu, Zhangyang Gao, and Cheng Tan.
  • [2023.12] Two co-authored paper on protein and video are accepted by AAAI 2024, congrats to Yufei Huang and Xuesong Nie.
  • [2023.10] One paper on self-supervised learning, GenURL, is accepted by TNNLS 2023.
  • [2023.09] One paper on video prediction, OpenSTL, is accepted by NeurIPS 2023.
  • [2023.09] One paper on data augmentation, Decoupled Mixup, is accepted by NeurIPS 2023.
  • [2023.09] Two co-authored paper on AI4Science are accepted by NeurIPS 2023, congrats to Haitao Lin and Jun Xia.
  • [2023.06] Build an open-source toolbox, OpenSTL, for spatio-temporal predictive learning based on PyTorch and update on arXiv (OpenSTL). On updating!
  • [2023.06] One paper on label noise, GNN-Cleaner, is accepted by TKDE 2023, congrats to Jun Xia.
  • [2023.04] One paper on self-supervised learning, A2MIM, is accepted by ICML 2023.
  • [2023.04] Co-authored paper on GNN explanation, MatchExplainer, is accepted by ICML 2023, congrats to Fang Wu.
  • [2023.03] Co-authored paper on sign language, CVT-SLR, is accepted by CVPR 2023 (Highlight), congrats to Zheng Jiangbin.
  • [2023.03] Co-authored paper on video prediction, TAU, is accepted by CVPR 2023, congrats to Cheng Tan.
  • [2023.01] Co-authored paper on molecular graph pre-training, Mole-BERT, is accepted by ICLR 2023, congrats to Jun Xia.
  • [2022.09] One paper on fine-grained self-supervised learning, CVSA, is accepted by BMVC 2022 (Spotlight).
  • [2022.09] Co-authored paper on domain adaptation, DaC, is accepted by NeurIPS 2022, congrats to Ziyi Zhang.
  • [2022.09] Co-authored paper on graph representation, DMAGE, is accepted by Neurocomputing 2022, congrats to Zelin Zang.
  • [2022.08] Co-authored paper on graph attack, AtkSE, is accepted by CIKM 2022, congrats to Zihan Liu.
  • [2022.07] One paper on data augmentation, AutoMix, is accepted by ECCV 2022 (Oral).
  • [2022.07] One paper on self-supervised learning, DLME, is accepted by ECCV 2022.
  • [2022.01] Build an open-source toolbox, OpenBioSeq, for supervised and self-supervised bio-sequence representation learning based on PyTorch. On updating!
  • [2022.03] Co-authored paper on semi-supervised learning, HCR, is accepted by CVPR 2022, congrats to Cheng Tan.
  • [2022.01] Build an open-source toolbox, OpenMixup, for supervised, self- and semi-supervised visual representation learning based on PyTorch. On updating!
  • [2021.10] Co-authored paper on deep clustering, GCML, is accepted by WACV 2022, congrats to Lirong Wu.
  • [2021.07] Got my B.S. degree from Nanjing University!
  • [2021.06] One paper on invertible learning, inv-ML, is accepted by ECML-PKDD 2021.
  • [2020.05] One paper on visual object tracking, TLPG-Tracker, is accepted by IJCAI 2020.

Research Interest

 Currently, I focus on Self-supervised Learning and Data-efficient Deep Learning:

Education

Internship

Publications

Selected Preprints:


Conferences (As First Author):


Conferences (As Co-author):


Journals:


Services

Membership:



Invited Talk:

  • 2024/03/27: Talk on "Modern Convolutional Neural Networks" @ Chengdu Institute of Computer Application, Chinese Academy of Sciences [PPT]
  • 2024/03/12: Talk on "Convolution Kernel Design and Gated Attention for Modern Convolutional Neural Networks" @ ShuZiHuanYu Platform [Video] [PPT]
  • 2023/12/14: Talk on "Mixup Data Augmentation for Computer Vision" @ Chongqing Technology and Business University [PPT]
  • 2023/12/14: Talk on "Introduction to AI Research and Experience Sharing" @ Chongqing Technology and Business University

Program committee member | Reviewer:

  • Conference Reviewer / PC Member:
    • Conference and Workshop on Neural Information Processing Systems (NeurIPS), 2022-2024
    International Conference on Machine Learning (ICML), 2022-2024
    International Conference on Learning Representations (ICLR), 2024
    Dataset and Benchmark Track on Neural Information Processing Systems (NeurIPS), 2023-2024
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022-2024
    International Conference on Computer Vision (ICCV), 2023
    Conference on European Conference on Computer Vision (ECCV), 2022-2024
    AAAI Conference on Artificial Intelligence (AAAI), 2022-2024
    International Joint Conference on Artificial Intelligence (IJCAI), 2023
    ACM Multimedia (ACMMM), 2022, 2024
    IEEE Conference on Multimedia Expo (ICME), 2024
    International Conference on Pattern Recognition (ICPR), 2024
    Asian Conference on Computer Vision (ACCV), 2024
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2022-2024
  • Journal Reviewer:
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    Electronic Research Archive (ERA)
    Neural Computing & Applications (NCA)

Social Awards:

  • 2024: ICLR 2024 Scholarship (Finantial Assistance Awardees)
  • 2023: ICML 2023 Participation Grant

All Rights Reserved by Siyuan Li. Part of page is generated by jemdoc.