Organizer Details
Ziyue Li
University of Cologne
Bio:
Dr. Ziyue Li is an assistant professor in the Information System Department, University of Cologne. His research tries to answer the question: how machine learning algorithms can efficiently facilitate spatial-temporal decisions? More than 70% of data are spatial-temporal, such as complex traffic networks, energy, and climate. Dr Li’s research focus are high-dimensional data analytics (such as tensor) and efficient deep learning models (including self-supervised learning, large language models). His work has been published in top-tier AI venues such as AAAI, SIGKDD, ICLR, NeurIPS, TMM, TKDE, awarded with 8+ best paper awards in INFORMS, IISE, and IEEE, and also deployed in real industries as well-proven products, especially in smart mobility. More in Ziyue Li’s Website.
Recent Work: Dr Li’s team currently is working on fine-tuning large language models (LLM) for typical spatiotemporal task, such as traffic flow prediction. LLMs are trained to predict the next word, can we fine-tune LLMs to predict next time-step value? In Dr Li’s latest work, the answer is YES! And excitingly, a slightly fine-tuned GPT-2 can achieve way better prediction results than those end-to-end trained models (More details can be found here). In the next steps, Dr Li will explore combing time-series data with text data, further leveraging LLM’s multi-modality ability.
Yizhou Wang
Northeastern University
Bio:
Yizhou Wang received the B.S. degree in Mathematics and Applied Mathematics (Honors Program) from the School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China, in 2020, and the M.S. degree in Electrical and Computer Engineering from Northeastern University, Boston, MA, in 2023. He is currently working toward the Ph.D. degree in the Department of Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts, under the supervision of Prof. Yun Raymond Fu. His research interests include machine learning, computer vision and data mining. He has published several papers at top-tier conferences including ICLR, CVPR, CIKM, ICDM and IJCAI. He has served as a Reviewer for TPAMI, TKDD, KAIS, ICML, NeurIPS, ICLR, CVPR, ECCV, KDD, AAAI, IJCAI, PAKDD, ICME, ACCV, etc.
Kuan-Chuan Peng
Mitsubishi Electric Research Laboratories (MERL)
Bio:
Dr. Kuan-Chuan Peng is an IEEE Senior Member and a Principal Research Scientist at Mitsubishi Electric Research Labs (MERL) in Cambridge, MA. He received his Ph.D. degree in Electrical and Computer Engineering from Cornell University in 2016. He received a B.S. degree in Electrical Engineering and an M.S. degree in Computer Science from National Taiwan University in 2009 and 2012 respectively. His expertise includes domain adaptation, anomaly detection, attention modeling, and fundamental computer vision and machine learning problems. He organized: (1) 2023 Workshop on Vision-and-Language Algorithmic Reasoning in conjunction with ICCV 2023. (2) 2022 and 2024 Workshop on Artificial Intelligence with Biased or Scarce Data in conjunction with AAAI 2022 and 2024. (3) 2022 Workshop on Vision with Biased or Scarce Data in conjunction with ECCV 2022. (4) 2020, 2021, 2022, 2023, and 2024 Workshop on Fair, Data-Efficient and Trusted Computer Vision in conjunction with CVPR in 2020, 2021, 2022, 2023, and 2024. (5) 2020 and 2021 Workshop on Vision Applications and Solutions to Biased or Scarce Data in conjunction with WACV in 2020 and 2021. (6) 2018 and 2019 Workshop on Vision with Biased or Scarce Data in conjunction with CVPR in 2018 and 2019.