M1.R3.4
HIERARCHICAL FLOW MATCHING FOR PROBABILISTIC TIME SERIES FORECASTING
Christopher Lee, Zhizhen Zhao, University of Illinois Urbana-Champaign, United States
Session:
M1.R3: Generative Models for Data Science Lecture
Track:
Special Sessions
Location:
Isabela III
Presentation Time:
Mon, 15 Dec, 11:20 - 11:40 AST (UTC -4)
Session Co-Chairs:
Harlin Lee, University of North Carolina at Chapel Hill and Yuejie Chi, Carnegie Mellon University
Session M1.R3
M1.R3.1: Can Agentic AI Match the Performance of Human Data Scientists?
An Luo, Jin Du, Fangqiao Tian, Xun Xian, Robert Specht, University of Minnesota, United States; Ganghua Wang, University of Chicago, United States; Xuan Bi, University of Minnesota, United States; Charles Fleming, Jayanth Srinivasa, Ashish Kundu, Cisco Research, United States; Mingyi Hong, Jie Ding, University of Minnesota, United States
M1.R3.2: DIFFUSION MODELS LEARN LOW-DIMENSIONAL DISTRIBUTIONS VIA SUBSPACE CLUSTERING
Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, University of Michigan, Ann Arbor, United States; Yi Ma, University of California, Berkeley, United States; Qing Qu, University of Michigan, Ann Arbor, United States
M1.R3.3: MULTI-MODAL LATENT DIFFUSION USING INFORMATION DISENTANGLING AUTOENCODERS
Daniel Siromani, Pier Luigi Dragotti, Imperial College London, United Kingdom
M1.R3.4: HIERARCHICAL FLOW MATCHING FOR PROBABILISTIC TIME SERIES FORECASTING
Christopher Lee, Zhizhen Zhao, University of Illinois Urbana-Champaign, United States
M1.R3.5: ADAPTIVE MULTIMODAL PROTEIN PLUG-AND-PLAY WITH DIFFUSION-BASED PRIORS
Amartya Banerjee, University of North Carolina at Chapel Hill, United States; Xingyu Xu, Carnegie Mellon University, United States; Caroline Moosmüller, Harlin Lee, University of North Carolina at Chapel Hill, United States
Contacts