128 citations · 207 across the 32 of their papers we have counts for
7 papers · 1 filter
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD Detection
Sicong Huang, Jiawei He, Kry Yik Chau Lui
While likelihood is attractive in theory, its estimates by deep generative models (DGMs) are often broken in practice, and perform poorly for out of distribution (OOD) Detection. V…
AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
Qi Yan, Raihan Seraj, Jiawei He +2
Machine-based prediction of real-world events is garnering attention due to its potential for informed decision-making. Whereas traditional forecasting predominantly hinges on stru…
Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
Yu Gong, Hossein Hajimirsadeghi, Jiawei He +2
Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missin…
Jacobian Determinant of Normalizing Flows
Huadong Liao, Jiawei He
Normalizing flows learn a diffeomorphic mapping between the target and base distribution, while the Jacobian determinant of that mapping forms another real-valued function. In this…
Improving Sequential Latent Variable Models with Autoregressive Flows
Joseph Marino, Lei Chen, Jiawei He +1
We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of ref…
Point Process Flows
Nazanin Mehrasa, Ruizhi Deng, Mohamed Osama Ahmed +5
Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature. We propose an intensity-free framework that directly model…
Generative Model with Dynamic Linear Flow
Huadong Liao, Jiawei He, Kunxian Shu
Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex d…