activity
20232025
most citedMasked Generative Modeling with Enhanced Sampling Scheme

2 citations · 2 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2025

Closing the Gap Between Synthetic and Ground Truth Time Series Distributions via Neural Mapping

Daesoo Lee, Sara Malacarne, Erlend Aune

In this paper, we introduce Neural Mapper for Vector Quantized Time Series Generator (NM-VQTSG), a novel method aimed at addressing fidelity challenges in vector quantized (VQ) tim…

cs.LG2024

Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation

Johan Vik Mathisen, Erlend Lokna, Daesoo Lee +1

State-of-the-art approaches in time series generation (TSG), such as TimeVQVAE, utilize vector quantization-based tokenization to effectively model complex distributions of time se…

cs.LG2023

Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling

Daesoo Lee, Sara Malacarne, Erlend Aune

We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE…

physics.geo-ph2023

Latent Diffusion Model for Conditional Reservoir Facies Generation

Daesoo Lee, Oscar Ovanger, Jo Eidsvik +3

Creating accurate and geologically realistic reservoir facies based on limited measurements is crucial for field development and reservoir management, especially in the oil and gas…

cs.LG20232 cited

Masked Generative Modeling with Enhanced Sampling Scheme

Daesoo Lee, Erlend Aune, Sara Malacarne

This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling…