Picture for Yuantao Gu

Yuantao Gu

See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers

Add code
Nov 04, 2024
Viaarxiv icon

Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems

Add code
Jun 11, 2024
Viaarxiv icon

EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector

Add code
Jan 03, 2024
Viaarxiv icon

Unravel Anomalies: An End-to-end Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection

Add code
Sep 30, 2023
Viaarxiv icon

Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Data

Add code
Sep 10, 2023
Viaarxiv icon

SageFormer: Series-Aware Graph-Enhanced Transformers for Multivariate Time Series Forecasting

Add code
Jul 04, 2023
Viaarxiv icon

Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework

Add code
Jul 04, 2023
Figure 1 for Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework
Figure 2 for Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework
Figure 3 for Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework
Figure 4 for Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework
Viaarxiv icon

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

Add code
Oct 09, 2021
Figure 1 for Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning
Viaarxiv icon

The Rate of Convergence of Variation-Constrained Deep Neural Networks

Add code
Jun 22, 2021
Figure 1 for The Rate of Convergence of Variation-Constrained Deep Neural Networks
Figure 2 for The Rate of Convergence of Variation-Constrained Deep Neural Networks
Viaarxiv icon

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Add code
May 17, 2021
Figure 1 for Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting
Viaarxiv icon