Picture for Quang Pham

Quang Pham

LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models

Add code
Nov 01, 2024
Viaarxiv icon

Class-incremental Learning for Time Series: Benchmark and Evaluation

Add code
Feb 19, 2024
Viaarxiv icon

CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition

Add code
Feb 04, 2024
Figure 1 for CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Figure 2 for CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Figure 3 for CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Figure 4 for CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Viaarxiv icon

HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts

Add code
Dec 12, 2023
Viaarxiv icon

On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation

Add code
Nov 18, 2023
Figure 1 for On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Figure 2 for On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Figure 3 for On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Figure 4 for On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Viaarxiv icon

Adaptive-saturated RNN: Remember more with less instability

Add code
Apr 24, 2023
Viaarxiv icon

Continual Learning: Fast and Slow

Add code
Sep 06, 2022
Figure 1 for Continual Learning: Fast and Slow
Figure 2 for Continual Learning: Fast and Slow
Figure 3 for Continual Learning: Fast and Slow
Figure 4 for Continual Learning: Fast and Slow
Viaarxiv icon

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

Add code
Mar 30, 2022
Figure 1 for Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
Figure 2 for Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
Figure 3 for Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
Figure 4 for Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
Viaarxiv icon

Learning Fast and Slow for Online Time Series Forecasting

Add code
Feb 23, 2022
Figure 1 for Learning Fast and Slow for Online Time Series Forecasting
Figure 2 for Learning Fast and Slow for Online Time Series Forecasting
Figure 3 for Learning Fast and Slow for Online Time Series Forecasting
Figure 4 for Learning Fast and Slow for Online Time Series Forecasting
Viaarxiv icon

DualNet: Continual Learning, Fast and Slow

Add code
Oct 01, 2021
Figure 1 for DualNet: Continual Learning, Fast and Slow
Figure 2 for DualNet: Continual Learning, Fast and Slow
Figure 3 for DualNet: Continual Learning, Fast and Slow
Figure 4 for DualNet: Continual Learning, Fast and Slow
Viaarxiv icon