lins-lab Goto Github PK

capaboost

[ICLR 2024] Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

cluster_tutorial

code_template

dynmoe

[Preprint] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

fedbr

[ICML 2023] FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction

fedrc

[ICML 2024] FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering

fedthe

[ICLR 2023] Test-time Robust Personalization for Federated Learning

lins-lab.github.io

m3

[ICLR 2024] Towards Robust Multi-Modal Reasoning via Model Selection

rded

[CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

rela

[Preprint] Efficiency for Free: Ideal Data Are Transportable Representations

research_methodology_of_computer_science_and_technology

ttab

[ICML23] On Pitfalls of Test-Time Adaptation