Tao LIN

Tao LIN

École Polytechnique Fédérale de Lausanne

H-index: 21

Europe-Switzerland

About Tao LIN

Tao LIN, With an exceptional h-index of 21 and a recent h-index of 21 (since 2020), a distinguished researcher at École Polytechnique Fédérale de Lausanne, specializes in the field of Distributed Deep Learning, Optimization for DL.

His recent articles reflect a diverse array of research interests and contributions to the field:

Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion

Towards Robust Multi-Modal Reasoning via Model Selection

PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference

Decentralized gradient tracking with local steps

FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering

Tao LIN Information

University

Position

PhD student

Citations(all)

3087

Citations(since 2020)

2974

Cited By

744

hIndex(all)

21

hIndex(since 2020)

21

i10Index(all)

28

i10Index(since 2020)

27

Email

University Profile Page

École Polytechnique Fédérale de Lausanne

Google Scholar

View Google Scholar Profile

Tao LIN Skills & Research Interests

Distributed Deep Learning

Optimization for DL

Top articles of Tao LIN

Title

Journal

Author(s)

Publication Date

Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion

arXiv preprint arXiv:2402.01342

Zexi Li

Zhiqi Li

Jie Lin

Tao Shen

Tao Lin

...

2024/2/2

Towards Robust Multi-Modal Reasoning via Model Selection

arXiv preprint arXiv:2310.08446

Xiangyan Liu

Rongxue Li

Wei Ji

Tao Lin

2023/10/12

PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology

arXiv preprint arXiv:2401.16355

Yuxuan Sun

Hao Wu

Chenglu Zhu

Sunyi Zheng

Qizi Chen

...

2024/1/29

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

SONG Haobo

Hao Zhao

Soumajit Majumder

Tao Lin

2023/10/13

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Jiamu Zheng

Jinghuai Zhang

Futing Wang

Tianyu Du

Tao Lin

2024

DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference

arXiv preprint arXiv:2404.00242

Jinwei Yao

Kaiqi Chen

Kexun Zhang

Jiaxuan You

Binhang Yuan

...

2024/3/30

Decentralized gradient tracking with local steps

Optimization Methods and Software

Yue Liu

Tao Lin

Anastasia Koloskova

Sebastian U Stich

2024/3/12

FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering

arXiv preprint arXiv:2301.12379

Yongxin Guo

Xiaoying Tang

Tao Lin

2023/1/29

Federated Unlearning: a Perspective of Stability and Fairness

arXiv preprint arXiv:2402.01276

Jiaqi Shao

Tao Lin

Xuanyu Cao

Bing Luo

2024/2/2

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

Peng Sun

Bei Shi

Daiwei Yu

Tao Lin

2024/6

DELTA: Diverse Client Sampling for Fasting Federated Learning

NeurIPS 2023 - Advances in Neural Information Processing Systems

Lin Wang

YongXin Guo

Tao Lin

Xiaoying Tang

2023

Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging

arXiv preprint arXiv:2306.01176

Jiamian Wang

Zongliang Wu

Yulun Zhang

Xin Yuan

Tao Lin

...

2023/6/1

FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction

ICML 2023 - International Conference on Machine Learning

Yongxin Guo

Xiaoying Tang

Tao Lin

2023

Test-Time Robust Personalization for Federated Learning

ICLR 2023 - International Conference on Learning Representations

Liangze Jiang*

Tao Lin*

2023/5/1

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

ICCV 2023 - International Conference on Computer Vision

Zexi Li

Xinyi Shang

Rui He

Tao Lin

Chao Wu

2023/3/17

Find Your Optimal Assignments On-the-fly: A Holistic Framework for Clustered Federated Learning

arXiv preprint arXiv:2310.05397

Yongxin Guo

Xiaoying Tang

Tao Lin

2023/10/9

Revisiting Weighted Aggregation in Federated Learning with Neural Networks

ICML 2023 - Proceedings of the 40th International Conference on Machine Learning

Zexi Li

Tao Lin

Xinyi Shang

Chao Wu

2023/2/14

Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks

arXiv preprint arXiv:2307.08013

Haobo Song

Soumajit Majumder

Tao Lin

2023/7/16

On Pitfalls of Test-Time Adaptation

Hao Zhao

Yuejiang Liu

Alexandre Alahi

Tao Lin

2023/6/6

Neural Mode Estimation

Peng Sun

Zhenyu Wen

Yejian Zhou

Zhen Hong

Tao Lin

2023/6/4

See List of Professors in Tao LIN University(École Polytechnique Fédérale de Lausanne)

Co-Authors

H-index: 50
Martin Jaggi

Martin Jaggi

École Polytechnique Fédérale de Lausanne

H-index: 31
Sebastian Urban Stich

Sebastian Urban Stich

École Polytechnique Fédérale de Lausanne

H-index: 11
Anastasia Koloskova

Anastasia Koloskova

École Polytechnique Fédérale de Lausanne

academic-engine