Tao LIN

tlin-taolin's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 17 papers 26 days ago

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

Paper • 2303.10058 • Published Mar 17, 2023

Towards Robust Multi-Modal Reasoning via Model Selection

Paper • 2310.08446 • Published Oct 12, 2023

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models

Paper • 2004.12406 • Published Apr 26, 2020 • 1

On Pitfalls of Test-Time Adaptation

Paper • 2306.03536 • Published Jun 6, 2023

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

Paper • 2401.16355 • Published Jan 29, 2024 • 2

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

Paper • 2205.13462 • Published May 26, 2022

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

Paper • 2405.14297 • Published May 23, 2024 • 2

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

Paper • 2407.01320 • Published Jul 1, 2024

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

Paper • 2301.12379 • Published Jan 29, 2023

Revisiting Weighted Aggregation in Federated Learning with Neural Networks

Paper • 2302.10911 • Published Feb 14, 2023 • 1

PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

Paper • 2407.00203 • Published Jun 28, 2024

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Paper • 2402.09240 • Published Feb 14, 2024 • 3

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published Oct 11, 2024 • 88

Generative Modeling with Explicit Memory

Paper • 2412.08781 • Published Dec 11, 2024

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

Paper • 2312.03526 • Published Dec 6, 2023

Efficient Generative Model Training via Embedded Representation Warmup

Paper • 2504.10188 • Published Apr 14 • 12

Unified Continuous Generative Models

Paper • 2505.07447 • Published 27 days ago • 43

upvoted a paper 26 days ago

Unified Continuous Generative Models

Paper • 2505.07447 • Published 27 days ago • 43