Tao Lin

21

Papers

70

Total Citations

Papers (21)

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?

CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors

Learn How to Query from Unlabeled Data Streams in Federated Learning

Multi-Sender Persuasion: A Computational Perspective

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

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

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

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

Ensemble Distillation for Robust Model Fusion in Federated Learning

A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling

Learning Utilities and Equilibria in Non-Truthful Auctions

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

An Improved Analysis of Gradient Tracking for Decentralized Machine Learning

RelaySum for Decentralized Deep Learning on Heterogeneous Data

Adversarial training for high-stakes reliability

Sample Complexity of Forecast Aggregation

DELTA: Diverse Client Sampling for Fasting Federated Learning

Exploring interpretable LSTM neural networks over multi-variable data