activity
20202025
most citedModeling Uncertain Feature Representation for Domain Generalization

4 citations · 4 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Zixuan Hu, Li Shen, Zhenyi Wang +2

Harmful fine-tuning poses critical safety risks to fine-tuning-as-a-service for large language models. Existing defense strategies preemptively build robustness via attack simulati…

cs.LG2025

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

Yongxian Wei, Anke Tang, Li Shen +3

Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conf…

cs.LG2024

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Yongxian Wei, Zixuan Hu, Li Shen +4

Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen t…

cs.LG2024

FREE: Faster and Better Data-Free Meta-Learning

Yongxian Wei, Zixuan Hu, Zhenyi Wang +3

Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts cons…

cs.LG2023

Task-Distributionally Robust Data-Free Meta-Learning

Zixuan Hu, Yongxian Wei, Li Shen +4

Data-Free Meta-Learning (DFML) aims to enable efficient learning of unseen few-shot tasks, by meta-learning from multiple pre-trained models without accessing their original traini…

cs.LG2023

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Zixuan Hu, Li Shen, Zhenyi Wang +3

Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing…