Zhenyi Wang

Affiliations

Department of Computer science and Engineering, University at Buffalo

papers

403

total citations

papers (16)

Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions

ECCV 2022arXiv

citations

Meta Learning on a Sequence of Imbalanced Domains With Difficulty Awareness

ICCV 2021arXiv

citations

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

CVPR 2023arXiv

citations

FREE: Faster and Better Data-Free Meta-Learning

CVPR 2024arXiv

citations

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

ICML 2024arXiv

citations

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

ICML 2024arXiv

citations

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

NEURIPS 2025arXiv

citations

Defense against Model Extraction Attack by Bayesian Active Watermarking

ICML 2024

citations

Data Augmented Flatness-aware Gradient Projection for Continual Learning

ICCV 2023

citations

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

CVPR 2022

citations

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

NEURIPS 2023

citations

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

NEURIPS 2023

citations

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

CVPR 2023

citations

Zhenyi Wang

Affiliations

papers (16)

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Representation Surgery for Multi-Task Model Merging

A Unified and General Framework for Continual Learning

Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions

Meta Learning on a Sequence of Imbalanced Domains With Difficulty Awareness

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

FREE: Faster and Better Data-Free Meta-Learning

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

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

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

Defense against Model Extraction Attack by Bayesian Active Watermarking

Data Augmented Flatness-aware Gradient Projection for Continual Learning

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

papers (16)

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Representation Surgery for Multi-Task Model Merging

A Unified and General Framework for Continual Learning

Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions

Meta Learning on a Sequence of Imbalanced Domains With Difficulty Awareness

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

FREE: Faster and Better Data-Free Meta-Learning

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

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

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

Defense against Model Extraction Attack by Bayesian Active Watermarking

Data Augmented Flatness-aware Gradient Projection for Continual Learning

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation