Jun Zhu

About Jun Zhu

Jun Zhu, With an exceptional h-index of 75 and a recent h-index of 62 (since 2020), a distinguished researcher at Tsinghua University, specializes in the field of Machine Learning, Bayesian Methods, Deep Generative Models, Adversarial Robustness, Reinforcement Learning.

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

DGPO: discovering multiple strategies with diversity-guided policy optimization

A comprehensive survey of continual learning: Theory, method and application

Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality

Memory efficient optimizers with 4-bit states

Learning sample difficulty from pre-trained models for reliable prediction

Towards Accelerated Model Training via Bayesian Data Selection

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Dpm-solver-v3: Improved diffusion ode solver with empirical model statistics

Jun Zhu Information

University

Position

Professor of Computer Science

Citations(all)

26205

Citations(since 2020)

21675

Cited By

9919

hIndex(all)

75

hIndex(since 2020)

62

i10Index(all)

256

i10Index(since 2020)

225

Email

University Profile Page

Google Scholar

Jun Zhu Skills & Research Interests

Machine Learning

Bayesian Methods

Deep Generative Models

Adversarial Robustness

Reinforcement Learning

Top articles of Jun Zhu

DGPO: discovering multiple strategies with diversity-guided policy optimization

Proceedings of the AAAI Conference on Artificial Intelligence

2024/3/24

A comprehensive survey of continual learning: Theory, method and application

2024/2/26

Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality

Advances in Neural Information Processing Systems

2024/2/13

Memory efficient optimizers with 4-bit states

Advances in Neural Information Processing Systems

2024/2/13

Learning sample difficulty from pre-trained models for reliable prediction

Advances in Neural Information Processing Systems

2024/2/13

Towards Accelerated Model Training via Bayesian Data Selection

Advances in Neural Information Processing Systems

2024/2/13

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Advances in Neural Information Processing Systems

2024/2/13

Dpm-solver-v3: Improved diffusion ode solver with empirical model statistics

Advances in Neural Information Processing Systems

2024/2/13

Diffusion models and semi-supervised learners benefit mutually with few labels

Advances in Neural Information Processing Systems

2024/2/13

A comprehensive study on robustness of image classification models: Benchmarking and rethinking

arXiv preprint arXiv:2302.14301

2023/2/28

Toward the third generation artificial intelligence

2023/2

All are worth words: A vit backbone for diffusion models

2023

Batch virtual adversarial training for graph convolutional networks

AI Open

2023/1/1

Adversarial Attacks on Face Recognition

2023/12/30

Training transformers with 4-bit integers

Advances in Neural Information Processing Systems

2023/12/15

Incorporating neuro-inspired adaptability for continual learning in artificial intelligence

Nature Machine Intelligence

2023/12

See List of Professors in Jun Zhu University(Tsinghua University)

Co-Authors

academic-engine