Qi Zhang

According to our database, Qi Zhang authored at least 10 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2025

On the Theoretical Understanding of Identifiable Sparse Autoencoders and Beyond.

Jingyi Cui, Qi Zhang, Yifei Wang, Yisen Wang

CoRR, June, 2025

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness.

Qi Zhang, Yifei Wang, Jingyi Cui, Xiang Pan, Qi Lei, Stefanie Jegelka, Yisen Wang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Projection Head is Secretly an Information Bottleneck.

Zhuo Ouyang, Kaiwen Hu, Qi Zhang, Yifei Wang, Yisen Wang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining.

Qi Zhang, Tianqi Du, Haotian Huang, Yifei Wang, Yisen Wang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Non-negative Contrastive Learning.

Yifei Wang, Qi Zhang, Yaoyu Guo, Yisen Wang

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Identifiable Contrastive Learning with Automatic Feature Importance Discovery.

Qi Zhang, Yifei Wang, Yisen Wang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the Generalization of Multi-modal Contrastive Learning.

Qi Zhang, Yifei Wang, Yisen Wang

Proceedings of the International Conference on Machine Learning, 2023

A Message Passing Perspective on Learning Dynamics of Contrastive Learning.

Yifei Wang, Qi Zhang, Tianqi Du, Jiansheng Yang, Zhouchen Lin, Yisen Wang

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders.

Qi Zhang, Yifei Wang, Yisen Wang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap.

Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Proceedings of the Tenth International Conference on Learning Representations, 2022