Zhixuan Pan

According to our database, Zhixuan Pan authored at least 3 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws.

Zhixuan Pan, Shaowen Wang, Jian Li

CoRR, April, 2025

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks.

Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Using scale-equivariant CNN to enhance scale robustness in feature matching.

Yun Liao, Peiyu Liu, Xuning Wu, Zhixuan Pan, Kaijun Zhu, Hao Zhou, Junhui Liu, Qing Duan

Vis. Comput., October, 2024