← Search

Zichen Liang

2 accepted papers

2025

KAC: Kolmogorov-Arnold Classifier for Continual Learning

CVPR 2025highlight

Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in pr…

2025

Surge: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors

EMNLP 2025

Neural surrogate models are powerful and efficient tools in data mining. Meanwhile, large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, such as generation and understanding. However, an equally important yet underexplored question is whether LLMs can serve a