Author

Haishan Ye

h-index 4 View on Semantic Scholar

We have 3 of 29 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes

Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugging, or efficient fine-tuning). However, scaling IFs to LLMs is hindered by the intractability of billion-scale Hessian matrices and the prohibitive memory overhead of...

Li-Song He, Yun-Xuan Jiang, Hai-Shan Ye et al. · 0 citations

Jul 2026

Sharper Analysis of Single-Loop Methods for Bilevel Optimization

This work establishes sharper convergence results for single-loop approximate implicit differentiation (AID) and iterative differentiation (ITD) methods, leveraging the proposed analytical framework, decoupled norm analysis (DNA).

Yubo Zhou, Jun Shu, Luo Luo et al. · arXiv.org · 0 citations

Jul 2026

Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning

Theoretical analysis further confirms that EISAM tightens the generalization bound by steering parameters toward flatter minima with reduced curvature, establishing it as a robust, scalable, and broadly applicable optimization solution that advances both the theory and practice in deep learning.

Yao Fu, Chunxia Zhang, Junmin Liu et al. · arXiv.org · 0 citations