Search Results for author: Ke Wan

Found 4 papers, 2 papers with code

R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration

1 code implementation30 May 2025 Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu

To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models.

Mathematical Reasoning

Causal rule ensemble approach for multi-arm data

no code implementations24 Apr 2025 Ke Wan, Kensuke Tanioka, Toshio Shimokawa

By bridging the gap between accuracy and interpretability, our study contributes a valuable tool for multi-arm HTE estimation, supporting precision medicine.

Interpretable Machine Learning

Online Drift Detection with Maximum Concept Discrepancy

1 code implementation7 Jul 2024 Ke Wan, Yi Liang, Susik Yoon

Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era.

Contrastive Learning Drift Detection

On the properties of Gaussian Copula Mixture Models

no code implementations2 May 2023 Ke Wan, Alain Kornhauser

This paper investigates Gaussian copula mixture models (GCMM), which are an extension of Gaussian mixture models (GMM) that incorporate copula concepts.

Cannot find the paper you are looking for? You can Submit a new open access paper.