arXiv subjects

Zekai Shen

Publications and source records attributed to Zekai Shen.

3 recordsLinked to original sources

arXiv2025

G-KV: Decoding-Time KV Cache Eviction with Global Attention

Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compression has emerged as an effective approach to greatly enhance the efficiency of reasoning. However, existing methods often focus on prompt compression or token eviction with local attention score, overlooking the long-term importance of tokens. We propose G-KV, a KV cache eviction method that employs a global scoring mechanism, combining local and historical attention scores to more accurately assess token importance. Additionally, we introduce post-training techniques, including reinforcement learning and distillation, to optimize models for compressed KV cache settings. The code of this paper is available on: https://github.com/microsoft/G-KV.

cs.CL↗

arXiv2025

A Survey and Benchmarking of Spatial-Temporal Traffic Data Imputation Models

Traffic data imputation is a critical preprocessing step in intelligent transportation systems, underpinning the reliability of downstream transportation services. Despite substantial progress in imputation models, model selection and development for practical applications remains challenging due to three key gaps: 1) the absence of a model taxonomy for traffic data imputation to trace the technological development and highlight their distinct features. 2) the lack of unified benchmarking pipeline for fair and reproducible model evaluation across standardized traffic datasets. 3) insufficient in-depth analysis that jointly compare models across multiple dimensions, including effectiveness, computational efficiency and robustness. To this end, this paper proposes practice-oriented taxonomies for traffic data missing patterns and imputation models, systematically cataloging real-world traffic data loss scenarios and analyzing the characteristics of existing models. We further introduce a unified benchmarking pipeline to comprehensively evaluate 11 representative models across various missing patterns and rates, assessing overall performance, performance under challenging scenarios, computational efficiency, and providing visualizations. This work aims to provide a holistic perspective on traffic data imputation and to serve as a practical guideline for model selection and application in intelligent transportation systems.

cs.LG↗

arXiv2025

Towards An Efficient and Effective En Route Travel Time Estimation Framework

En route travel time estimation (ER-TTE) focuses on predicting the travel time of the remaining route. Existing ER-TTE methods always make re-estimation which significantly hinders real-time performance, especially when faced with the computational demands of simultaneous user requests. This results in delays and reduced responsiveness in ER-TTE services. We propose a general efficient framework U-ERTTE combining an Uncertainty-Guided Decision mechanism (UGD) and Fine-Tuning with Meta-Learning (FTML) to address these challenges. UGD quantifies the uncertainty and provides confidence intervals for the entire route. It selectively re-estimates only when the actual travel time deviates from the predicted confidence intervals, thereby optimizing the efficiency of ER-TTE. To ensure the accuracy of confidence intervals and accurate predictions that need to re-estimate, FTML is employed to train the model, enabling it to learn general driving patterns and specific features to adapt to specific tasks. Extensive experiments on two large-scale real datasets demonstrate that the U-ERTTE framework significantly enhances inference speed and throughput while maintaining high effectiveness. Our code is available at https://github.com/shenzekai/U-ERTTE

cs.AI↗