Author

Xiujun Ma

h-index 0 View on Semantic Scholar

2 papers indexed here

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.

Open access Oct 2026

TideKV: Delayed KV eviction via layer-wise chunked prefill for memory-efficient long-context LLM inference

TideKV, an on-GPU cache-construction architecture using layer-major delayed eviction that substantially expands feasible context lengths without sacrificing cache utility is presented.

Yu Wang, Zhu Wang, Ning Hu et al. · Journal of systems architect... · 0 citations

Preprint Aug 2026

More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It

Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time. It also has the potential to serve as a general-purpose front end for a broad range of downstream sampling methods. However, we uncover a striking paradox:...

Hao-Sen Yang, Jia-Xing Sun, Xiujun Ma · 1 citation