Skip to content

Author

Xiujun Ma

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

Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing KV cache compression reduces decoding memory but typically requires full-prompt prefill to preserve global context, retaining a high construction peak...

Yu Wang, Zhu Wang, Ning Hu et al. · 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

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.