Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Kan Zhu

Kan Zhu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×1AI×1Architecture×1OS×1

Frequent co-authors

Baris Kasikci2×
Yi Pan1×
Haocheng Xi1×
Xingyang Li1×
Yibo Wu1×
Mayank Mishra1×

Research Timeline

2026
Themis: Software-Defined Hardware Prefetching

A new hardware-software interface for data prefetching is proposed to reduce useless prefetches in datacenter workloads by 40%.

LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization

The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIEmpiricalRecentSep 29, 2026

LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization

Yi Pan, Haocheng Xi, Kan Zhu, Xingyang Li +9 more

The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.

View →
cs.ARcs.OSEmpirical
Recent
Jul 31, 2026

Themis: Software-Defined Hardware Prefetching

Keisuke Kamahori, Neil Adit, Kan Zhu, Yuqi Mai +12 more

A new hardware-software interface for data prefetching is proposed to reduce useless prefetches in datacenter workloads by 40%.

View →