Skip to content

Author

Keisuke Kamahori

University of Washington

We have 3 of 16 papers

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.

#artificial intelligence Preprint May 2026

Murmur: Efficient Long-Context ASR Inference with Hierarchical Chunking

This paper first analyzes how context length affects the accuracy of long-context ASR models and finds that an intermediate chunk size of about five minutes matches single-pass accuracy while avoiding repetition loops, and proposes Murmur, an inference system for long-form ASR based on hierarchical chunking.

Wei-Tzu Lee, Keisuke Kamahori, Baris Kasikci · 1 citation
#artificial intelligence Preprint Oct 2026

SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning

The results suggest that SPEEDRUNBENCH is a useful testbed for studying agents's strategy formation capabilities as well as being a saturation-resistant evaluation measure, as there is almost always a faster completion time waiting to be discovered.

Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike et al. · 0 citations
Preprint Jul 2026

Themis: Software-Defined Hardware Prefetching

Themis is a profile-guided hardware prefetching solution that implements a novel hardware-software interface for data prefetching: the software directs the hardware on where to prefetch, and the hardware identifies and issues prefetches in the regions of interest.

Keisuke Kamahori, Neil Adit, Kan Zhu et al. · 0 citations

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