Author

Shunsuke Yokokawa

View on Semantic Scholar

1 paper 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.

Preprint Jul 2026

FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness

FlashBEV is proposed, a fully fused and IO-aware execution strategy mathematically equivalent to Tensorized Sampling-VT (same operator output) while substantially reducing global memory traffic and kernel-launch overhead, and achieves more than an order of magnitude lower peak GPU memory and significant inference-latency speedups.

Shunsuke Yokokawa, Hironori Kasahara · 0 citations