Author

Zhijie Wu

h-index 5 View on Semantic Scholar

We have 1 of 13 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.

Preprint Aug 2026

Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models

Gated VLA-Cache is proposed, a lightweight, training-free extension that augments visual-similarity caching with neural introspection that improves reliability when blind caching hurts.

Zhijie Wu, Kento Kawaharazuka, Kei Okada · 0 citations