5 citations · 9 across the 10 of their papers we have counts for
4 papers · 1 filter
Counterexamples to Local Reconstruction Gain as a Proxy for Final Fidelity in Residual Completion
Yasuto Hoshi, Daisuke Miyashita, Jun Deguchi
Residual completion augments query-aware sparse attention by estimating the contribution of tokens omitted from the exact sparse computation. We ask whether improving a layer's att…
Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?
Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
In Retrieval-Augmented Generation (RAG) systems, a large number of retrieved chunks are concatenated to form the input context so that users can receive high-quality responses base…
Residual-Mass Accounting for Partial-KV Decoding
Yasuto Hoshi, Daisuke Miyashita, Jun Deguchi
We study a controlled partial-KV decoding setting in which exact unnormalized softmax contributions are computed for sink/tail anchors and a retrieved token set, while the remainin…
On Storage Neural Network Augmented Approximate Nearest Neighbor Search
Taiga Ikeda, Daisuke Miyashita, Jun Deguchi
Large-scale approximate nearest neighbor search (ANN) has been gaining attention along with the latest machine learning researches employing ANNs. If the data is too large to fit i…