5 citations · 9 across the 10 of their papers we have counts for
13 papers
AiSAQ-in-Filtering for DRAM-free Filtered Information Retrieval
Kento Tatsuno, Daisuke Miyashita, Kazunari Sumiyoshi +3
Filtering search is one of the crucial applications of approximate nearest neighbor search (ANNS). In filtering search, label information is used in conjunction with unstructured v…
KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse
Taiga Ikeda, Daisuke Miyashita, Jun Deguchi
KV-cache reuse in large language model serving is commonly limited to exact prompt prefixes, preventing reuse when the same retrieved document appears after different system prompt…
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…
Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage
Hiroaki Yamanaka, Daisuke Miyashita, Takashi Toi +3
Driven by our mission of "uplifting the world with memory," this paper explores the design concept of "memory" that is essential for achieving artificial superintelligence (ASI). R…
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…
Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models
Kengo Nakata, Daisuke Miyashita, Youyang Ng +2
In this paper, we rethink sparse lexical representations for image retrieval. By utilizing multi-modal large language models (M-LLMs) that support visual prompting, we can extract…
AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval
Kento Tatsuno, Daisuke Miyashita, Taiga Ikeda +3
Graph-based approximate nearest neighbor search (ANNS) algorithms work effectively against large-scale vector retrieval. Among such methods, DiskANN achieves good recall-speed trad…
SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI Tool
Youyang Ng, Daisuke Miyashita, Yasuto Hoshi +4
Large Language Model (LLM) based Generative AI systems have seen significant progress in recent years. Integrating a knowledge retrieval architecture allows for seamless integratio…
RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
Yasuto Hoshi, Daisuke Miyashita, Youyang Ng +4
Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-a…
Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?
Yasuto Hoshi, Daisuke Miyashita, Yasuhiro Morioka +3
Neural document retrievers, including dense passage retrieval (DPR), have outperformed classical lexical-matching retrievers, such as BM25, when fine-tuned and tested on specific q…
Revisiting a kNN-based Image Classification System with High-capacity Storage
Kengo Nakata, Youyang Ng, Daisuke Miyashita +3
In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to upd…