Related papers: CQ-CiM: Hardware-Aware Embedding Shaping for Robus…

Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to…

The rapid growth of medical knowledge and increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) have demonstrated value; however, inherent limitations remain. Retrieval-augmented…

Dynamic random access memory (DRAM) is critical to classical computing but notably absent in current superconducting quantum processors. Integrating high-coherence memory units would enable resource-efficient control of logical qubits and…

SRAM-based compute-in-memory (CIM) offers high computational density and energy efficiency for deep neural network (DNN) accelerators, but its limited capacity causes on/off-chip data movement overhead for large DNN models. Existing CIM…

Retrieval-Augmented Generation (RAG) has become critical for knowledge-intensive applications, yet evaluating its performance in vertical domains remains difficult due to domain complexity, diverse context scales, and heavy reliance on…

The increasing amount of data processed on edge and the demand for reducing the energy consumption for large neural network architectures have initiated the transition from traditional von Neumann architectures towards in-memory computing…

Computing-in-memory (CIM) has attracted significant attentions in recent years due to its massive parallelism and low power consumption. However, current CIM designs suffer from large area overhead of small CIM macros and bad programmablity…

Resistive random-access memory (RRAM) provides an excellent platform for analog matrix computing (AMC), enabling both matrix-vector multiplication (MVM) and the solution of matrix equations through open-loop and closed-loop circuit…

Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be…

The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe…

Modern embedding models capture both semantic and syntactic structures of queries, often mapping different queries to similar regions in vector space. This results in non-uniform cluster access patterns in disk-based vector search systems,…

In this research, we develop a taxonomy to conceptualize a comprehensive overview of the constituting characteristics that define retrieval augmented generation (RAG) applications, facilitating the adoption of this technology for different…

Retrieval-Augmented Generation (RAG) is a promising approach to mitigate hallucinations in Large Language Models (LLMs) for legal applications, but its reliability is critically dependent on the accuracy of the retrieval step. This is…

We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop…

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence,…

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Retrieval-augmented generation (RAG) has become a dominant paradigm for mitigating knowledge hallucination and staleness in large language models (LLMs) while preserving data security. By retrieving relevant evidence from private,…

In today's data-centric world, where data fuels numerous application domains, with machine learning at the forefront, handling the enormous volume of data efficiently in terms of time and energy presents a formidable challenge. Conventional…