Related papers: A Context-Switching/Dual-Context ROM Augmented RAM…
On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memory capacity, which restricts usable context. This reduced practical context window creates a…
Analog content-addressable memories (aCAMs) based on memristors provide a promising pathway toward energy-efficient large-scale associative computing for Edge AI and embedded intelligence applications. They have been successfully applied to…
Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly…
3D die-stacked DRAM has emerged as a key technology for delivering high bandwidth and high density for applications such as high-performance computing, graphics, and machine learning. However, different applications place diverse and…
Semantic caching significantly reduces computational costs and improves efficiency by storing and reusing large language model (LLM) responses. However, existing systems rely primarily on matching individual queries, lacking awareness of…
With emerging storage-class memory (SCM) nearing commercialization, there is evidence that it will deliver the much-anticipated high density and access latencies within only a few factors of DRAM. Nevertheless, the latency-sensitive nature…
Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work…
Approximate computing (AC) leverages the inherent error resilience and is used in many big-data applications from various domains such as multimedia, computer vision, signal processing, and machine learning to improve systems performance…
In recent years, a great deal of attention has been paid to the Transformer network for speech recognition tasks due to its excellent model performance. However, the Transformer network always involves heavy computation and large number of…
Much effort has been devoted to device and materials engineering to realize nanoscale resistance random access memory (RRAM) for practical applications, but there still lacks a rational physical basis to be relied on to design scalable…
This paper rethinks translation memory augmented neural machine translation (TM-augmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variance-bias decomposition principle. The finding demonstrates that…
Resistive memories (RRAM) are promising candidates for replacing present nonvolatile memories and realizing storage class memories; hence resistance switching devices are of particular interest. These devices are typically memristive, with…
Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…
VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly…
We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…
This article emphasizes the great potential of big data processing for advanced user- and situation-oriented, so context-aware resource utilization in future wireless networks. In particular, we consider the application of dedicated,…
Detecting anomalies in real-world multivariate time series data is challenging due to complex temporal dependencies and inter-variable correlations. Recently, reconstruction-based deep models have been widely used to solve the problem.…
RRAM-based in-Memory Computing is an exciting road for implementing highly energy efficient neural networks. This vision is however challenged by RRAM variability, as the efficient implementation of in-memory computing does not allow error…
The storage industry is moving toward emerging non-volatile memories (NVMs), including the spin-transfer torque magnetoresistive random-access memory (STT-MRAM) and the phase-change memory (PCM), owing to their high density and low-power…