16 accepted papers
Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue history, causing the model’s memory footprint to quickly ex…
Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associated with interpretability of feed-forward modules (FFNs) and propose MemoryLLM, which aims to decoup…
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this sparsity into practical performance, an expert caching mechanism is required. Previous works have proposed hardware-centric …
User-defined keyword spotting on a resource-constrained edge device is challenging. However, keywords are often bounded by a maximum keyword length, which has been largely under-leveraged in prior works. Our analysis of keyword-length distribution shows that user-defined keyword spotting can be trea…
With the rapid expansion in the scale of large language models (LLMs), enabling efficient distributed inference across multiple computing units has become increasingly critical. However, communication overheads from popular distributed inference techniques such as Tensor Parallelism pose a significa…
Spotting user-defined/flexible keywords represented in text frequently uses an expensive text encoder for joint analysis with an audio encoder in an embedding space, which can suffer from heterogeneous modality representation (i.e., large mismatch) and increased complexity. In this work, we propose…
Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization scheme, KV-Runahead to accelerate the prompt phase. The key obs…
Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challeng…
Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more parameters) to improve the predictive power may not be viab…
Streaming keyword spotting is a widely used solution for activating voice assistants. Methods based on Deep Neural Networks with Hidden Markov Model (DNN-HMM) have proven to be efficient and widely adopted in this space, primarily because of the ability to detect and identify the start and end of th…
This paper explores the possibility of using visual object detection techniques for word localization in speech data. Object detection has been thoroughly studied in the contemporary literature for visual data. Noting that an audio can be interpreted as a 1-dimensional image, object localization tec…
DNN pruning is a popular way to reduce the size of a model, improve the inference latency, and minimize the power consumption on DNN accelerators. However, existing approaches might be too complex, expensive or ineffective to apply to a variety of vision/language tasks, DNN architectures and to hono…
Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering layer (DKM) and its application to train-time weight clusteri…
Neural Architecture Search (NAS) is an open and challenging problem in machine learning. While NAS offers great promise, the prohibitive computational demand of most of the existing NAS methods makes it difficult to directly search the architectures on large-scale tasks. The typical way of conductin…
SNOW is an efficient learning method to improve training/serving throughput as well as accuracy for transfer and lifelong learning of convolutional neural networks based on knowledge subscription. SNOW selects the top-K useful intermediate feature maps for a target task from a pre-trained and frozen…
Convolution is a critical component in modern deep neural networks, thus several algorithms for convolution have been developed. Direct convolution is simple but suffers from poor performance. As an alternative, multiple indirect methods have been proposed including im2col-based convolution, FFT-bas…