Related papers: Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator E…

Exploiting sparsity underlying neural networks has become one of the most potential methodologies to reduce the memory footprint, I/O cost, and computation workloads during inference. And the degree of sparsity one can exploit has become…

Transformers, composed of QKV generation, attention computation, and FFNs, have become the dominant model across various domains due to their outstanding performance. However, their high computational cost hinders efficient hardware…

The attention mechanism is becoming increasingly popular in Natural Language Processing (NLP) applications, showing superior performance than convolutional and recurrent architectures. However, attention becomes the compution bottleneck…

An indoor, real-time location system (RTLS) can benefit both hospitals and patients by improving clinical efficiency through data-driven optimization of procedures. Bluetooth-based RTLS systems are cost-effective but lack accuracy and…

Analysts routinely use Bayesian hierarchical models to understand natural processes. The no-U-turn sampler (NUTS) is the most widely used algorithm to sample high-dimensional, continuously differentiable models. But NUTS is slowed by high…

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

Recent advances in reasoning Large Language Models (LLMs) are driving the emergence of agentic AI systems. Edge deployment of LLM agents near end users is increasingly necessary to protect data privacy, enable offline use, and provide…

Accelerators for sparse matrix multiplication are important components in emerging systems. In this paper, we study the main challenges of accelerating Sparse Matrix Multiplication (SpMM). For the situations that data is not stored in the…

Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore activation sparsity observed at runtime. We reinterpret…

Vision-and-language navigation (VLN) is a crucial but challenging cross-modal navigation task. One powerful technique to enhance the generalization performance in VLN is the use of an independent speaker model to provide pseudo instructions…

This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-short-term-memory (LSTM) networks instead of their…

Mainstream event-based spatio-temporal representation learning methods typically process event streams by converting them into sequences of event frames, achieving remarkable performance. However, they neglect the high spatial sparsity and…

In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity…

With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain…

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…

Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs. As a prevalent property of the models using the ReLU activation function, activation sparsity has been proven a promising…

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However,…