Related papers: SOFA: A Compute-Memory Optimized Sparsity Accelera…

Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…

Programming-based Pre-trained Language Models (PPLMs) such as CodeBERT have achieved great success in many downstream code-related tasks. Since the memory and computational complexity of self-attention in the Transformer grow quadratically…

SoCs are now designed with their own AI accelerator segment to accommodate the ever-increasing demand of Deep Learning (DL) applications. With powerful MAC engines for matrix multiplications, these accelerators show high computing…

Energy-efficient sense amplifier (SA) circuits are essential for reliable detection of stored memory states in emerging memory systems. In this work, we present four novel sense amplifier (SA) topologies based on phase transition material…

The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at…

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Transformer-based models have demonstrated superior performance in various fields, including natural language processing and computer vision. However, their enormous model size and high demands in computation, memory, and communication…

The memory capacity in edge devices is often limited due to constraints on cost, size, and power. Consequently, memory competition leads to inevitable page swapping in memory-constrained mixed-criticality edge devices, causing slow storage…

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…

Transformer neural networks (TNNs) are being applied across a widening range of application domains, including natural language processing (NLP), machine translation, and computer vision (CV). Their popularity is largely attributed to the…

The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However,…

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. In previous neuromorphic architectures with leaky integrate-and-fire neurons, the crossbar itself has been separated from the…

We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…

Deep learning-based point cloud processing plays an important role in various vision tasks, such as autonomous driving, virtual reality (VR), and augmented reality (AR). The submanifold sparse convolutional network (SSCN) has been widely…

Decomposing matrix A into a lower matrix L and an upper matrix U, which is also known as LU decomposition, is an essential operation in numerical linear algebra. For a sparse matrix, LU decomposition often introduces more nonzero entries in…

Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual…