相关论文: Multi-objective Optimization in CPU Design Space E…

Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of…

The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing,…

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whose pre-training optimizes local representations rather than…

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…

This paper introduces Data-Driven Search-based Software Engineering (DSE), which combines insights from Mining Software Repositories (MSR) and Search-based Software Engineering (SBSE). While MSR formulates software engineering problems as…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Neural Architecture Search (NAS) is increasingly popular to automatically explore the accuracy versus computational complexity trade-off of Deep Learning (DL) architectures. When targeting tiny edge devices, the main challenge for DL…

Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often…

Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…

Generative models for Image Super-Resolution (SR) are increasingly powerful, yet their reliance on self-attention's quadratic complexity (O(N^2)) creates a major computational bottleneck. Linear Attention offers an O(N) solution, but its…

The growing performance gap between multi-core CPUs and main memory necessitates hardware-aware software design paradigms. This study provides a comprehensive performance analysis of Data Oriented Design (DOD) versus the traditional…

The never-ending demand for high performance and energy efficiency is pushing designers towards an increasing level of heterogeneity and specialization in modern computing systems. In such systems, creating efficient memory architectures is…

Efficient and timely calculations of Machine Learning (ML) algorithms are essential for emerging technologies like autonomous driving, the Internet of Things (IoT), and edge computing. One of the primary ML algorithms used in such systems…

Given the ever increasing bandwidth of the visual information available to many intelligent systems, it is becoming essential to endow them with a sense of what is worthwhile their attention and what can be safely disregarded. This article…

Automated fetal head segmentation in ultrasound images is critical for accurate biometric measurements in prenatal care. While existing deep learning approaches have achieved a reasonable performance, they struggle with issues like low…

Neighborhood attention reduces the cost of self attention by restricting each token's attention span to its nearest neighbors. This restriction, parameterized by a window size and dilation factor, draws a spectrum of possible attention…

Computer experiments with both qualitative and quantitative factors are widely used in many applications. Motivated by the emerging need of optimal configuration in the high-performance computing (HPC) system, this work proposes a…