相关论文: Transformer^-1: Input-Adaptive Computation for Res…

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

We use a data-driven approach to model a three-dimensional turbulent flow using cutting-edge Deep Learning techniques. The deep learning framework incorporates physical constraints on the flow, such as preserving incompressibility and…

Machine learning has recently gained traction as a way to overcome the slow accelerator generation and implementation process on an FPGA. It can be used to build performance and resource usage models that enable fast early-stage design…

Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often…

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to several key advantages in latency, privacy and always-on availability. However, due to limited computing resources, efficient DNN…

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…

Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper…

Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large transformer models by reducing activation recomputation.…

We develop an adaptive control architecture to achieve stabilization and command following of uncertain dynamical systems with improved transient performance. Our framework consists of a new reference system and an adaptive controller. The…

Distributed computing systems often consist of hundreds of nodes, executing tasks with different resource requirements. Efficient resource provisioning and task scheduling in such systems are non-trivial and require close monitoring and…

Deep learning has proven to be a highly effective tool for a wide range of applications, significantly when leveraging the power of multi-loss functions to optimize performance on multiple criteria simultaneously. However, optimal selection…

Large language models exhibit sophisticated capabilities, yet understanding how they work internally remains a central challenge. A fundamental obstacle is that training selects for behavior, not circuitry, so many weight configurations can…

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade performance due to their reliance on spatially…

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

The growing demand for optimal and low-power energy consumption paradigms for IOT devices has garnered significant attention due to their cost-effectiveness, simplicity, and intelligibility. In this article, an AI hardware energy-efficient…

Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired…

Automated co-design of machine learning models and evaluation hardware is critical for efficiently deploying such models at scale. Despite the state-of-the-art performance of transformer models, they are not yet ready for execution on…

The recently proposed Forgetting Transformer (FoX) incorporates a forget gate into softmax attention and has shown consistently better or on-par performance compared to the standard RoPE-based Transformer. Notably, many attention heads in…