Related papers: A System Level Performance Evaluation for Supercon…

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high…

This article surveys the System Level Synthesis framework, which presents a novel perspective on constrained robust and optimal controller synthesis for linear systems. We show how SLS shifts the controller synthesis task from the design of…

Interactive high-performance computing is doubtlessly beneficial for many computational science and engineering applications whenever simulation results should be visually processed in real time, i.e. during the computation process.…

Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks. However, their substantial computational and memory demands, due to billions of parameters, hinder…

On-device machine learning (ODML) enables intelligent applications on resource-constrained devices. However, power consumption poses a major challenge, forcing a trade-off between model accuracy and power efficiency that often limits model…

System Level Synthesis (SLS) allows us to construct internally stabilizing controllers for large-scale systems. However, solving large-scale SLS problems is computationally expensive and the state-of-the-art methods consider only state…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Artificial intelligence (AI) methods have become critical in scientific applications to help accelerate scientific discovery. Large language models (LLMs) are being considered as a promising approach to address some of the challenging…

The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of…

3D point clouds enhanced the robot's ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks,…

Charge Coupled Devices (CCDs) have been successfully used in several low energy X-ray astronomical satellite over the past two decades. Their high energy resolution and high spatial resolution make them an perfect tool for low energy…

Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternative, fine-tuning smaller models, often sacrifices…

Spatial computing architectures promise a major stride in performance and energy efficiency over the traditional load/store devices currently employed in large scale computing systems. The adoption of high-level synthesis (HLS) from…

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy…

Diffusion models have shown promise in text generation, but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion doesn't model word-order dependencies explicitly and operates on short, fixed…

The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language models (LLMs). Nonetheless, the high rejection rates…

Small Language Models (SLMs) have gained substantial attention due to their ability to execute diverse language tasks successfully while using fewer computer resources. These models are particularly ideal for deployment in limited…

A rich body of prior work has highlighted the existence of communication bottlenecks in synchronous data-parallel training. To alleviate these bottlenecks, a long line of recent work proposes gradient and model compression methods. In this…

Existing satellite remote sensing change detection (CD) methods often crop original large-scale bi-temporal image pairs into small patch pairs and then use pixel-level CD methods to fairly process all the patch pairs. However, due to the…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…