Related papers: FRAMER: A Software-based Capability Model

We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such…

Because of their high temporal resolution, increased resilience to motion blur, and very sparse output, event cameras have been shown to be ideal for low-latency and low-bandwidth feature tracking, even in challenging scenarios. Existing…

Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for…

Since modern anti-virus software mainly depends on a signature-based static analysis, they are not suitable for coping with the rapid increase in malware variants. Moreover, even worse, many vulnerabilities of operating systems enable…

Transformers are widely used for solving tasks in natural language processing, computer vision, speech, and music domains. In this paper, we talk about the efficiency of transformers in terms of memory (the number of parameters),…

Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. However, we posit that the very same strength can make…

Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they…

Memory safety errors continue to pose a significant threat to current computing systems, and graphics processing units (GPUs) are no exception. A prominent class of memory safety algorithms is allocation-based solutions. The key idea is to…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Ensemble of machine learning models yields improved performance as well as robustness. However, their memory requirements and inference costs can be prohibitively high. Knowledge distillation is an approach that allows a single model to…

Understanding application resilience (or error tolerance) in the presence of hardware transient faults on data objects is critical to ensure computing integrity and enable efficient application-level fault tolerance mechanisms. However, we…

Collaborative filtering (CF) is widely searched in recommendation with various types of solutions. Recent success of Graph Convolution Networks (GCN) in CF demonstrates the effectiveness of modeling high-order relationships through graphs,…

Accurate click-through rate (CTR) prediction is vital for online advertising and recommendation systems. Recent deep learning advancements have improved the ability to capture feature interactions and understand user interests. However,…

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Capability-based memory isolation is a promising new architectural primitive. Software can access low-level memory only via capability handles rather than raw pointers, which provides a natural interface to enforce security restrictions.…

As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…

With the increase in the number of parameters in large language models, the process of pre-training and fine-tuning increasingly demands larger volumes of GPU memory. A significant portion of this memory is typically consumed by the…

Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models. However, the high memory costs associated with fine-tuning remain…

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales quadratically with…