Related papers: FRAMER: A Software-based Capability Model

Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category, such as 200 subcategories belonging to the bird, which is highly challenging due to large variance in the same…

In software development, the prevalence of unsafe languages such as C and C++ introduces potential vulnerabilities, especially within the heap, a pivotal component for dynamic memory allocation. Despite its significance, heap management…

Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recognition. Existing methods, mostly following the paradigm of 3D…

Almost all modern hardware, from phone SoCs to high-end servers with accelerators, contain memory translation and protection hardware like IOMMUs, firewalls, and lookup tables which make it impossible to reason about, and enforce protection…

Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and…

In classification problems with large output spaces (up to millions of labels), the last layer can require an enormous amount of memory. Using sparse connectivity would drastically reduce the memory requirements, but as we show below, it…

This report provides an introduction to the ensmallen numerical optimization library, as well as a deep dive into the technical details of how it works. The library provides a fast and flexible C++ framework for mathematical optimization of…

Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a different copy of the model is required for each task, this…

The main memory access latency has not much improved for more than two decades while the CPU performance had been exponentially increasing until recently. Approximate memory is a technique to reduce the DRAM access latency in return of…

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…

This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach…

Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sacrificing performance and becoming the de-facto learning…

The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding success. However, since the relation modeling…

A common challenge for most current recommender systems is the cold-start problem. Due to the lack of user-item interactions, the fine-tuned recommender systems are unable to handle situations with new users or new items. Recently, some…

Backdoor attacks pose a significant threat to deep neural networks, particularly as recent advancements have led to increasingly subtle implantation, making the defense more challenging. Existing defense mechanisms typically rely on an…

We have seen significant leapfrog advancement in machine learning in recent decades. The central idea of machine learnability lies on constructing learning algorithms that learn from good data. The availability of more data being made…

We study, formally and experimentally, the trade-off in temporal and spatial overhead when managing contiguous blocks of memory using the explicit, dynamic and real-time heap management system Compact-fit (CF). The key property of CF is…

3D single object tracking within LIDAR point clouds is a pivotal task in computer vision, with profound implications for autonomous driving and robotics. However, existing methods, which depend solely on appearance matching via Siamese…

When implementing functionality which requires sparse matrices, there are numerous storage formats to choose from, each with advantages and disadvantages. To achieve good performance, several formats may need to be used in one program,…

Traditional image annotation tasks rely heavily on human effort for object selection and label assignment, making the process time-consuming and prone to decreased efficiency as annotators experience fatigue after extensive work. This paper…