Related papers: DLBricks: Composable Benchmark Generation to Reduc…

We present DLTK, a toolkit providing baseline implementations for efficient experimentation with deep learning methods on biomedical images. It builds on top of TensorFlow and its high modularity and easy-to-use examples allow for a…

Deep Learning (DL) models are widely used in machine learning due to their performance and ability to deal with large datasets while producing high accuracy and performance metrics. The size of such datasets and the complexity of DL models…

Deep learning (DL) is one of the most prominent branches of machine learning. Due to the immense computational cost of DL workloads, industry and academia have developed DL libraries with highly-specialized kernels for each…

Deep learning recommendation models (DLRM) rely on large embedding tables to manage categorical sparse features. Expanding such embedding tables can significantly enhance model performance, but at the cost of increased GPU/CPU/memory usage.…

Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms. Several important works have investigated whether neural networks can effectively…

Effective processing, interpretation, and management of sensor data have emerged as a critical component of cyber-physical systems. Traditionally, processing sensor data requires profound theoretical knowledge and proficiency in…

Deep Learning (DL) has had an immense success in the recent past, leading to state-of-the-art results in various domains such as image recognition and natural language processing. One of the reasons for this success is the increasing size…

Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck is found in the embedding layers, which perform many random…

We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code. BenchPress synthesizes compiling functions by adding new code in any part of an empty or existing…

We introduce DSCodeBench, a new benchmark designed to evaluate large language models (LLMs) on complicated and realistic data science code generation tasks. DSCodeBench consists of 1,000 carefully constructed problems sourced from realistic…

The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted…

Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger…

As large language models (LLMs) continue to advance, the need for up-to-date and well-organized benchmarks becomes increasingly critical. However, many existing datasets are scattered, difficult to manage, and make it challenging to perform…

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in…

We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions or web-only queries, DRBench evaluates agents on multi-step…

As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and…

Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may…

Deep learning (DL) models have achieved paradigm-changing performance in many fields with high dimensional data, such as images, audio, and text. However, the black-box nature of deep neural networks is a barrier not just to adoption in…

Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the…

Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance…