Related papers: An Early Exploration of Deep-Learning-Driven Prefe…
The extraction of useful deep features is important for many computer vision tasks. Deep features extracted from classification networks have proved to perform well in those tasks. To obtain features of greater usefulness, end-to-end…
Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…
Constrained low-rank matrix approximations have been known for decades as powerful linear dimensionality reduction techniques to be able to extract the information contained in large data sets in a relevant way. However, such low-rank…
Indirect memory accesses frequently appear in applications where memory bandwidth is a critical bottleneck. Prior indirect memory access proposals, such as indirect prefetchers, runahead execution, fetchers, and decoupled access/execute…
Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding…
Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…
When compared to blocking concurrency, non-blocking concurrency can provide higher performance in parallel shared-memory contexts, especially in high contention scenarios. This paper proposes FLeeC, an application-level cache system based…
In today's data-centric world, where data fuels numerous application domains, with machine learning at the forefront, handling the enormous volume of data efficiently in terms of time and energy presents a formidable challenge. Conventional…
Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…
Federated learning is a popular paradigm for machine learning. Ideally, federated learning works best when all clients share a similar data distribution. However, it is not always the case in the real world. Therefore, the topic of…
Recent years have witnessed an explosive growth of mobile devices. Mobile devices are permeating every aspect of our daily lives. With the increasing usage of mobile devices and intelligent applications, there is a soaring demand for mobile…
Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…
Services and applications based on the Memento Aggregator can suffer from slow response times due to the federated search across web archives performed by the Memento infrastructure. In an effort to decrease the response times, we…
Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive.…
Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads…
This work advocates the use of deep learning to perform max-min and max-prod power allocation in the downlink of Massive MIMO networks. More precisely, a deep neural network is trained to learn the map between the positions of user…
The Memory stress (Mess) framework provides a unified view of the memory system benchmarking, simulation and application profiling. The Mess benchmark provides a holistic and detailed memory system characterization. It is based on hundreds…
Minimizing job scheduling time is a fundamental issue in data center networks that has been extensively studied in recent years. The incoming jobs require different CPU and memory units, and span different number of time slots. The…
Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle…
Recent deep learning models such as ChatGPT utilizing the back-propagation algorithm have exhibited remarkable performance. However, the disparity between the biological brain processes and the back-propagation algorithm has been noted. The…