Related papers: Phaedrus: Predicting Dynamic Application Behavior …
The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at…
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations. While traditional embedding-based profiles lack…
Pre-trained Language Models (PLMs) have demonstrated their superiority and versatility in modern Natural Language Processing (NLP), effectively adapting to various downstream tasks through further fine-tuning. Federated Parameter-Efficient…
Large language models (LLMs) demonstrate remarkable capabilities but face deployment challenges due to their massive parameter counts. While existing compression techniques like pruning can reduce model size, it leads to significant…
In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in…
Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning…
Artificial Intelligence (AI) applications, such as Large Language Models, are primarily driven and executed by Graphics Processing Units (GPUs). These GPU programs (kernels) consume substantial amounts of energy, yet software developers…
With the rapid development of big data and AI technology, programming is in high demand and has become an essential skill for students. Meanwhile, researchers also focus on boosting the online judging system's guidance ability to reduce…
Customized accelerators have revolutionized modern computing by delivering substantial gains in energy efficiency and performance through hardware specialization. Field-Programmable Gate Arrays (FPGAs) play a crucial role in this paradigm,…
Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…
Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing…
Training large language models requires jointly configuring two interdependent aspects of the system: the global batch size, which governs statistical efficiency, and the 3D parallelism strategy, which governs hardware throughput. Existing…
Machine learning models depend critically on feature quality, yet useful features are often scattered across multiple relational tables. Feature augmentation enriches a base table by discovering and integrating features from related tables…
Dynamic program analysis (also known as profiling) is well-known for its powerful capabilities of identifying performance inefficiencies in software packages. Although a large number of dynamic program analysis techniques are developed in…
Learning feature interactions is crucial for click-through rate (CTR) prediction in recommender systems. In most existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all…
Our goal in this dissertation is to provide tools, programming models, and system support for PIM architectures (with a focus on DRAM-based solutions), to ease the adoption of PIM in current and future systems. To this end, we make at least…
Scientific software is often driven by multiple parameters that affect both accuracy and performance. Since finding the optimal configuration of these parameters is a highly complex task, it extremely common that the software is used…
Interprocedural data-flow analyses form an expressive and useful paradigm of numerous static analysis applications, such as live variables analysis, alias analysis and null pointers analysis. The most widely-used framework for…
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by…
The large models, as predicted by scaling raw forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the…