Related papers: Partial Cross-Compilation and Mixed Execution for …
Soft prompts have emerged as a powerful alternative to adapters in parameter-efficient fine-tuning (PEFT), enabling large language models (LLMs) to adapt to downstream tasks without architectural changes or parameter updates. While prior…
Deep neural networks (DNNs) offer plenty of challenges in executing efficient computation at edge nodes, primarily due to the huge hardware resource demands. The article proposes HYDRA, hybrid data multiplexing, and runtime layer…
With the transition towards a smart grid, Information and Communications Technology (ICT) infrastructures play a growing role in the operation of transmission systems. Cyber-physical systems are usually studied using co-simulation. The…
In this paper, we explore alternative ways to train a neural machine translation system in a multi-domain scenario. We investigate data concatenation (with fine tuning), model stacking (multi-level fine tuning), data selection and…
Multi-task model training has been adopted to enable a single deep neural network model (often a large language model) to handle multiple tasks (e.g., question answering and text summarization). Multi-task training commonly receives input…
Mobile edge computing has become an effective and fundamental paradigm for futuristic autonomous vehicles to offload computing tasks. However, due to the high mobility of vehicles, the dynamics of the wireless conditions, and the…
In recent times, there has been a growing focus on end-to-end autonomous driving technologies. This technology involves the replacement of the entire driving pipeline with a single neural network, which has a simpler structure and faster…
A pivotal task for quantum computing is to speed up solving problems that are both classically intractable and practically valuable. Among these, combinatorial optimization problems have attracted tremendous attention due to their broad…
Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep Neural Network (DNN)…
Dynamic circuits use real-time outcomes of mid-circuit measurements, processed by a classical controller, to adapt subsequent operations during circuit execution. This additional flexibility over static circuits comes at a price.…
Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve this…
Comparative evaluation of several systems is a recurrent task in researching. It is a key step before deciding which system to use for our work, or, once our research has been conducted, to demonstrate the potential of the resulting model.…
The effectiveness of the machine learning methods for real-world tasks depends on the proper structure of the modeling pipeline. The proposed approach is aimed to automate the design of composite machine learning pipelines, which is…
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands. However, prior work has demonstrated that semantic parsing is a difficult multilingual transfer task with low transfer…
Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we…
Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges which utilizes a cluster to train a model in parallel.…
New low-precision accelerators, vector instruction sets, and library functions make maximizing accuracy and performance of numerical code increasingly challenging. Two lines of work$\unicode{x2013}$traditional compilers and numerical…
Edge-cloud computing offloads parts of the computations that traditionally occurs in the cloud to edge nodes,e.g., CDN servers, in order to get closer to the users and reduce latency. To improve performance even further, WebAssembly is…
Runtime-reconfigurable software coupled with reconfigurable hardware is highly desirable as a means towards maximizing runtime efficiency without compromising programmability. Compilers for such software systems are extremely difficult to…