Related papers: Adjusted Objects: An Efficient and Principled Appr…
As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…
Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian optimization. However,…
Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…
With the advent of hundreds of cores on a chip to accelerate applications, the operating system (OS) needs to exploit the existing parallelism provided by the underlying hardware resources to determine the right amount of processes to be…
Dataflow languages provide natural support for specifying constraints between objects in dynamic applications, where programs need to react efficiently to changes of their environment. Researchers have long investigated how to take…
The concept of the Internet of Things (IoT) is a reality now. This paradigm shift has caught everyones attention in a large class of applications, including IoT-based video analytics using smart doorbells. Due to its growing application…
Concurrent linearizable access to shared objects can be prohibitively expensive in a high contention workload. Many applications apply ad-hoc techniques to eliminate the need of synchronous atomic updates, which may result in…
Fitting statistical models is computationally challenging when the sample size or the dimension of the dataset is huge. An attractive approach for down-scaling the problem size is to first partition the dataset into subsets and then fit…
This study develops an algorithm for distributed computing of linear programming problems of huge-scales. Global consensus with single common variable, multiblocks, and augmented Lagrangian are adopted. The consensus is used to partition…
Services are autonomous, self-describing, technology-neutral software units that can be described, published, discovered, and composed into software applications at runtime. Designing software services and composing services in order to…
A major part of debugging, testing, and analyzing a complex software system is understanding what is happening within the system at run-time. Some developers advocate running within a debugger to better understand the system at this level.…
One of the major performance and scalability bottlenecks in large scientific applications is parallel reading and writing to supercomputer I/O systems. The usage of parallel file systems and consistency requirements of POSIX, that all the…
For the right application, the use of programming paradigms such as functional or logic programming can enormously increase productivity in software development. But these powerful paradigms are tied to exotic programming languages, while…
Modern retrieval systems are often driven by an underlying machine learning model. The goal of such systems is to identify and possibly rank the few most relevant items for a given query or context. Thus, such systems are typically…
The paper deals with the developing of the methodological backgrounds for the modeling and simulation of complex dynamical objects. Such backgrounds allow us to perform coordinate transformation and formulate the algorithm of its usage for…
A number of high-level languages and libraries have been proposed that offer novel and simple to use abstractions for concurrent, asynchronous, and distributed programming. The execution models that realise them, however, often change over…
Ensuring Service Level Objectives (SLOs) in large-scale architectures, such as Distributed Computing Continuum Systems (DCCS), is challenging due to their heterogeneous nature and varying service requirements across different devices and…
Recent advances in crowd counting have achieved promising results with increasingly complex convolutional neural network designs. However, due to the unpredictable domain shift, generalizing trained model to unseen scenarios is often…
Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…
The advent of parameter-efficient fine-tuning methods has significantly reduced the computational burden of adapting large-scale pretrained models to diverse downstream tasks. However, existing approaches often struggle to achieve robust…