Related papers: Pipeline Inspection, Visualization, and Interopera…
The robot manipulation ecosystem currently faces issues with integrating open-source components and reproducing results. This limits the ability of the community to benchmark and compare the performance of different solutions to one another…
Multi-party computing (MPC) has been gaining popularity as a secure computing model over the past few years. However, prior works have demonstrated that MPC protocols still pay substantial performance penalties compared to plaintext,…
Multi-hop QA with annotated supporting facts, which is the task of reading comprehension (RC) considering the interpretability of the answer, has been extensively studied. In this study, we define an interpretable reading comprehension…
Condition monitoring subsea pipelines in low-visibility underwater environments poses significant challenges due to turbidity, light distortion, and image degradation. Traditional visual-based inspection systems often fail to provide…
Recent works have considered two qualitatively different approaches to overcome line-of-sight limitations of 3D sensors used for perception: cooperative perception and infrastructure-augmented perception. In this paper, motivated by…
While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the use of large neural architectures and the application of…
Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…
The application of artificial intelligence technology has greatly enhanced and fortified the safety of energy pipelines, particularly in safeguarding against external threats. The predominant methods involve the integration of intelligent…
With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more…
We introduce pyndri, a Python interface to the Indri search engine. Pyndri allows to access Indri indexes from Python at two levels: (1) dictionary and tokenized document collection, (2) evaluating queries on the index. We hope that with…
The aim of this paper is to develop an approach to visualizations that benefits from distributed computing. Three schemes of process distribution are considered: parallel, pipeline, and expanding pipeline computations. Expanding pipeline…
Executing a control sequence requires computation. While this is a simple observation, developing a framework that relates a controller's required computation to its ability to successfully control a system (e.g. lower control cost) is…
Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of…
In this work we introduce repro_eval - a tool for reactive reproducibility studies of system-oriented information retrieval (IR) experiments. The corresponding Python package provides IR researchers with measures for different levels of…
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…
Water resource management is of crucial societal and economic importance, requiring a strong capacity for anticipating environmental change. Progress in physical process knowledge, numerical methods and computational power, allows us to…
The complexity of modern Just-In-Time (JIT) compiler optimization poses significant challenges for developers seeking to understand and debug intermediate representation (IR) behavior. This work introduces JITScope, an interactive…
Virtual representations of physical critical infrastructures, such as water or energy plants, are used for simulations and digital twins to ensure resilience and continuity of their services. These models usually require 3D point clouds…
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…
Technology-assisted review (TAR) is an important industrial application of information retrieval (IR) and machine learning (ML). While a small TAR research community exists, the complexity of TAR software and workflows is a major barrier to…