Related papers: Implementing Transitive Credit with JSON-LD
Accurate forecasting of recovery rates (RR) is central to credit risk management and regulatory capital determination. In many loan portfolios, however, RR modeling is constrained by data scarcity arising from infrequent default events.…
Semi-structured data formats such as JSON have proved to be useful data models for applications that require flexibility in the format of data stored. However, JSON data often come without the schemas that are typically available with…
High Performance Distributed Computing is essential to boost scientific progress in many areas of science and to efficiently deploy a number of complex scientific applications. These applications have different characteristics that require…
Interdisciplinary collaborations now sweep most fields of the natural and life sciences, necessary to tackle the world's most challenging problems. Yet, the scientific enterprise continues to be dominated by old stereotypes:…
Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…
The sharing and citation of research data is becoming increasingly recognized as an essential building block in scientific research across various fields and disciplines. Sharing research data allows other researchers to reproduce results,…
Trajectory planning in autonomous driving is highly dependent on predicting the emergent behavior of other road users. Learning-based methods are currently showing impressive results in simulation-based challenges, with transformer-based…
In Reward Learning (ReL), we are given feedback on an unknown target reward, and the goal is to use this information to recover it in order to carry out some downstream application, e.g., planning. When the feedback is not informative…
We developed the Learning About STEM Student Outcomes (LASSO) online assessment platform to increase instructor use of research-based assessments (RBAs). LASSO does this by making it easy to collect and analyze high-quality evidence about…
Motivation: Technical debt is a metaphor that describes not-quite-right code introduced for short-term needs. Developers are aware of it and admit it in source code comments, which is called Self- Admitted Technical Debt (SATD). Therefore,…
Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it…
In deep learning, transfer learning (TL) has become the de facto approach when dealing with image related tasks. Visual features learnt for one task have been shown to be reusable for other tasks, improving performance significantly. By…
The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultaneously since the…
While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance…
Atomic swaps enable the transfer of value between the cryptocurrencies of various blockchains without the need to trust an intermediary. In this paper, we propose the concept of atomic loans, which utilize atomic swap technology to allow…
Research has become increasingly reliant on software, serving as the driving force behind bioinformatics, high performance computing, physics, machine learning and artificial intelligence, to name a few. While substantial progress has been…
Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most…
Humans can learn from very few samples, demonstrating an outstanding generalization ability that learning algorithms are still far from reaching. Currently, the most successful models demand enormous amounts of well-labeled data, which are…
Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL). However, designing shaping functions usually requires much expert knowledge and…
In software-engineering research, many empirical studies are conducted with open-source or industry developers. However, in contrast to other research communities like economics or psychology, only few experiments use financial incentives…