Related papers: Data Programming by Demonstration: A Framework for…
One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate…
Programming is a craft which often demands that learners engage in a significantly high level of individual practice and experimentation in order to acquire basic competencies. However, practice behaviours can be undermined during the early…
Computer programming is among the fundamental aspects of computer science curriculum. Many students first introduced to introductory computer programming courses experience difficulties in learning and comprehending. Vast amount of…
Learning from Demonstration (LfD) has been established as the dominant paradigm for efficiently transferring skills from human teachers to robots. In this context, the Federated Learning (FL) conceptualization has very recently been…
With the rapid commoditization of wearable sensors, detecting human movements from sensor datasets has become increasingly common over a wide range of applications. To detect activities, data scientists iteratively experiment with different…
Creating programs to correctly manipulate data is a difficult task, as the underlying programming languages and APIs can be challenging to learn for many users who are not skilled programmers. Large language models (LLMs) demonstrate…
The differentiable implementation of logic yields a seamless combination of symbolic reasoning and deep neural networks. Recent research, which has developed a differentiable framework to learn logic programs from examples, can even acquire…
Dataset distillation generates a small set of information-rich instances from a large dataset, resulting in reduced storage requirements, privacy or copyright risks, and computational costs for downstream modeling, though much of the…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…
Programming is a core skill in computer science and software engineering (SE), yet identifying and resolving code errors remains challenging for both novice and experienced developers. While Large Language Models (LLMs) have shown…
Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not…
Symbols representing abstract states such as "dish in dishwasher" or "cup on table" allow robots to reason over long horizons by hiding details unnecessary for high-level planning. Current methods for learning to identify symbolic states in…
Instruction tuning fine-tunes pre-trained Multi-modal Large Language Models (MLLMs) to handle real-world tasks. However, the rapid expansion of visual instruction datasets introduces data redundancy, leading to excessive computational…
Labelling user data is a central part of the design and evaluation of pervasive systems that aim to support the user through situation-aware reasoning. It is essential both in designing and training the system to recognise and reason about…
Large language models (LLMs) are demonstrating significant promise as an alternate strategy to facilitate analyses and optimizations of high-performance computing programs, circumventing the need for resource-intensive manual tool creation.…
Deep Learning (DL) is considered the state-of-the-art in computer vision, speech recognition and natural language processing. Until recently, it was also widely accepted that DL is irrelevant for learning tasks on tabular data, especially…
User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user…
We investigate the effect of using human demonstration data in the replay buffer for Deep Reinforcement Learning. We use a policy gradient method with a modified experience replay buffer where a human demonstration experience is sampled…
Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…
The linear programming (LP) approach is, together with value iteration and policy iteration, one of the three fundamental methods to solve optimal control problems in a dynamic programming setting. Despite its simple formulation,…