Related papers: The effect of multiple internal representations on…
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is non-trivial to manually design a robot controller that combines these modalities which have very different characteristics.…
Neural combinatorial optimization (NCO) has achieved remarkable performance, yet its learned model representations and decision rationale remain a black box. This impedes both academic research and practical deployment, since researchers…
The arrival of AI coding assistants in educational settings presents a paradigm shift, introducing a "new kid in the classroom" for both students and instructors. Thus, understanding the perceptions of these key actors about this new…
We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model…
Undergraduate physics education has greatly benefited from the introduction of computational activities. However, despite the benefits computation has delivered, we still lack a complete understanding of the computationally integrated…
Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations…
Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…
The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning within a much broader spectrum of…
We propose a novel approach for learning causal response representations. Our method aims to extract directions in which a multidimensional outcome is most directly caused by a treatment variable. By bridging conditional independence…
Computer science's increased recognition as a prominent field of study has attracted students with diverse academic backgrounds. This has significantly increased the already high failure rates in introductory courses. To address this…
The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text.…
The theme of the World Conference on Physics Education 2012 is "Context, Culture, and Representations." In this talk I present a brief outline of a theoretical framework that allows us to discuss these issues using a model based in…
Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast,…
Many recent language models (LMs) of Transformers family exhibit so-called in-context learning (ICL) ability, manifested in the LMs' ability to modulate their function by a task described in a natural language input. Previous work curating…
The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent is still a significant…
Despite the wide variety of input types in machine learning, this diversity is often not fully reflected in their representations or model architectures, leading to inefficiencies throughout a model's lifecycle. This paper introduces an…
Pre-trained large language models have demonstrated a strong ability to learn from context, known as in-context learning (ICL). Despite a surge of recent applications that leverage such capabilities, it is by no means clear, at least…
Often in language and other areas of cognition, whether two components of an object are identical or not determines if it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…
Deep learning models have been successfully applied to a variety of software engineering tasks, such as code classification, summarisation, and bug and vulnerability detection. In order to apply deep learning to these tasks, source code…
Socioemotional and regulation processes in learning are important. We add to the understanding of previous work on co-regulation processes in the learning sciences, extending the caregiver-child paradigm and focusing on the teacher-student…