Related papers: Proactive Agentic Whiteboards: Enhancing Diagramma…
We introduce the notion of an Active Proxy interface, i.e. tangible models as proxies for physical data referents, supporting interactive exploration of data through active manipulation. We realise an active proxy data visualisation system,…
Comprehending natural language instructions is a charming property for both 2D and 3D layout synthesis systems. Existing methods implicitly model object joint distributions and express object relations, hindering generation's…
Query formulation is increasingly performed by systems that need to guess a user's intent (e.g. via spoken word interfaces). But how can a user know that the computational agent is returning answers to the "right" query? More generally,…
Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve…
Artificial neural networks (ANNs) have shown to be amongst the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, their educational potential is limited in…
Agentic Artificial Intelligence (AI) represents a paradigm shift from reactive systems to proactive, autonomous decision making frameworks. Existing AI-based educational systems remain fragmented and lack multi-level integration across…
A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which require external assistance to recover…
Educational games are an increasingly popular teaching tool in modern classrooms. However, the development of complementary tools for teachers facilitating classroom gameplay is lacking. We present the results of a participatory design…
Data storytelling workflows ask learners to integrate analytical, design, and narrative skills, but instructors rarely have the capacity to provide detailed feedback at each step. Computational and AI-assisted storytelling offers…
Automating teaching presents unique challenges, as replicating human interaction and adaptability is complex. Automated systems cannot often provide nuanced, real-time feedback that aligns with students' individual learning paces or…
We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework exploits the positional, textual, and visual information of…
In the last two decades, Interactive White Boards (IWBs) have been widely available as a pedagogic tool. The usability of these boards for teaching disciplines where complex drawings are needed, we consider debatable in multiple regards. In…
Generative AI challenges traditional assessments by allowing students to produce correct answers without demonstrating understanding or reasoning. Rather than prohibiting AI, this work argues that one way to integrate AI into education is…
While current chat-based AI assistants primarily operate reactively, responding only when prompted by users, there is significant potential for these systems to proactively assist in tasks without explicit invocation, enabling a…
Drawing appropriate diagrams is a useful problem solving heuristic that can transform a problem into a representation that is easier to exploit for solving the problem. A major focus while helping introductory physics students learn problem…
Recent advances in visual analytics have enabled us to learn from user interactions and uncover analytic goals. These innovations set the foundation for actively guiding users during data exploration. Providing such guidance will become…
Artificial intelligence (AI) is increasingly reshaping lifelong learning by introducing new possibilities for personalized, flexible, and data-informed educational practices. In the field of adult education, AI has gained particular…
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior…
Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…
Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating,…