Related papers: Not All Scaffolds Are Equal: How Initiation Mode D…

In recent years, Multi-modal Foundation Models (MFMs) and Embodied Artificial Intelligence (EAI) have been advancing side by side at an unprecedented pace. The integration of the two has garnered significant attention from the AI research…

Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine learning, in many…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for…

Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch…

Adaptive systems react to changes in their environment by changing their behavior. Identifying these needed adaptations is very difficult, but central to requirements elicitation for adaptive systems. As the necessary or potential…

In this work, we investigate how implicit neural feed back can accelerate reinforcement learning in complex robotic manipulation settings. While prior electroencephalogram (EEG) guided reinforcement learning studies have primarily focused…

During learning trials, systems are exposed to different failure conditions which may break robotic parts before a safe behavior is discovered. Humans contour this problem by grounding their learning to a safer structure/control first and…

Modern programming languages, such as Python, support language features from several paradigms, such as object-oriented, procedural, and functional. Research has shown that code written in some paradigms can be harder to comprehend, but to…

Adaptive learning often diagnoses precisely yet intervenes weakly, producing help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence…

Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the…

The performance of EM in learning mixtures of product distributions often depends on the initialization. This can be problematic in crowdsourcing and other applications, e.g. when a small number of 'experts' are diluted by a large number of…

Debugging is often a challenging and infuriating experience for secondary school students learning their first text-based programming language. Many students resort to ineffective debugging strategies, making success with solving errors…

Entrepreneurship education equips students to transform innovative ideas into actionable entrepreneurship plans, yet traditional approaches often struggle to provide the personalized guidance and practical alignment needed for success.…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative…

Learning analytics systems increasingly integrate large language models (LLMs) to provide adaptive scaffolding in complex learning environments, yet personalization is often driven by global instructional choices rather than principled…

Current AI-driven educational systems primarily rely on behavioural analytics, performance metrics, and content-level interactions to model learning. While these approaches provide useful indicators of learner activity, they are…

Adaptive learning often diagnoses precisely yet intervenes weakly, yielding help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence…