相关论文: Interpreting gains and losses in conceptual test u…

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a…

Active perception approaches select future viewpoints by using some estimate of the information gain. An inaccurate estimate can be detrimental in critical situations, e.g., locating a person in distress. However the true information gained…

We propose a new dataset for evaluating question answering models with respect to their capacity to reason about beliefs. Our tasks are inspired by theory-of-mind experiments that examine whether children are able to reason about the…

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this…

Multimodal Large Language Models (MLLMs) have recently emerged as general architectures capable of reasoning over diverse modalities. Benchmarks for MLLMs should measure their ability for cross-modal integration. However, current benchmarks…

This paper presents Integrated Information Theory (IIT) 4.0. IIT aims to account for the properties of experience in physical (operational) terms. It identifies the essential properties of experience (axioms), infers the necessary and…

Concept drift describes unforeseeable changes in the underlying distribution of streaming data over time. Concept drift research involves the development of methodologies and techniques for drift detection, understanding and adaptation.…

Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…

Statistical models such as those derived from Item Response Theory (IRT) enable the assessment of students on a specific subject, which can be useful for several purposes (e.g., learning path customization, drop-out prediction). However,…

In-context learning (ICL) has garnered significant attention for its ability to grasp functions/tasks from demonstrations. Recent studies suggest the presence of a latent task/function vector in LLMs during ICL. Merullo et al. (2024) showed…

Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs). However, standard RL assigns credit only at the level of the final answer, penalizing entire reasoning…

The current work aims to better understand student course experiences for those who reported negative perceptions in introductory physics. We conducted semi-structured interviews with 24 students who reported negative perceptions of their…

Automated short answer grading (ASAG) with large language models (LLMs) is commonly evaluated with aggregate metrics such as macro-F1 and Cohen's kappa. However, these metrics provide limited insight into how grading performance varies…

Integrated Information Theory (IIT) is an audacious attempt to pin down the abstract, phenomenological experiences of consciousness into a rigorous, mathematical framework. We show that IIT's stance in regards to neuronal noise is…

The research presented in this thesis was motivated by the need to improve introductory physics courses. Introductory physics courses are generally the first courses in which students learn to create models to solve complex problems.…

We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or…

We consider the problem of function estimation in the case where the data distribution may shift between training and test time, and additional information about it may be available at test time. This relates to popular scenarios such as…

We investigate student understanding of energy and momentum concepts at the level of introductory physics by designing and administering a 25-item multiple choice test and conducting individual interviews. We find that most students have…

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in…

Computer Adaptive Testing (CAT) aims to accurately estimate an individual's ability using only a subset of an Item Response Theory (IRT) instrument. Many applications also require diverse item exposure across testing sessions, preventing…