Related papers: Online administration of a reasoning inventory in …
The relationship between reading and writing (RRW) is one of the major themes in learning science. One of its obstacles is that it is difficult to define or measure the latent background knowledge of the individual. However, in an academic…
Writing and argumentation are critical to both professional physics and physics education. However, the skill of making an extended argument in writing is often overlooked in physics classrooms, apart from certain practices like lab…
Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…
Physics can be seen as a conceptual approach to scientific problems, a method for discovery, but teaching this aspect of our discipline can be a challenge. We report on a first-time remote teaching experience for a computational physics…
Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic…
In this paper, we introduce BMMR, a large-scale bilingual, multimodal, multi-disciplinary reasoning dataset for the community to develop and evaluate large multimodal models (LMMs). BMMR comprises 110k college-level questions spanning 300…
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…
Computation is becoming an increasingly important part of physics education. However, there are currently few theories of learning that can be used to help explain and predict the unique challenges and affordances associated with…
Randomized experiments (a.k.a. A/B tests) are a powerful tool for estimating treatment effects, to inform decisions making in business, healthcare and other applications. In many problems, the treatment has a lasting effect that evolves…
Social and technical trends have significantly changed methods for evaluating and disseminating computing research. Traditional venues for reviewing and publishing, such as conferences and journals, worked effectively in the past. Recently,…
This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…
Physics lab courses are an essential part of the physics undergraduate curriculum. Learning goals for these classes often include the ability to interpret measurements and uncertainties. The Physics Measurement Questionnaire (PMQ) is an…
Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credit assignment (CA)…
Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted reasoning chains.…
Streaming data routinely generated by mobile phones, social networks, e-commerce, and electronic health records present new opportunities for near real-time surveillance of the impact of an intervention on an outcome of interest via causal…
Developing and making sense of quantitative models is a core practice of physics. Covariational reasoning -- considering how the changes in one quantity affect changes in another, related quantity -- is an essential part of modeling…
Distance education had existed for a long time, then it has undergone a renaissance with the advent of computers and the Internet. Distance education relied on physically delivered material and assessments to students, who work offline at…
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such…
While Aspect-based Sentiment Analysis (ABSA) systems have achieved high accuracy in identifying sentiment polarities, they often operate as "black boxes," lacking the explicit reasoning capabilities characteristic of human affective…
Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…