Related papers: Superstudent intelligence in thermodynamics
Students in introductory physics courses often rely on ineffective strategies, focusing on final answers rather than understanding underlying principles. Integrating scientific argumentation into problem-solving fosters critical thinking…
Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many…
The Hopfield model, originally inspired by spin-glass physics, occupies a central place at the intersection of statistical mechanics, neural networks, and modern artificial intelligence. Despite its conceptual simplicity and broad…
With the rapid evolution of Artificial Intelligence (AI), its potential implications for higher education have become a focal point of interest. This study delves into the capabilities of AI in Physics Education and offers actionable AI…
This paper focuses on evaluating the effectiveness of Large Language Models at solving embodied robotic tasks using the Meta PARTNER benchmark. Meta PARTNR provides simplified environments and robotic interactions within randomized indoor…
The proliferation of generative AI tools has rendered traditional modular assessments in computing and data-centric education increasingly ineffective, creating a disconnect between academic evaluation and authentic skill measurement. This…
Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited…
The grading of open-ended questions is a high-effort, high-impact task in education. Automating this task promises a significant reduction in workload for education professionals, as well as more consistent grading outcomes for students, by…
We present a thermodynamics experiment suitable for first year undergraduate students employing Stirling Engines to create a demonstration of energy transformation and to measure the mechanical efficiency of such engines. Using an…
Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o3 model, which…
In "Embers of Autoregression" (McCoy et al., 2023), we showed that several large language models (LLMs) have some important limitations that are attributable to their origins in next-word prediction. Here we investigate whether these issues…
This study systematically evaluates 27 frontier Large Language Models on eight biology benchmarks spanning molecular biology, genetics, cloning, virology, and biosecurity. Models from major AI developers released between November 2022 and…
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple…
Accurate estimation of item (question or task) difficulty is critical for educational assessment but suffers from the cold start problem. While Large Language Models demonstrate superhuman problem-solving capabilities, it remains an open…
With the emergence of advanced reasoning models like OpenAI o3 and DeepSeek-R1, large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, their ability to perform rigorous logical reasoning remains an open…
Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and test-time compute scaling. However, many open questions remain regarding the interplay between reasoning token usage and…
Generative artificial intelligence (genAI) is becoming increasingly prevalent and capable in physics, particularly for programming-related tasks. How, then, does genAI affect students' computational modeling? We interviewed 19 undergraduate…
This paper explores using large isomorphic problem banks to overcome many challenges of traditional exams in large STEM classes, especially the threat of content sharing websites and generative AI to the security of exam items. We first…
Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, merely increasing the number of model parameters yields…
Using a novel professional certification survey, the study focuses on assessing the vocational skills of two highly cited AI models, GPT-3 and Turbo-GPT3.5. The approach emphasizes the importance of practical readiness over academic…