Search for: All records

Many AI-based code assistants, particularly those poweredby Large Language Models (LLMs), provide completesolutions, which can reduce active problem solving andlimit incidental learning, the acquisition of knowledge asa byproduct of task engagement. Such learning requiresactive participation rather than passive acceptance ofAI-generated answers, which might be incorrect. This studyexamines how incidental learning can be supported throughguided interaction. We present LeetCoach, an LLM-assistedcoding platform that applies a cognitive forcing strategy,prompting learners to reflect and take incremental stepsinstead of receiving full solutions. Using LeetCode-stylequestions, we conducted a pilot study with novice andadvanced college programmers who completed tasks underassisted and unassisted conditions. Novices showedsubstantial post-test gains despite receiving AI guidanceonly during the intervention, suggesting that incidentalexposure improved later performance. Advanced learnersshowed smaller gains. Across both groups, participantsrequired fewer debugging attempts in the post-test comparedto earlier stages, indicating improved debugging efficiencyand algorithmic understanding. These findings provide earlyevidence that LLMs can be designed to promote indirectlearning while shaping problem-solving strategies. Thiswork offers a proof of concept for cognitively informedtutoring systems in computer science education anddiscusses implications for integrating LLMs to enhance bothimmediate outcomes and lasting skill development. 

The performance of object detection models in adverse weather conditions remains a critical challenge for intelligent transportation systems. Since advancements in autonomous driving rely heavily on extensive datasets, which help autonomous driving systems be reliable in complex driving environments, this study provides a comprehensive dataset under diverse weather scenarios like rain, haze, nighttime, or sun flares and systematically evaluates the robustness of state-of-the-art deep learning-based object detection frameworks. Our Adverse Driving Conditions Dataset features eight single weather effects and four challenging mixed weather effects, with a curated collection of 50,000 traffic images for each weather effect. State-of-the-art object detection models are evaluated using standard metrics, including precision, recall, and IoU. Our findings reveal significant performance degradation under adverse conditions compared to clear weather, highlighting common issues such as misclassification and false positives. For example, scenarios like haze combined with rain cause frequent detection failures, highlighting the limitations of current algorithms. Through comprehensive performance analysis, we provide critical insights into model vulnerabilities and propose directions for developing weather-resilient object detection systems. This work contributes to advancing robust computer vision technologies for safer and more reliable transportation in unpredictable real-world environments. 

Traffic event retrieval is one of the important tasks for intelligent traffic system management. To find accurate candidate events in traffic videos corresponding to a specific text query, it is necessary to understand the text query's attributes, represent the visual and motion attributes of vehicles in videos, and measure the similarity between them. Thus we propose a promising method for vehicle event retrieval from a natural-language-based specification. We utilize both appearance and motion attributes of a vehicle and adapt the COOT model to evaluate the semantic relationship between a query and a video track. Experiments with the test dataset of Track 5 in AI City Challenge 2021 show that our method is among the top 6 with a score of 0.1560.