Video-based learning (VBL) has become a dominant method for learning practical skills, yet accessibility guidelines provide limited guidance for users with cognitive differences. In particular, challenges that individuals with Borderline Intellectual Functioning (BIF) encounter in video-based learning remain largely underexplored, despite VBL’s potential to support their learning through features like self-paced viewing and visual demonstration. To address this gap, we conducted a series of studies with BIF individuals and caretakers to comprehensively understand their VBL challenges. Our analysis revealed challenges stemming from misalignment between user cognitive characteristics and video elements (e.g., overwhelmed by pacing and density, difficulty inferring omitted content), and experiential factors intensifying challenges (e.g., low self-efficacy). While participants employed coping strategies such as repetitive viewing to address these challenges, these strategies could not overcome fundamental gaps with video. We further discuss the design implications on both content and UI-level features for BIF and broader groups with cognitive diversities.

The aesthetic design of 3D scenes in game content enhances players’ experience by inducing desired emotions. Creating emotionally engaging scenes involves designing low-level features, such as color distribution, contrast, and brightness. This study presents LumiMood, an AI-driven creativity support tool (CST) that automatically adjusts lighting and post-processing to create moods for 3D scenes. LumiMood supports designers by synthesizing reference images, creating mood templates, and providing intermediate design steps. Our formative study with 10 designers identified distinct challenges in mood design based on the participants’ experience levels. A user study involving 40 designers revealed that using LumiMood benefits the designers by streamlining workflow, improving precision, and increasing mood intention accuracy. Results indicate that LumiMood supports clarifying mood concepts and improves interpretation of lighting and post-processing, thus resolving the challenges. We observe the effect of template based designing and discuss considerable factors for AI-driven CSTs for users with varying levels of experiences.

Large Language Models (LLMs) have shown promise in Automated Essay Scoring (AES), but their zero-shot and few-shot performance often falls short compared to state-of-the-art models and human raters. However, fine-tuning LLMs for each specific task is impractical due to the variety of essay prompts and rubrics used in real-world educational contexts. This study proposes a novel approach combining LLMs and Comparative Judgment (CJ) for AES, using zero-shot prompting to choose between two essays. We demonstrate that a CJ method surpasses traditional rubric-based scoring in essay scoring using LLMs.

This paper presents a deep neural network based test vector generation method for dynamic verification of memory devices. The proposed method is built on reinforcement learning framework, where the action is input stimulus on device pins and the reward is coverage score of target circuitry. The developed agent efficiently explores high-dimensional and large action space by using policy gradient method with Å-nearest neighbor search, transfer learning, and replay buffer. The generated test vectors attained the coverage score of 100% for fifteen representative circuit blocks of modern DRAM design. The output vector length was only 7% of the human-created vector length.