🏷️ visualization

> **Synthesis:** Graf et al. (2026) transformed a conventional Learning Analytics Dashboard (LAD) into an interactive ILAD by adding an LLM-powered pedagogical agent and a Judgement of Learning (JoL) …

2026-08-08 · learning-analytics, metacognition, llm, higher-ed, engagement-metrics

> **Synthesis:** Systematic study of domain-adapted text-to-image models for nuclear engineering education. Fine-tunes Stable Diffusion on nuclear domain images; fine-tuned model achieves 78% domain a…

2026-08-06 · generative-ai, stem-education, ai-generated-content, multimodal, content-quality

> **Calibrating Trustworthiness: Co-Designing Metrics and Visualizations for Evaluating LLMs in Education** — Longitudinal co-design with learning engineers building an LLM-powered digital textbook. C…

2026-08-05 · llm, ai-ed-evaluation, trust-calibration, human-in-the-loop, instructional-design

> **Shixian Zhou, Minghuan Shen, Xiaolin Wen, Zijun Qiu, Yongliang Jiang, Xiangyang Wu, Fei Wu, Yong Wang, Zhiguang Zhou** — arXiv preprint (2026).…

2026-08-03 · learning-analytics, multimodal, student-experience, engagement-metrics, higher-ed

Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet most evaluations remain chart-centric and offer limited insight into **scientific visualization (SciVis)…

2026-07-17 · llm, generative-ai, stem-education, ai-literacy, benchmark

Building upon found examples is a popular way people learn to code, especially in creative coding communities where sharing projects and remixing are common practices. But effectively doing so require…

2026-07-09 · scaffolding, generative-ai, feedback-loop, active-learning, programming-its

SupplyNet is a gamified visual simulation system that uses a contextual graph-based [[llm]] multi-agent framework to model interdependent supply chain dynamics. Designed for [[professional-training]] …

2026-06-24 · intelligent-tutoring, llm, generative-ai, active-learning, professional-training

Revisits WordStream (2009) as a quantitative encoding for qualitative learning analytics; demonstrates how structured coding can surface cohort-level trends while preserving individual narrative conte…

2026-06-18 · learning-analytics, k-12, higher-ed, qualitative-research, edtech-platform

StanBKT introduces an open-source Python package for Bayesian Knowledge Tracing (BKT) that moves beyond traditional expectation-maximization (EM) point estimates to full Bayesian inference via Stan. T…

2026-05-25 · intelligent-tutoring, learning-analytics, adaptive-learning, benchmark, open-source

**Annie Yuan (2026)**. arXiv preprint (cs.HC). Current AI-driven educational systems primarily rely on behavioural analytics and performance metrics, lacking the ability to model expert cognition used…

2026-05-22 · learning-analytics, intelligent-tutoring, adaptive-learning, student-experience, teacher-role

Agentic analytics using AI-produced concept-map artifacts as shared human-AI representations improves collaboration quality analysis and AI response grounding over transcript-only baselines. CLARA int…

2026-05-19 · learning-analytics, generative-ai, llm, higher-ed, edtech-platform

> **From Prototype to Classroom** (Elhaimeur & Chrisochoides, 2026) describes a tutoring system for quantum computing that bridges the gap between dense mathematical formalism and limited qualified in…

2026-05-08 · adaptive-learning, higher-ed, intelligent-tutoring, knowledge-tracing, stem-education

> When LLMs process STEM problems that require interpreting diagrams, graphs, or schematics alongside text, their accuracy degrades substantially. This effect is: > General-purpose LLMs achieve near-c…

2026-05-07 · llm, intelligent-tutoring, stem-education, higher-ed, k-12