# Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

arXiv: https://arxiv.org/abs/2604.03401 · HTML: https://mlsanity.com/paper/2604.03401/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 8 of 8)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders](https://mlsanity.com/paper/2412.09586/) (2024)
- [Evaluating Large Language Models in Analysing Classroom Dialogue](https://mlsanity.com/paper/2402.02380/) (2024)
- [LLM-Driven Learning Analytics Dashboard for Teachers in EFL Writing Education](https://mlsanity.com/paper/2410.15025/) (2024)
- [Adversary-Guided Motion Retargeting for Skeleton Anonymization](https://mlsanity.com/paper/2405.05428/) (2024)
- [Multi-Model Synthetic Training for Mission-Critical Small Language Models](https://mlsanity.com/paper/2509.13047/) (2025)

## Abstract (arXiv)

Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts.