# QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery

arXiv: https://arxiv.org/abs/2602.17478 · HTML: https://mlsanity.com/paper/2602.17478/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning](https://mlsanity.com/paper/2402.11435/) (2024)
- [BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding](https://mlsanity.com/paper/2503.21483/) (2025)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment](https://mlsanity.com/paper/2412.19326/) (2024)
- [Deep-Learning-Based Image Segmentation Integrated with Optical Microscopy for Automatically Searching for Two-Dimensional Materials](https://mlsanity.com/paper/1910.12750/) (2019)
- [Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning](https://mlsanity.com/paper/2205.15948/) (2022)
- [Quantum Vision Clustering](https://mlsanity.com/paper/2309.09907/) (2023)
- [Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution](https://mlsanity.com/paper/2412.15650/) (2024)
- [Defining Quantum Neural Networks via Quantum Time Evolution](https://mlsanity.com/paper/1905.10912/) (2019)
- [MaskTerial: A Foundation Model for Automated 2D Material Flake Detection](https://mlsanity.com/paper/2412.09333/) (2024)

## Built on by (most cited first, 3 of 3)

- [OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials](https://mlsanity.com/paper/2603.17043/) (2026)
- [QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling](https://mlsanity.com/paper/2605.13833/) (2026)
- [QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization](https://mlsanity.com/paper/2609.12202/) (2026)

## Abstract (arXiv)

Characterizing two-dimensional quantum materials from optical microscopy images is challenging due to the subtle layer-dependent contrast, limited labeled data, and significant variation across laboratories and imaging setups. Existing vision models struggle in this domain since they lack physical priors and cannot generalize to new materials or hardware conditions. This work presents a new physics-aware multimodal framework that addresses these limitations from both the data and model perspectives. We first present Synthia, a physics-based synthetic data generator that simulates realistic optical responses of quantum material flakes under thin-film interference. Synthia produces diverse and high-quality samples, helping reduce the dependence on expert manual annotation. We introduce QMat-Instruct, the first large-scale instruction dataset for quantum materials, comprising multimodal, physics-informed question-answer pairs designed to teach Multimodal Large Language Models (MLLMs) to understand the appearance and thickness of flakes. Then, we propose Physics-Aware Instruction Tuning (QuPAINT), a multimodal architecture that incorporates a Physics-Informed Attention module to fuse visual embeddings with optical priors, enabling more robust and discriminative flake representations. Finally, we establish QF-Bench, a comprehensive benchmark spanning multiple materials, substrates, and imaging settings, offering standardized protocols for fair and reproducible evaluation.