# PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing

arXiv: https://arxiv.org/abs/2607.22422 · HTML: https://mlsanity.com/paper/2607.22422/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2402.19072/) (2024)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers](https://mlsanity.com/paper/2205.03436/) (2022)
- [Temporal Query Network for Efficient Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.12917/) (2025)
- [Self-Supervised Multimodal Fusion Transformer for Passive Activity Recognition](https://mlsanity.com/paper/2209.03765/) (2022)
- [iMoT: Inertial Motion Transformer for Inertial Navigation](https://mlsanity.com/paper/2412.12190/) (2024)
- [MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion](https://mlsanity.com/paper/2504.02287/) (2025)
- [PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows](https://mlsanity.com/paper/2504.06070/) (2025)
- [PADM: A Physics-aware Diffusion Model for Attenuation Correction](https://mlsanity.com/paper/2511.06948/) (2025)

## Abstract (arXiv)

Accurate on-device fluid identification is essential for microfluidic applications, yet maintaining reliability under varying flow, pressure, and temperature remains a key challenge. Existing learning-based methods often treat sensor signals as domain-agnostic features, neglecting the underlying physical relationships that govern fluid behavior, thereby limiting generalization and interpretability. To address this, we propose PRIMS, a physics-aware multimodal Transformer that integrates physical knowledge into representation learning and attention mechanisms through three dedicated modules: (1) Physics-based Token Vectorization transforms raw Coriolis and pressure sensor signals into physically meaningful token embeddings; (2) Physical Component Synthesizer models viscosity-related dependencies among flow, pressure, and density; and (3) Physics-guided Fusion captures cross-physical correlations through attention-based integration. By embedding these physics-based relationships directly into the model architecture, PRIMS bridges analytical fluid mechanics and deep learning, enabling interpretable, data-efficient, and resilient fluid classification. Evaluations on a five-fluid benchmark under dynamic flow, pressure, and temperature conditions show that PRIMS achieves 98.92% average F1-score with only 0.46 million parameters, a 14 times reduction compared to state-of-the-art Transformer-based methods. PRIMS also consistently outperforms prior SOTA models under out-of-distribution shifts to unseen temperature ranges and unseen flow-rate ranges, indicating strong robustness to operating conditions not observed during training. These findings suggest that designing architectures that explicitly mirror governing physical relationships can make them learn transferable, environment-independent representations, improving real-world reliability for microfluidic sensing.