# KOALA: Koopman Operator Learning for WiFi-Based Anticipatory Hum

arXiv: https://arxiv.org/abs/2608.15815 · HTML: https://mlsanity.com/paper/2608.15815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Deep learning for universal linear embeddings of nonlinear dynamics](https://mlsanity.com/paper/1712.09707/) (2017)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [History Repeats Itself: Human Motion Prediction via Motion Attention](https://mlsanity.com/paper/2007.11755/) (2020)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Back to MLP: A Simple Baseline for Human Motion Prediction](https://mlsanity.com/paper/2207.01567/) (2022)
- [Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics](https://mlsanity.com/paper/1811.07490/) (2018)
- [MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing](https://mlsanity.com/paper/2305.10345/) (2023)
- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting](https://mlsanity.com/paper/2403.16536/) (2024)
- [SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing](https://mlsanity.com/paper/2207.07859/) (2022)
- [SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM](https://mlsanity.com/paper/2308.09891/) (2023)
- [3D Human Motion Prediction: A Survey](https://mlsanity.com/paper/2203.01593/) (2022)
- [MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation](https://mlsanity.com/paper/2208.10414/) (2022)
- [Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction](https://mlsanity.com/paper/2308.08942/) (2023)
- [WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing](https://mlsanity.com/paper/2402.09430/) (2024)
- [AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi](https://mlsanity.com/paper/2309.16964/) (2023)
- [Robust data-driven control for nonlinear systems using the Koopman operator](https://mlsanity.com/paper/2304.03519/) (2023)
- [Graph-based 3D Human Pose Estimation using WiFi Signals](https://mlsanity.com/paper/2511.19105/) (2025)

## Abstract (arXiv)

WiFi Channel State Information (CSI) has emerged as a privacy-preserving alternative to cameras for human pose estimation. However, existing approaches treat pose inference as an instantaneous regression problem and do not model temporal dynamics, making future motion prediction infeasible. Naively applying vision-based prediction methods compounds the estimation noise already present in CSI-derived poses, as autoregressive rollouts amplify errors at every step. We propose KOALA, the framework for human motion prediction directly from WiFi CSI, by lifting noisy CSI-derived pose sequences into a learned Koopman latent space where nonlinear dynamics become linear, enabling multi-horizon prediction via simple matrix-vector products without autoregressive iteration or error accumulation. A residual CSI-conditioned operator resolves the identity attractor problem inherent from Koopman formulations, and an anchor-delta prediction head eliminates the degenerate shortcut of copying the current pose across all horizons. To regularise the lifting and operator jointly, we introduce a Koopman Anchored Latent (KAL) loss that operates in the temporal-encoder feature space, enforcing dynamical consistency across prediction horizons without requiring contrastive, spectral, or auxiliary losses. Experiments on MM-Fi and WiPose show that KOALA achieves robust, consistent performance across both short- and long-term prediction horizons, outperforming all baselines by a substantial margin.