# EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding

arXiv: https://arxiv.org/abs/2609.25582 · HTML: https://mlsanity.com/paper/2609.25582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation](https://mlsanity.com/paper/2412.02725/) (2024)
- [emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography](https://mlsanity.com/paper/2410.20081/) (2024)
- [Neural Codecs as Biosignal Tokenizers](https://mlsanity.com/paper/2510.09095/) (2025)
- [PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation](https://mlsanity.com/paper/2506.10351/) (2025)
- [EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography](https://mlsanity.com/paper/2410.23625/) (2024)
- [TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge](https://mlsanity.com/paper/2512.15729/) (2025)
- [NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models](https://mlsanity.com/paper/2510.13068/) (2025)
- [Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation](https://mlsanity.com/paper/2410.23629/) (2024)
- [ForceBand: Learning Forceful Manipulation with sEMG](https://mlsanity.com/paper/2606.26093/) (2026)
- [SPECTRE: Spectral Pre-training Embeddings with Cylindrical Temporal Rotary Position Encoding for Fine-Grained sEMG-Based Movement Decoding](https://mlsanity.com/paper/2512.22481/) (2025)

## Abstract (arXiv)

Public surface electromyography (EMG) datasets vary widely in electrode layout, channel count, frequency support, and size. Simply mixing them for pretraining can misalign channel semantics, introduce spectral targets that some devices cannot observe, and let large or high-channel-count datasets dominate learning. We introduce EMGBlend, a self-supervised framework designed around these differences. It combines shared channel patches with geometry-aware attention, restricts spectral targets to each recording's supported frequency band, and balances exposure across data sources. We pretrain a 109M-parameter model on 11 public EMG sources and evaluate it on gesture recognition, continuous-force regression, and contact classification. EMGBlend consistently outperforms matched random initialization and waveform reconstruction controls. Fixed-budget source controls show that multi-source pretraining improves gesture recognition and remains competitive for force decoding. Ablations confirm that geometry, band-aware targets, and source balancing each contribute to transfer, although cross-person NinaPro force estimation remains difficult. Overall, EMGBlend shows how heterogeneous EMG datasets can be combined through explicit mechanism design rather than simple concatenation. Code is available at https://github.com/tamanano/EMGBlend