# Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis

arXiv: https://arxiv.org/abs/2605.13248 · HTML: https://mlsanity.com/paper/2605.13248/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications](https://mlsanity.com/paper/2408.02686/) (2024)
- [Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners](https://mlsanity.com/paper/2410.02131/) (2024)
- [Neural Codecs as Biosignal Tokenizers](https://mlsanity.com/paper/2510.09095/) (2025)
- [Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalities](https://mlsanity.com/paper/2504.19596/) (2025)
- [Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models](https://mlsanity.com/paper/2405.11566/) (2024)
- [PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection](https://mlsanity.com/paper/2509.19774/) (2025)
- [CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models](https://mlsanity.com/paper/2512.02180/) (2025)
- [BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression](https://mlsanity.com/paper/2602.16951/) (2026)
- [RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection](https://mlsanity.com/paper/2602.23060/) (2026)
- [Multi-scale Masked Autoencoder for Electrocardiogram Anomaly Detection](https://mlsanity.com/paper/2502.05494/) (2025)
- [Sensing Cardiac Health Across Scenarios and Devices: A Multi-Modal Foundation Model Pretrained on Heterogeneous Data from 1.7 Million Individuals](https://mlsanity.com/paper/2507.01045/) (2025)
- [Toward Resource-Efficient Collaboration of Large AI Models in Mobile Edge Networks](https://mlsanity.com/paper/2602.13206/) (2026)

## Built on by (most cited first, 1 of 1)

- [GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals](https://mlsanity.com/paper/2609.27018/) (2026)

## Abstract (arXiv)

The analysis of physiological time series, such as electrocardiograms (ECG) and photoplethysmograms (PPG), is persistently hindered by modality and frequency gaps stemming from heterogeneous recording devices. Existing foundation models typically rely on continuous latent spaces, which frequently suffer from severe modality entanglement, lack high-fidelity cross-frequency generative capacity, and impose high computational costs that prohibit edge-device deployment. In this paper, we propose Compact Latent Manifold Translation (CLMT), a highly parameter-efficient (0.09B) unified framework that bridges these gaps through a novel two-stage discrete translation paradigm. First, we introduce a Universal Tokenizer utilizing Hierarchical Residual Vector Quantization (RVQ) to decouple heterogeneous signals into isolated, well-structured discrete latent manifolds, effectively preventing inter-modality interference. Second, a Context-Prompted Latent Translator maps these discrete tokens across modalities by integrating static physiological priors, reframing complex signal synthesis as a pure latent sequence translation task. Extensive evaluations demonstrate that our 0.09B model significantly outperforms massive baselines. In cross-modal PPG-to-ECG synthesis, it resolves temporal phase drift and dramatically improves the clinical R-peak detection F1-score from 0.37 (baseline) to 0.83. Furthermore, in extreme cross-frequency super-resolution (25Hz to 100Hz), it successfully recovers high-frequency diagnostic landmarks, achieving an unprecedented Pearson correlation of 0.9956. By learning a universal discrete language for biological signals with a fraction of the computational footprint, our approach sets a new trajectory for edge-deployable, multi-modal medical foundation models.