SLIP (Sensor Language-Informed Pretraining; any-channel sensor-language FM)
IMUPPGECGEEGtime-seriesTextOpen Weights
Key facts
- Pretraining Data
- ~600K sensor–caption pairs, ~1 B time points
Datasets used
Related Research
- WESAD
Wearable Stress and Affect Detection
- SLIP: Learning Transferable Sensor Models via Language-Informed Pretraining
An open-weights (MIT) sensor-language FM that is agnostic to channel count and sampling rate. That s
- Aether
compute-optimal physiological waveform FM family (20M–2.1B)
- AnyMo
Foundation model