Patrick Langer
+1 more
- Stanford University; Aionic Labs; ETH Zurich
Patrick Langer has 2 papers in the ChatPPG research atlas (2026) and 9 co-authors in the atlas. Main topics: time-series-language-model, TSLM, OpenTSLM, stanford, eth-zurich, on-device.
Papers
- PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning2026 · arXiv 2610.21308v1
Ports OpenTSLM-SP (soft-prompt variant: a time-series encoder + projector inject signal windows as embeddings into a LoRA-adapted Llama-3.2-1B) to MLX-Swift, so inference runs entirely on a consumer iPhone (iPhone Air, iOS 26.4.1) with no health data leaving the device. Parity protocol: encoder, projector and rotary embedding match the Python MLX reference within 10⁻⁴ max element-wise. Greedy-decoded token sequences are identical between Swift and Python MLX; final answers match PyTorch.
- Venue: arXiv 2610.21308v1 (cs.LG, cs.CL; submitted 2026-10-15); a version accepted at the Workshop on Deploying AI in Healthcare (DAIH), COLM 2026
- Signals: ecg, eeg, text
- Form factor: other
- TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series Data2026 · arXiv 2610.21274v1
Problem: time-series language models (TSLMs) lack open, signal-grounded, reproducible text–time-series pairs. LLM-written captions cannot be regenerated exactly. Pipeline: deterministic captioner with three extractor tiers (statistical, structural, semantic) plus a cross-channel synthesis layer.
- Venue: arXiv 2610.21274v1 (cs.LG, cs.CL; submitted 2026-10-15; 46 pp incl. supplement)
- Signals: hr, steps, sleep, activity, text
- Form factor: wrist