Let your wearable data "speak" for itself! Introducing SensorLM, a family of sensor-language foundation models trained on ~60 million hours of data, enabling robust wearable data understanding with natural language. → goo.gle/4lSLwQi

🚨 Let your wearable data "speak" for themselves! ⌚️🗣️ Introducing *SensorLM*, a family of sensor-language foundation models, trained on ~60 million hours of data from >103K people, enabling robust wearable sensor data understanding with natural language. 🧵

I will be at #NeurIPS2024 Poster Session 2 West, presenting our paper "Towards open respiratory acoustic foundation models: Pretraining and benchmarking". Link: openreview.net/pdf?id=vXnGXR… Welcome to chat about anything, e.g. mobile health, foundation models, multimodal LLMs.

Our work towards respiratory acoustic foundation model is to be presented at NeurIPS24 D&B track. This was an amazing effort by @EveYuwei and @TongXia9 (with collaborators). This work will be useful for downstream tasks with limited data. Blog opera-benchmark.github.io/bl…

Super excited to share our work!

We announce our work on Open Respiratory Acoustic Foundation Models (arxiv.org/abs/2406.16148). In this work we build the first open and reproducible respiratory sounds based model for respiratory health. Work led by @EveYuwei and @TongXia9

Rowing does improve the cardio fitness 😆

Tomorrow I will present my work on uncertainty quantification in FL (along with @TongXia9, @AbhirupGhosh16 and @cecim) at FL4Data-Mining #KDD2023 during poster session 11:30 am - 12:00 pm local time. Welcome to stop by! You can find our paper here: openreview.net/pdf?id=QSQOTU…