Excited there's another time series for health workshop at NeurIPS this year --- submit your work!

🩺📈 The "Learning from Time-series for Health (TS4H)" workshop is BACK at NeurIPS 2025 🥳! This workshop unites researchers across health time-series domains (from wearables to clinical systems) to tackle shared challenges. Details: timeseries4health.github.io 🧵 (1/6)

Excited we have some papers accepted to ICML'25 in collaboration with some tremendous folks 🎉 Looking forward to Vancouver to discuss model editing for LLMs/VLMs and improving medical benchmarking!

Happy to share our ICLR'25 paper to be presented by @snagaraj.bsky.social! It's the first method to capture how label noise can change over time in sequential classification tasks. Many implications, one being towards better models of labelers' behavior over time, even for non-time series tasks 🎉

Super excited to share our new work on keeping LLMs factually up-to-date for long periods of time 🎉