OrganicHAR at UbiComp 2026: Discovering Activities Sensors Can Actually Distinguish
mynkgoel · x · 2026-10-16
A team presented OrganicHAR at UbiComp 2026: instead of forcing sensors to recognize predefined activity labels — even though what sensors can distinguish doesn't always match how we describe activities — the system "discovers" activity structures that match the sensors' actual discriminative capabilities.
Applications shown include safety monitoring and task assistance for elderly care, understanding personal productivity patterns, and helping building occupants answer comfort/occupancy questions.
More from Research
- Researchers derive a dropout scaling law from active parameter count — gordic_aleksa · 2026-10-16
- Gemini is a robotics outlier: dropping it lifts capability-robotics correlation from 0.20 to 0.96 — ycombinator · 2026-10-16
- EPFL team uses RFdiffusion to design de novo metamorphic proteins switching between two folds — ferruz_noelia · 2026-10-16
- Manipulating a model's sense of power may reveal its takeover counterfactuals — jd_pressman · 2026-10-16
- Poser benchmark unmasks alignment-faking LLMs, one detection method catches 98% — jd_pressman · 2026-10-16
- Six Years of Evidence That MLP Neurons Are an Interpretable Basis, in One Thread — aryaman2020 · 2026-10-16