Neuroscientist Konrad Kording says calibration-free BCI decoding — the field's hardest problem — may be solved
KordingLab · x · 2026-10-03
Konrad Kording (KordingLab, UPenn) quote-posted that calibration-free decoder design is one of the hardest — arguably the hardest — problems in brain-computer interfaces. With this new work plus another effort his lab is cooking, "we may have solved it," adding that calibration "clearly is unnecessary" and it's nice to see it happening.
Calibration-free decoding would remove the need for per-user calibration training before each BCI session, a key bottleneck for practical brain-computer interfaces. Technical details haven't been shared yet.
More from Research
- LEV: Looped decision model lifts 2.6B accuracy 63.2% to 76.2% with adaptive compute — jiqizhixin · 2026-11-19
- Aurora2-400M-A20M: a sparse MoE pretrained from scratch in 36 hours on one RTX Pro 6000 — Tall_Abrocoma_3533 · 2026-11-19
- Researcher calls METR/Anthropic '2x speedup' RSI analysis statistically dubious — jessi_cata · 2026-11-19
- Linear Probes Could Reveal Which Persona a Base Model Is Playing, Researchers Suggest — cephaloform · 2026-11-19
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- OpenVax codebase grows from 78K to 565K lines in 15 months — iskander · 2026-11-19