ruv 1d9c0b3d4c docs(study): sharpest finding — the encoder barely matters for CSI pose ...

Random frozen encoder + trained head matches a fully-trained encoder to
within 2-4pts (cross-subject <2pts). WiFi-CSI sensing is largely a
random-features + target-readout problem: barely a learned representation
to transfer, which unifies the zero-shot collapse, no-transfer results,
foundation-encoder failure, and why per-room calibration works. Practical:
invest in readout + calibration, not encoder pretraining.

Co-Authored-By: claude-flow <ruv@ruv.net>

2026-05-31 03:43:14 -04:00

..

homecore-vs-home-assistant.md

bench: HOMECORE vs Home Assistant — measured perf + capability matrix

2026-05-30 23:41:15 -04:00

mmfi-wifi-sensing-study.md

docs(study): sharpest finding — the encoder barely matters for CSI pose

2026-05-31 03:43:14 -04:00

person-count-cog.md

docs(bench): append v0.0.2 section to person-count benchmark log

2026-05-21 19:47:55 -04:00

pose-estimation-cog.md

docs: repoint #640 references to #645 (original deleted, replaced) (#646)

2026-05-19 17:18:05 -04:00

wifi-pose-efficiency-frontier.md

bench: ship int4 edge artifact + CPU latency

2026-05-31 01:30:29 -04:00