Record speaker-aware AV research and literature

2026-08-30 15:36:28 +08:00
parent 4abbde4f52
commit 348c5c3343
29 changed files with 907 additions and 6 deletions
@@ -22,6 +22,18 @@ horizon curves are archived in
 It keeps causal-valid summaries separate from full-timeline curves and records
 the head-capacity/context caveats for comparisons with G+A and G+A+V.

+The next research plan is
+[speaker-aware Thinker and wearer-transition evaluation](docs/speaker_aware_thinker_plan_2026-08-28.md)
+(2026-08-28): person-organized video chunks, frozen-Thinker local-evidence
+interventions, and onset/offset plus third-party-conversation diagnostics.
+These are planned experiments, not implemented or validated results.
+
+The [trainable speaker-fusion survey](docs/trainable_speaker_fusion_survey_2026-08-28.md)
+extends this to person-wise temporal branches, local-memory adapters and upper-layer
+Thinker LoRA on 8×L20, with matched-onset-recall false-entry evaluation and
+addressee-specific safeguards. It also records related-work and input-permission
+limits; none of these new variants has been implemented or measured yet.
+
 The main experiment is deliberately simple:

 ```text