# Main ICASSP manuscript ## Current structure (2026-09-17) The current draft uses **causal local evidence adaptation** as the single umbrella for recent modality evidence and cutoff-aligned Omni tail access. It supersedes the older scope description below; historical strategy docs remain records of their dates. The new scoped decision is [`../../docs/manuscript_local_evidence_structure_2026-09-17.md`](../../docs/manuscript_local_evidence_structure_2026-09-17.md). - Method has two subsections: **Model Architecture** (task, global/local features, fusion and learning) and **Streaming Inference Architecture** (8-s maximum context, completed-history reuse, temporary current tail, cutoff alignment). Only one displayed fusion equation remains. - The core is frozen Qwen Omni `G` + recent 1-s Qwen audio `A`; pooled person vision is optional, not an established performance contribution. - The three contributions cover global--local adaptation, its partial-tail streaming realization, and controlled dense versus onset/offset analysis. Caching alone is not claimed as a new algorithm; mechanism gains await matched controls. - The method figure now depicts that actual core rather than an unmeasured 25-Hz MuVAP person-attention branch. Preserved-EgoSpeak residual fusion and its block-phase embedding are auxiliary controls, not the default head. - Semantic opportunity evaluation is deferred during annotation auditing. Its historical protocol and workload are preserved in [`annotation_protocol_notes.tex`](annotation_protocol_notes.tex), which is deliberately not included in the submission PDF. Historical results remain in the original `results/` and `reports/` records. - Analysis uses Main Comparison, Local Evidence Analysis, Streaming and Context Analysis, and Error and Qualitative Analysis. Omni LoRA is deferred. Planned experiments are in the [dated experiment log](../../docs/local_evidence_analysis_experiment_log_2026-09-17.md). - Locked main rows and the tail-refresh x local-audio / context-cap table are unmeasured placeholders, not zero or mixed-protocol confirmatory numbers. Historical main-table screens are identified explicitly. Already inspected official-test runs remain exploratory despite additional seed repetitions. - The main table now includes an exploratory F3 seed-0 no-box full-frame screen and the re-evaluated G+A dense horizon curve, both under `causal_valid_only`. F3's 0.2-s/ten-horizon mAP is 82.38/65.54 versus G+A's 81.72/65.11. This is not a matched visual-motion claim: F2, matched capacity/history controls, boundary evaluation, and repeat seeds are still missing. Source records: [F3](../../results/easycom_fullframe_qwen_av/f3_seed0/README.md) and [G+A](../../results/easycom_omni_audio_recheck_2026-09-24/official_test/README.md). - Backbone transfer adds paired G/GA controls for Qwen2.5-Omni 3B/7B and MiniCPM-o 4.5, fixing the same local audio sidecar. Compact table deltas are pending and require readout/refresh/history audits; MiniCPM is not yet GPU-verified or an established matched 8-s stream. This scoped transfer overrides the older cache-diagnostic-only restriction below, not the 3B core. - The body targets four technical pages with one method figure, one main table, one compact streaming/transfer controls table, and one error/qualitative figure slot. The optional fifth page is references only; replace TODOs rather than keep appending, and finalize author kit and applicable AI-drafting disclosure. ## Build and historical scope This is the editable paper directory. It uses the unmodified official ICASSP 2026 LaTeX assets stored in `../ICASSP2026_Paper_Templates/`. When the ICASSP 2027 author kit is released, replace or add the official template and update `template_dir` in `latexmkrc` only after checking the new instructions. Compile from this directory: ```bash make ``` The PDF and all intermediate files are written to `build/`; only source files belong in Git. VS Code's LaTeX Workshop extension is supported when the repository is opened as the workspace. Open `main.tex` and run **LaTeX Workshop: Build LaTeX project**. The workspace setting writes output to `build/`, while `latexmkrc` provides the template and bibliography-style search paths to both LaTeX Workshop and command-line builds. Current source layout: ```text main/ main.tex references.bib figures/ method_architecture.tex # reproducible TikZ source method_architecture.pdf # manuscript-ready vector figure latexmkrc Makefile README.md build/ # generated, ignored ``` Running `make` regenerates the method figure when its TikZ source changes before compiling the manuscript. The manuscript is intentionally a content skeleton with visible TODOs. Do not turn planned implementations, controls, or results into completed claims. The frozen paper story is documented in [`../../docs/icassp2027_acceptance_storyline_2026-09-10.md`](../../docs/icassp2027_acceptance_storyline_2026-09-10.md). The paper asks how long-context Omni understanding can be adapted into sub-second, wearer-relative floor control for an invisible egocentric wearer. Its single candidate contribution is a causal local floor-evidence adapter: - Qwen2.5-Omni-3B is the primary global backbone; - matched LoRA/PEFT is a baseline, not a separate contribution; - Qwen2.5-Omni-7B is an optional capacity-scaling control; - the primary local method uses an anonymous, no-ID visible-person set; - track continuity is conditional and must defeat no-ID/shuffled/capacity controls before entering the paper; - MiniCPM-o remains outside the core method and main comparison; it appears only as a scoped streaming/cache diagnostic with a matched Qwen 1-Hz causal-hold control, and its 5-Hz cache row requires equivalence and leakage audits before reporting; - the oracle is analysis-only motivation, not a deployable method or headline; - the publication gate is lower competing-risk-censored multi-other false entry at matched wearer-onset recall without worse valid onset or yield. Competing-risk censoring and training-side threshold calibration are now implemented and unit-tested. The remaining P0 blocker is the real-data event audit and protocol/scenario freeze; until then, event values are timing-derived proxies. Already viewed Sessions 1--3 numbers are exploratory internal evidence and must not appear in the confirmatory paper table.