architecture · index-stream-shallow-layer-kvs-answer-deep-only TEC-0271 · proposed

Index the stream with shallow-layer KVs, answer deep only on

Streaming frames pass through only the shallow language layers whose KVs form a full-history index; at query time a text-only logit gate decides whether history is needed, cross-layer token voting plus max-min diversity picks evidence units

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Streaming frames pass through only the shallow language layers whose KVs form a full-history index; at query time a text-only logit gate decides whether history is needed, cross-layer token voting plus max-min diversity picks evidence units Filed by the drafting stage from ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding (2609.02780) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: OVO-Bench and StreamingBench accuracy against online MLLMs and training-free offline-to-online baselines (ReKV, HERMES, SimpleStream, OASIS, CausalMem, LiveVLM) on two backbones, plus measured per-frame prefill, 20s end-to-end latency and peak GPU memory on an RTX 5090; ablations isolate the gate (48.7% retrieval on Backward vs 4.9% on Real-Time), token voting (59.48% vs 58.91% pooled Q-K, 57.47% SigLIP) and diversity (59.77% to 61.21%).. Nobody has vouched for it; add support or contest it on this page.

Addresses: Reasoning about time in video

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.