- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper examines which historical KV states support long-term consistency in autoregressive video generation, focusing on the middle region between sink and recent caches. Removal, restoration, identity replacement, and content-corruption interventions test the role of this history, while attention analyses examine its use across frames and prompt transitions. The authors interpret the results as evidence that middle KV primarily provides visual references rather than event memory. Based on this interpretation, they propose Temporal-Weighted Reservoir (TWR), a training-free policy that maintains broad historical coverage while preferentially retaining earlier references under a fixed active-cache budget. Evaluations across four video backbones compare cache policies and budgets, reporting improved identity similarity, reduced identity drift, and better long-term visual consistency.
Critical strengths
-
Identity gains extend across four backbones. Relative to Uniform Reservoir, FaceSim improves by 7.2, 4.6, 12.8, and 2.6 points on daVinci-MagiHuman, Wan2.1, Wan2.2, and HY-World 1.5, respectively; ID drift decreases on all four.
-
Direct interventions support the value of historical KV. Restoring middle KV improves identity similarity with paired intervals above zero. Identity replacement and content corruption also affect subsequent frames.
Critical weaknesses
-
Identity improvements are not jointly validated with action completion. Dynamic, motion smoothness, and prompt-switch results do not directly establish whether actions are completed, repeated, or followed responsively. Dynamic does not uniformly decrease relative to Uniform, so reduced motion is not a demonstrated explanation. Nevertheless, without joint identity-and-action evaluation, the practical significance of improved consistency remains uncertain.
-
The mechanism interpretation and baseline comparison support narrower conclusions than claimed. The absence of stable attention peaks at matching past events does not exclude distributed event information; content corruption establishes an influence of history, not an absence of event memory. Separately, Section 5.1 describes PC and Figure 7 labels it DF-PC with one fixed sink slot. Unless Deep Sink and positional handling are included, this supports a controlled policy comparison rather than superiority over complete Deep Forcing. These limitations affect both the explanatory and comparative contributions.
Questions for authors
-
Can existing videos support joint identity-and-action success rates, repetition or stalled-action frequencies, and response delay after prompt switches? A targeted blinded assessment would help distinguish appropriate stillness from failure.
-
Does removing or replacing relevant-event history affect later related behavior more than an equally sized intervention on unrelated history? Alternatively, please limit the conclusion to the absence of stable matched-event attention under the tested readout.
-
Does the Deep Forcing baseline include Deep Sink and positional handling? Please clarify its scope and either provide a representative full-method comparison or restrict superiority claims to the tested policies.
-
How sensitive are gains over Uniform to generation seeds and weighting? Please show paired intervals and representative sensitivity results. Report memory and time alongside budget curves, separating LongLive-RAG’s archive costs from active KV.