- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
WAM-Cache accelerates Fast-WAM's video DiT prefill without retraining by reusing layerwise visual KV states across control cycles and refreshing tokens selected by latent changes, previous action attention, and cache age. The evaluated inference path encodes current observations without generating future video. The method reduces prefill FLOPs by 32–42% while largely preserving task success in simulation and on a real robot.
Critical strengths
- The method reduces prefill FLOPs by 32–42% with small losses in task success and can approach dense performance at higher refresh budgets while retaining substantial computational savings.
- At comparable compute budgets, it outperforms the evaluated baselines, and the combined signals achieve higher task success with fewer refreshed tokens than either signal alone.
- The paper is well written, with carefully designed figures that clearly explain the refresh mechanism.
Critical weaknesses
- TTF-VLA[1] uses current visual tokens where pixel changes are large or previous attention is high, reuses historical tokens elsewhere, and replaces all tokens with current features at periodic keyframes. Given these similar design principles, the additional methodological contribution of the proposed refresh policy remains unclear. The author could provide additional comparison to validate their contribution if possible.
- Treating the KV-drift oracle as a performance upper bound for all drift prediction rules requires further justification. Even if the true KV changes are known exactly, background regions with larger changes may be less important to refresh than a grasp target with smaller changes. Ranking tokens by drift magnitude does not necessarily reflect their impact on actions, so it remains unclear whether the oracle’s task success rate provides an upper bound for other rules.
- The refresh policy may spend its budget on irrelevant changes such as flickering lights and fail to update tokens that matter for the current action. The reliability of this selection strategy in such cases remains unverified.
[1] Liu C, Zhang J, Li C, et al. Ttf-vla: Temporal token fusion via pixel-attention integration for vision-language-action models[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2026, 40(22): 18452-18459.
Questions for authors
Please see Weaknesses 1–3 above.
6 comments
Rebuttal 2: W1 (continued)
4. Different attention source: action attention, which the WAM architecture provides directly. WAM-Cache uses the action expert's attention to the cached video K/V, averaged over all action queries, layers, and heads. It measures how strongly the policy consumes the very K/V pairs whose refresh is being decided. TTF-VLA describes an action-to-vision variant (its Eq. 8, using the first action token at a single layer), but its reported experiments use text-to-vision attention, which is also the default in its released code. Moreover, the WAM architecture makes action attention inexpensive to obtain: the action expert attends over the full cache at every chunk, regardless of which tokens are refreshed. A text-based score would instead come from the video DiT's text cross-attention, where visual tokens act as queries, so it is available only for recomputed tokens unless additional computation is spent on the reused ones. Empirically, action attention is the most important component (81.46% alone vs. 60–65% for change-based rules, Table 3).
5. Complementary rather than alternative. Since TTF-VLA operates on input tokens and WAM-Cache operates on K/V states, the two methods can be combined. TTF-VLA itself is applied on top of VLA-Cache [55] and raises its LIBERO average from 71.3% to 74.0%. Following your suggestion, we conducted the analogous experiment by applying TTF on top of WAM-Cache on LIBERO.
Table D2. Combining TTF with WAM-Cache on LIBERO (success rate, %).
| Method | Spatial | Object | Goal | Long | Avg. |
|---|---|---|---|---|---|
| Fast-WAM (dense prefill) | 96.80 | 99.40 | 96.00 | 93.80 | 96.50 |
| + WAM-Cache | 96.20 | 99.20 | 97.60 | 90.40 | 95.85 |
| + WAM-Cache + TTF | 97.00 | 99.40 | 97.60 | 92.40 | 96.60 |
The results indicate that TTF further improves WAM-Cache from 95.85% to 96.60% on average, with the largest gain on Long (+2.0), and brings it on par with the dense prefill (96.50%). This confirms that TTF-VLA contributes temporal fusion for robustness, whereas WAM-Cache contributes compute reduction, and that the two are complementary.
We hope this explanation resolves your concern and clearly conveys the contribution of WAM-Cache.
[55] Xu, et al. VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching. arXiv (2025).
Rebuttal 3: W2
W2: Treating the KV-drift oracle as a performance upper bound for all drift prediction rules requires further justification. Even if the true KV changes are known exactly, background regions with larger changes may be less important to refresh than a grasp target with smaller changes. Ranking tokens by drift magnitude does not necessarily reflect their impact on actions, so it remains unclear whether the oracle's task success rate provides an upper bound for other rules.
Thank you for this insightful comment. We fully agree that ranking tokens by drift magnitude does not necessarily reflect their impact on actions. In fact, this is exactly the central message of our paper, and the K/V-drift oracle is designed to demonstrate it. We apologize that our wording "performance ceiling" in the Introduction caused this confusion.
1. Purpose of the oracle: to show that tokens cannot be selected simply by predicting their K/V drift. A natural approach to cache refresh is to predict which tokens' K/V states drift most and refresh those tokens. Pixel difference and latent surprise are two such predictors. If their low success rates were caused by inaccurate drift prediction, a better predictor would close the gap. The oracle removes prediction error entirely: it ranks tokens by the exact K/V drift, measured against a dense prefill of the new frame. As shown in Table D3, it still reaches only 65.34%, about 25 points below the dense model, whereas action attention, which uses no drift information at all, reaches 81.46%.
Table D3. Refresh rules grouped by the information they use (from Table 3, clean RoboTwin 2.0, content budget 0.5, ).
| Selection rule | Drift information | SR (%) | |
|---|---|---|---|
| Pixel difference | Estimated | 60.40 | 0.625 |
| Surprise only | Estimated | 60.62 | 0.615 |
| Oracle K/V drift | Exact | 65.34 | 0.599 |
| Action attention only | None | 81.46 | 0.643 |
| Attention ∪ surprise (Ours) | Estimated | 88.36 | 0.584 |
| Fast-WAM (dense prefill) | – | 90.16 | 1.000 |
The results indicate that the bottleneck lies in the drift-ranking criterion itself, rather than in the accuracy of drift prediction: even exact knowledge of how much each token drifts does not reveal which tokens matter for the action. Your example of a background region with large changes and a grasp target with small changes is precisely the failure case we describe in Section 4.3, which motivates our action-conditioned selection.
2. Clarification of our wording and revision. In Section 5.3 of the submission, we described the oracle as "an upper bound for any rule that predicts cache drift". This referred to drift prediction: since the oracle ranks tokens by the exact K/V drift, no drift predictor can rank tokens more accurately. It was not intended as an upper bound on task success. We agree that, since drift ranking does not determine action impact, a less accurate drift predictor may occasionally refresh more action-relevant tokens and achieve a higher success rate. Our conclusion does not rely on such a bound: it rests on the comparison in Table D3, in which exact drift falls far behind attention without any drift information. We have therefore revised the paper:
- : "This performance ceiling reveals that ..." → "This reveals that ..."
- Section 5.3: we have removed the sentence "It is an upper bound for any rule that predicts cache drift, not a practical method."
- : we have added the definition of the oracle score (cosine distance between the cached and the exact keys and values, summed over all layers), together with the statement that it does not bound task success.
We hope this clarification resolves your concern. Thank you again for helping us make this point more precise.
Rebuttal 1: W1
We are grateful for your insightful review. We are delighted by your appreciation of our work as achieving "substantial computational savings", being "well written", and featuring "carefully designed figures".
You also raised some points of weakness, which we found very enlightening. We have thoroughly analyzed the issues you mentioned and provide the following responses. Changes are highlighted in blue in the revision.
Thank you for your careful review and for bringing TTF-VLA [a] to our attention. We agree that TTF-VLA and WAM-Cache are related at a high level, and we have cited it in the related work of the revision (Section 2).
Nevertheless, the two methods differ substantially. Table D1 summarizes the differences, and we discuss them below in order of importance.
Table D1. Comparison between TTF-VLA and WAM-Cache.
1. Different objectives: TTF-VLA improves accuracy, whereas WAM-Cache reduces inference cost. TTF-VLA fuses historical visual tokens into the current input to exploit temporal information and improve the success rate of a VLA. Its vision encoder and LLM backbone still process every frame in full. The paper reports a runtime overhead of less than 2% and names direct KQV reuse as a future direction. In contrast, WAM-Cache selects tokens whose layerwise K/V states can be reused, and forms queries only for the refresh set, which removes 32–42% of the prefill FLOPs. Consequently, stale content plays opposite roles in the two methods. In TTF-VLA, historical tokens are a beneficial signal, and every selection variant in its ablation improves on the baseline on average. In WAM-Cache, a stale K/V pair is an approximation error that propagates across layers and chunks, so the selection rule is decisive: at a matched budget, success ranges from 26.9% to 88.4% (Table 3).
2. Different change signal: latent drift since the last refresh, rather than pixel difference. TTF-VLA thresholds the grayscale pixel difference between consecutive frames. WAM-Cache scores the normalized latent distance between a token's current embedding and its embedding at its last refresh (Eq. 5). The score therefore measures the displacement from the observation that the cached K/V pair actually represents, so drift that accumulates over several reuses is detected, whereas a consecutive-frame difference may miss it. It is also computed on the latent that the prefill requires anyway. We note that a change signal alone is insufficient in either form (60.40% vs. 60.62% in Table 3), which is precisely what motivates our action-conditioned signal.
3. Different staleness control: a per-token age bound, rather than a global keyframe. TTF-VLA replaces all tokens at periodic keyframes, regardless of their state. This is free in TTF-VLA because its encoder always runs in full, but in a compute-skipping setting a keyframe amounts to a periodic dense prefill. WAM-Cache instead maintains an age counter for each token, which is reset whenever the token is refreshed by any signal (Eqs. 7–8). A forced refresh therefore applies only to tokens that neither content signal has selected for G consecutive chunks, and its amortized cost is bounded by 1/(G+1) (Appendix B).
[a] Liu, et al. TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models. AAAI (2026).