- Rating
- 2(−1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Trace Forcing addresses long-horizon degradation in autoregressive video diffusion by modifying the inference-time KV cache. It diagnoses deviation of cached features from training-horizon reference statistics and maintains anchor representations through exponential moving averages along cross-frame key-similarity correspondences. Content-adaptive update rates balance preservation of earlier representations against adaptation to recent content. The generator requires no additional training. Experiments on Self-Forcing and LongLive evaluate 240- and 480-second generation against existing training-free methods, using VBench-Long and quality-drift metrics.
Critical strengths
-
The method addresses a meaningful limitation beyond positional extrapolation. The feature-deviation analysis provides a useful diagnostic of the cache feedback process, while traced anchors and adaptive updates offer a concrete inference-time intervention. The existing adaptive-update ablation matches the effective average update rate, which is a useful control for the quality-versus-motion tradeoff.
-
The reported long-horizon gains on two backbones are practically relevant. On Self-Forcing at 240 seconds, the average score improves from 78.97 for MemRoPE to 79.75; on LongLive at 480 seconds, it improves from 77.29 to 79.30, with Dynamic Degree increasing from 44.94 to 54.90. At 480 seconds, imaging-quality drift decreases from 5.25 to 2.63 on Self-Forcing and from 3.52 to 2.04 on LongLive. These results support the usefulness of the cache intervention without retraining.
Critical weaknesses
-
Table 3 supports adaptive updating but does not isolate content tracing from EMA smoothing: the missing control is position-wise EMA with the same cache structure, RoPE scheme, and update settings. Comparisons with MemRoPE change other design choices. The reduced Mahalanobis distance and its correlation with artifacts also establish an association, without demonstrating the stronger causal claim about feature deviation.
-
On Self-Forcing at 480 seconds, the average gain over MemRoPE is only 0.22 on 20 prompts, with slightly lower imaging quality and Dynamic Degree. Different prompt sets at 240 and 480 seconds prevent a direct comparison over time. Appendix J also identifies difficulty with content emerging after warm-up, and the paper lacks end-to-end latency and peak-memory measurements for matching. These gaps limit the evidence for a reliable practical advantage.
-
The novelty appears incremental. MemRoPE already combines EMA-based KV memory with position-free caching and online RoPE; TokenFlow and FLATTEN provide precedents for correspondence-based feature propagation and flow-guided attention. Trace Forcing's distinction is its causal, training-free, per-head KV tracing and warm-up-based update rule. The paper should make clearer what methodological advance this adaptation and combination provides.
Questions for authors
-
Could you compare position-wise and traced EMA, each with fixed and adaptive updating, in the existing Self-Forcing 240-second setting? Match cache allocations, RoPE, prompts, seeds, sampling, and update-rate settings, and recompute warm-up statistics consistently. Report quality, drift, Dynamic Degree, and effective update rates.
-
Please compare MemRoPE, Trace Forcing, and the position-wise control on common prompts and seeds using 120-, 240-, and 480-second prefixes where applicable. Report quality and motion curves, per-prompt differences, and uncertainty. Examples of objects entering or reappearing after warm-up would also help assess the limitation in Appendix J.
-
What are generation time, throughput, and peak GPU memory for Trace Forcing and MemRoPE on the same hardware at matched total cache-token budgets? Include each cache allocation, matching/update time, and temporary buffers.
4 comments
[@rSAN-2] Causal Role of Feature Deviation (W1)
To examine the causal role of the feature deviation, we intervened on the deviation itself: injecting deviation into the cached tokens within the training horizon degrades the visual quality in proportion to its magnitude, whereas removing it beyond the horizon recovers the quality lost over the rollout (Imaging 64.97 68.90 and Aesthetic 50.86 53.88). For the setting and the full results, we respectfully refer the reviewer to our response to Reviewer vQhd ([@vQhd-w2]).
[@rSAN-3] Common-prompt Comparison with MemRoPE over 120/240/480 s Prefixes (W2, Q2)
To compare over time on common prompts, we evaluated the 120-, 240-, and 480-second prefixes, using the same 20 prompts and seeds as the 480-second evaluation in Table 1.
| Prefix | Method | Imaging Quality↑ | Imaging Quality ↓ | Aesthetic Quality↑ | Aesthetic Quality ↓ | Background Consistency↑ | Motion Smoothness↑ | Subject Consistency↑ | Dynamic Degree↑ |
|---|---|---|---|---|---|---|---|---|---|
| 120 s | MemRoPE | 70.37 | 3.48 | 57.56 | 3.93 | 96.29 | 98.67 | 97.30 | 47.50 |
| Trace Forcing | 69.91 | 2.78 | 58.58 | 3.11 | 96.29 | 98.73 | 97.34 | 51.00 | |
| 240 s | MemRoPE | 70.33 | 3.78 | 56.04 | 4.46 | 96.24 | 98.62 | 97.25 | 47.29 |
| Trace Forcing | 69.79 | 3.11 | 57.90 | 3.40 | 96.33 | 98.71 | 97.32 | 49.25 | |
| 480 s | MemRoPE | 69.99 | 4.33 | 54.99 | 4.70 | 96.22 | 98.57 | 97.20 | 47.43 |
| Trace Forcing | 69.78 | 3.43 | 57.52 | 3.61 | 96.35 | 98.67 | 97.32 | 46.07 |
The per-prompt differences (Trace Forcing − MemRoPE) are summarized below as mean ± standard error over the 20 prompts.
| Prefix | Imaging Quality | Imaging Quality | Aesthetic Quality | Aesthetic Quality | Dynamic Degree |
|---|---|---|---|---|---|
| 120 s | −0.46 ± 0.56 | −0.71 ± 0.39* | +1.01 ± 0.71 | −0.82 ± 0.48* | +3.50 ± 4.03 |
| 240 s | −0.54 ± 0.82 | −0.67 ± 0.52 | +1.85 ± 0.77* | −1.06 ± 0.46* | +1.96 ± 3.45 |
| 480 s | −0.21 ± 0.81 | −0.90 ± 0.35* | +2.53 ± 0.82** | −1.09 ± 0.37** | −1.36 ± 3.07 |
* , ** (Wilcoxon).
The aesthetic advantage of Trace Forcing grows with the length and is significant at 240 and 480 seconds, with a lower in both metrics at every prefix, which is significant in all cases except the of imaging quality at 240 seconds. As the prefix grows from 120 to 480 seconds, the aesthetic quality of MemRoPE drops from 57.56 to 54.99, whereas that of Trace Forcing remains nearly constant (58.58 to 57.52). Imaging quality and Dynamic Degree show no significant difference at any prefix. The advantage over MemRoPE therefore holds on a common prompt set, rather than resulting from the different prompt sets used at 240 and 480 seconds.
[@rSAN-4] Content Introduced after Warm-up (W2, Q2)
Under LongLive’s interactive prompt switching, in which a new action or object is introduced every 80 seconds, Trace Forcing achieves the highest CLIP score in every segment (25.15 on average vs. 24.17 for LongLive and 24.41 for -RoPE); the setting and the full results are provided in our response to Reviewer vQhd ([@vQhd-q2]).
Additionally,
- Examples of content entering after the warm-up are added to Appendix N ([@pyCt-w2]).
- The remaining limitation is left to future work, for which we consider recording, for each anchor token, the cross-attention weights assigned to the individual prompt words, and re-estimating when the prompt is switched or the distribution of these weights changes, as described in our response to Reviewer pyCt ([@pyCt-w3]).
[@rSAN-5] End-to-end Latency and Peak Memory at a Matched Cache Budget (W2, Q3)
We measured the overhead under a matched cache budget of 18,720 tokens per layer (Trace Forcing: 4,680 sink + 7,800 anchor + 1,560 raw + 4,680 new; MemRoPE: 4,680 sink + 3,120 EMA + 6,240 recent + 4,680 new).
Latency. When generating 120 s videos on a single RTX A6000, Trace Forcing is only 0.7% (Self-Forcing) and 0.5% (LongLive) slower than MemRoPE. Per chunk, matching takes 17.3 ms and the anchor update takes 14.4 ms (0.7% and 0.6% of the chunk latency, respectively).
Memory. Trace Forcing requires an additional 3.5 GB of peak memory, which has a fixed size that does not grow with the video length. The temporary buffers of matching (0.88 GB) are freed before the forward pass.
For the generation time, throughput, and peak memory of other methods, we respectfully ask the reviewer to refer to the table in our response to Reviewer pyCt ([@pyCt-q1]) and to Appendix L (Table 6).
[@rSAN-6] Methodological Advance (W3)
Although EMA-based memory and correspondence-based propagation have precedents, Trace Forcing employs them for a different purpose, namely suppressing the deviation of the cached tokens during a causal rollout, and this purpose determines its design. The differences from MemRoPE in the cache composition and in correspondence matching are discussed in [@rSAN-1]. Here, we clarify how Trace Forcing differs from TokenFlow and FLATTEN in the use of correspondences, and why the warm-up-based update rule is required.
Correspondence in a causal rollout. TokenFlow (Geyer et al., 2024) and FLATTEN (Cong et al., 2024) also employ correspondences. However, these methods edit a source video, so that the correspondences are obtained from the given video in advance and are used to keep the edited frames temporally consistent. In contrast, Trace Forcing has no source video: the correspondences are computed online between the generated tokens during a causal rollout, and are used to aggregate the cached tokens into anchors that suppress the deviation.
Warm-up-based update rule. This difference also makes the update rule necessary. In video editing, the motion is already given by the source video, whereas in Trace Forcing the model must generate the motion while being conditioned on the anchors. Since an anchor that is updated slowly retains its past content, a small update rate suppresses the deviation but also hinders the motion: with a uniform rate, the dynamic degree declines as the rate decreases. Our update rule resolves this trade-off by setting the rate of each anchor according to how much its content changes during the warm-up, so that the deviation is suppressed in static content while the motion of dynamic content is preserved.
Following the reviewer’s suggestion, we will revise the paper to emphasize the novelty of each component.
References
- Geyer, Michal, et al. “TokenFlow: Consistent Diffusion Features for Consistent Video Editing.” ICLR 2024.
- Cong, Yuren, et al. “FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing.” ICLR 2024.
Thank you for the additional experiments and clarifications. The common-prompt comparisons and cost measurements address several of my questions. However, the contribution of tracing remains insufficiently supported. With adaptive updating, the gains over position-wise EMA are small. With a fixed update rate, the authors report no considerable difference. These results do not provide strong evidence that tracing adds substantial value beyond EMA aggregation.
The authors also acknowledge cases in which the update rule suppresses legitimate new content or changes in motion. The prompt-switching results provide useful evidence, but higher average scores do not resolve these failures. The proposed changes to the update rule have not yet been validated.
The authors could consider defining a narrower scope and evaluating the method in a concrete application domain. Videos with limited motion and relatively stable content may be one direction to explore. However, simpler position-wise EMA may also work well in such settings, so narrowing the scope would still require evidence of a meaningful advantage over that baseline.
The paper reports useful practical improvements, and the additional experiments clarify both its strengths and limitations. Nevertheless, they do not sufficiently establish the value of the distinctive tracing mechanism. Together with the unresolved difficulty in handling evolving content, this leaves the contribution insufficiently strong for acceptance at ICLR. I am therefore lowering my rating from 3 to 2 (weak rejection).
We sincerely thank Reviewer rSAN for the insightful comments, which pointed out several aspects that we had overlooked. We believe that addressing them will considerably improve our paper. Along with our responses, we have uploaded the revised paper, in which the revised parts are marked in blue. We respectfully ask the reviewers to please refer to it together with our responses.
[@rSAN-1] Difference from MemRoPE and Comparison with Position-wise EMA (W1, Q1)
Beyond correspondence matching and the adaptive update rule, Trace Forcing differs from MemRoPE in what the EMA is used for. In MemRoPE, the EMA serves as an additional memory: the four most recent frames are kept as raw tokens, and two EMA frames, a long-term and a short-term memory that aggregate the same evicted frames at different rates, are added to retain the frames evicted from the window. The model therefore still relies mainly on raw tokens, in which the deviation accumulates. In Trace Forcing, the EMA instead replaces the raw tokens: under the same 12-frame budget, only a single frame is kept raw (R=1), and all the other past frames are held as anchor tokens (A=5), which are less deviated. Each raw token leaving the recent slot passes through the anchor slots one at a time and updates each of them, so that the anchors keep the temporal order of the history, for which a queue of raw tokens is used. The five anchor frames thus form a temporally ordered history of the past frames, rather than two memories of different time scales, so that the context preserves how the content has moved across the past frames. This design suppresses the deviation in the context, which induces artifacts, as much as possible. Consistent with this design, the advantage of Trace Forcing over MemRoPE in aesthetic quality grows with the video length, with a lower σ in both imaging and aesthetic quality at every length ([@rSAN-3]). Nevertheless, we fully agree that the contribution of correspondence matching should be clarified against position-wise EMA under an identical cache allocation.
In our view, correspondence matching makes two contributions over position-wise EMA: (1) it aggregates more similar tokens into each anchor than position-wise EMA (cosine similarity of 0.790 vs. 0.899 for the tokens whose content moves to a different position), and (2) it makes adaptive updating content-aware, since with position-wise EMA the update rates follow fixed regions of the frame rather than the contents (please refer to Fig. 15, Appendix J). The detailed analysis is provided in our response to Reviewer pyCt ([@pyCt-w1]).
In addition, we compared the two variants on the quality metrics under adaptive updating, with the same cache composition, RoPE, prompts, seeds, sampling, and update settings, recomputing the warm-up statistics under each correspondence (Self-Forcing, 20 prompts), following the setting of our ablation study.
We consider the main role of tracing to be making the adaptive update rule work as intended. Adaptive updating assigns each anchor a rate that determines how much of the change of its content the anchor accepts, and without tracing, the change of each content cannot be measured properly.
We therefore regard the contribution of tracing as closely tied to adaptive updating, and conducted the ablation under adaptive updating. As requested by the reviewer, we also conducted it with a fixed update rate, in which the two variants showed no considerable difference. Under adaptive updating, tracing achieves slightly higher scores than position-wise EMA, and we would further like to emphasize the contribution of tracing through the qualitative results in Fig. 13 and Fig. 15.