- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses the problem that existing caching methods decide reuse based on feature differences, which do not match how the sampling trajectory actually evolves. It replaces the zero-order residual reuse of TeaCache-style caching with first-order linear extrapolation in actual time, and decides when to refresh using an extrapolation-magnitude threshold, residual changes, a maximum skip count and PID-adapted thresholds. On FLUX.1-dev, HunyuanVideo and Wan2.1, it shows higher reference fidelity than TeaCache, TaylorSeer and SeaCache at similar latency.
Critical strengths
(1) The evaluations is solid, and the fidelity gains are clear and consistent across models.
(2) The method is lightweight and easy to use: it requires no training, only stores two residuals and a few scalars, and can be plugged directly into existing residual-caching framewokrs.
Critical weaknesses
1、Limited novelty. The method linearly extrapolates the residual using the trend of the last two residuals. In essence, this applies TaylorSeer’s first-order extrapolation to TeaCache’s residual cache, together with a set of heuristic refresh rules (threshold-based refresh and standard PID tuning).
(1) Related work on first-order residual extrapolation: AB-Cache [1], PrediT [2], etc.
(2) Related work on residual reuse with adaptive refresh decisions: EasyCache [3], DiCache [4], etc.
2、 Issues with related-work citations and comparisons.
(1) For example, the citations of event-camera pretraining and optical-flow papers seem unrelated to this work. Please check the related-work citations more carefully.
(2) More related work should be cited and compared, including AB-Cache, PrediT, EasyCache, MeanCache [5] and DiCache. Among them, AB-Cache is the closest method and was also evaluated on HunyuanVideo and FLUX.
3、Key parameters (e.g., the thresholds and the curvature threshold) are missing, and the ablation does not separate the individual contributions of the rules. It is therefore unclear whether the performance gain mainly comes from the extrapolation itself, from a particular refresh rule, or from the PID controller.
[1] AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
[2] PrediT: Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
[3] EasyCache: Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
[4] DiCache: Let Diffusion Model Determine Its Own Cache
[5] MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
Questions for authors
pls see weaknesses.
7 comments
Response to Reviewer 2LCg [2/2]
3. Complete Hyperparameters and Rule-by-Rule Ablation Breakdown (Weakness 3)
-
Complete Hyperparameter Specification: All models share a unified controller configuration, while the table threshold (
tafc_thresh) and, where enabled, the maximum consecutive cache run determine the acceleration operating point: -
Base Thresholds (): In Eq. (9), directly sets (
0.04 / 0.15 / 0.30for FLUX;0.02 / 0.15for HunyuanVideo;0.03 / 0.15for Wan2.1), and . -
Time Modulation & Warmup/Cutoff: In Eq. (9), modulates the budget across normalized step progress , and . In Eq. (10), all experiments fix
warmup_steps = 3(full evaluations at , with the first valid two-anchor forecast error collected at for calibration) andcutoff_steps = 49(). No maximum consecutive-cache-run limit is imposed in the approximately settings. For FLUX, and are used in the approximately and settings, respectively; for HunyuanVideo and Wan2.1, is used in the approximately setting. -
PID Controller: Fixed at with in Eqs. (14)–(15).
-
Isolating Individual Contributions in the Ablation Study: Our ablations distinguish the effects of extrapolation, refresh rules, and PID feedback: “w/o First-Order Extrapolation” replaces the residual forecast with zero-order reuse; “w/o Adaptive Threshold” removes the prescribed time-dependent budget modulation; and “w/o Closed-Loop Control” disables PID updates by fixing constantly 1. To further isolate the refresh rules, we added “w/o Alone,” which removes only the anchor-variation gate while retaining Eq. 7 and PID feedback, and “Fixed Uniform + First-Order,” which retains the predictor but uses periodic refreshes. Full TAFC achieves higher PSNR at comparable measured refresh ratios, indicating that the gains do not come from extrapolation alone. We have clarified these implementations and included the additional controls in the revised manuscript. The threshold settings and their mapping to the base budgets are provided in the hyperparameter response above.
[1] AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
[2] PrediT: Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
[3] EasyCache: Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
[4] DiCache: Let Diffusion Model Determine Its Own Cache
[5] MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
Kind Reminder
Dear Reviewer 2LCg
As the deadline of discussion period is approaching, we would kindly like to inquire if you would get a chance to review our response and if there are any remaining questions we can address.
Your insights, both the constructive suggestions and areas of contention, have been crucial for us. We have done our best to address each point and clarify any misunderstandings. We are truly keen to have a constructive dialogue with you to refine our work further.
Best regards,
Authors of Submission 23200
Response to Reviewer 2LCg [1/2]
We sincerely thank you for your constructive feedback and for recognizing the solid empirical evaluations and lightweight, plug-and-play nature of TAFC. Below, we address your concerns by adding direct conceptual and experimental comparisons with AB-Cache [1], PrediT [2], EasyCache [3], DiCache [4], and MeanCache [5] and providing the full hyperparameter values and rule-level ablation breakdown.
1. Novelty beyond Combining TalyorSeer with Teacache, and More Comparisons (Weakness 1 & Weakness 2(2))
While TaylorSeer forecasts feature evolution and TeaCache uses feature-derived signals to guide reuse, TAFC starts from the physical-time dynamics of the generative ODE: an error in the model velocity perturbs the latent update in proportion to the sampling-time interval. This motivates approximating the reusable Transformer residual over actual sampling time and controlling how far that approximation is extended. Specifically, TAFC forecasts from two model-evaluated residuals using their physical-time separation, assesses reuse through the extrapolated correction and variation, and adapts subsequent budgets using forecast errors observed at refreshes. The residual is the operational quantity, while preserving the velocity-driven sampling trajectory is the underlying objective. Our contribution is this integrated prediction-and-control design motivated by physical-time error propagation, rather than first-order extrapolation alone.
Our contribution lies in integrating physical-time residual forecasting with reliability gating and error-feedback control, rather than introducing numerical extrapolation or adaptive caching individually. For more clarification with related work and comparisons, we have cited all five methods the reviewer mentions and clarified these distinctions in the revised manuscript. The quantitative comparisons are presented below. We did not evaluate AB-Cache because its official implementation was unavailable at the time of our experiments. For MeanCache, the publicly released code supported only Z-Image and Qwen-Image at the time, rather than the backbones evaluated in our study; we therefore provide a conceptual comparison.
New Comparison Table 1: FLUX.1-dev Evaluation with DiCache [4] and PrediT [2] (TAFC rows from Table 1)
New Comparison Table 2: Wan2.1-1.3B Video Evaluation with EasyCache [3] (TAFC row from Table 3)
Across all settings, TAFC achieves lower latency and TFLOPs while outperforming DiCache by +10.05 dB (∼2×) and +3.21 dB (∼3×), PrediT by +6.45 dB (∼2×) and +1.00 dB (∼3×) on FLUX.1-dev, and EasyCache by +4.42 dB PSNR on Wan2.1-1.3B.
2. Removing Unrelated Citations (Weakness 2(1))
Thank you for pointing this out. Our intention is to provide broader context on differential-equation-based visual modeling and efficient trajectory computation, rather than to present these works as prior methods for diffusion caching. However, we recognize that grouping event-camera pretraining and optical flow within this paragraph made their relevance unclear and distracted from the closest caching literature. We have therefore removed these citations from this paragraph and refocus the discussion on AB-Cache [1], PrediT [2], EasyCache [3], DiCache [4], and MeanCache [5], clarifying their methodological relationships to TAFC and including the additional empirical comparisons where available.