- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper proposes DART, a framework that jointly applies feature caching and quantization to accelerate diffusion models. The authors define a sensitivity proxy as the relative change of the state within one step, and use it throughout all components. BPP partitions the trajectory into segments within which the fluctuation of is bounded, and recomputes the network only at the start of each segment. DAR corrects the input shift caused by caching and the output distortion caused by quantization, each with a channel-wise affine map. TSQ shares quantization parameters within each segment, and NPF folds the correction parameters into adjacent operators. On LDM-4 and DiT-XL/2 (ImageNet-256) and HunyuanVideo, the authors report better speed and quality than existing caching, quantization, and joint methods.
Critical strengths
-
The motivation is clear. The authors show that naively combining caching and quantization amplifies the error along the trajectory, and shows that correlates with the joint error more strongly than the feature distance. This provides a useful starting point for joint acceleration.
-
The method is evaluated on diverse backbones. DART is applied to a U-Net, a DiT, and a video model, using only a small calibration set.
Critical weaknesses
-
The contribution over existing methods seems limited. Most components of DART appear to closely follow prior methods.
- BPP. Eq. (2) uses the same objective, the cumulative L1 drift, and the same length constraint as the DPS of CacheQuant [A], with one additional constraint on the fluctuation of . Moreover, the proxy itself is taken from SenCache [B], as described by the authors (Ln206).
- DAR. Eqs. (3) and (5) seem to match the DEC of CacheQuant, which also corrects the error with channel-wise affine maps fitted in closed form.
- TSQ and NPF. Grouping timesteps and assigning separate quantization parameters to each group is a common practice in diffusion quantization, as in APQ-DM [C] and AccuQuant [D]. For NPF, CacheQuant also seems to fold its correction parameters into weight quantization (Sec. 4.3 of [A]), and merging batch normalization into dequantization parameters is a common technique in quantization. NPF thus does not seem to be new.
-
Key settings are missing, and the description of retraining is inconsistent.
- Missing settings. The paper does not describe which blocks or features are cached for LDM, DiT, and HunyuanVideo. Ln323 states that the DAR statistics are collected after weight reconstruction, but the reconstruction method and the settings in which it is used are not specified. Even if the code is provided, these settings should be stated in the paper, since they are needed to interpret the results and to see where the difference from the baselines comes from.
- Inconsistent description of retraining. The paper claims that DART is training-free and requires no retraining (Ln128, Ln360, and Ln474). Table 1, however, marks the W4A8 results of DART as requiring retraining. It would be helpful to clarify this inconsistency.
References
[A] CacheQuant: Comprehensively Accelerated Diffusion Models, CVPR 2025
[B] SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching, CVPR 2026
[C] Towards Accurate Post-Training Quantization for Diffusion Models, CVPR 2024
[D] AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models, NeurIPS 2025
Questions for authors
The caching in DART reuses cached features, while recent methods such as TaylorSeer [E] extrapolate them. Do BPP and DAR remain effective when combined with such methods, given that the input-side correction of DAR may overlap with extrapolation?
[E] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers, ICCV 2025