- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies cross-request computation reuse for text-to-video generation, focusing on whether historical computation is compatible with a new request and which parts can be reused. Carnator constructs early signatures from object regions and appearance descriptors extracted from attention and latent states during early denoising, then filters historical caches using calibrated thresholds. For accepted caches, it combines region-guided latent reuse with historical sparse-attention connectivity reuse while preserving selected target-specific computation. The authors report improved acceleration over the evaluated cross-request baselines while maintaining competitive generation quality.
Critical strengths
- Clear formulation and coherent design. The paper distinguishes semantic similarity from computational compatibility and uses evidence from internal generation states to guide both cache selection and region-specific reuse.
- Useful initial empirical evidence. Experiments across multiple backbones and component ablations demonstrate acceleration potential. Early-signature filtering improves text alignment over text-only retrieval. Separating threshold selection from independent certification is also more principled than relying solely on manually chosen thresholds.
Critical weaknesses
- Limited workload representativeness. The evaluation uses a curated VidProM subset with a target-informed cache that guarantees noun-matched candidates for every test request. Its hit rates and speedups may not generalize to independently arriving requests.
- Missing strong acceleration baselines. The paper does not compare against within-request sparse-attention methods such as Radial Attention, Sparse VideoGen2, RAPID, and DFSAttn, leaving the additional benefit of cross-request reuse unclear. Gains over reduced-step sampling or few-step distilled models are also unverified.
[1] Shangran Lin, Lu Lu, Jian Chen, and Qiang Liu. RAPID: Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video Diffusion. CVPR, 2026.
[2] Jie Hu, Zixiang Gao, Yutong He, and Kun Yuan. DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation. arXiv preprint arXiv:2605.23445, 2026.
[3] Shuo Yang et al. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation. NeurIPS, 2025.
[4] Xingyang Li et al. Radial Attention: O(n log n) Sparse Attention with Energy Decay for Long Video Generation. NeurIPS, 2025.
Questions for authors
- Could cross-request reuse reduce generation diversity? In particular, does reusing historical latent states bias outputs toward cached videos and reduce variation across different random seeds for the same prompt?
4 comments
Thanks for the response. The TeaCache experiment demonstrates composability with feature caching, but does not address my concern about comparisons with within-request sparse-attention methods. As shown in Table 3, the speedup of CARNATOR largely comes from reusing the sparse attention patterns from historical requests. Within-request sparse attention methods, such as Radial Attention, Sparse VideoGen2, RAPID, and DFSAttn, also reduce attention computation, so their complementarity with CARNATOR remains to be demonstrated. Therefore, I would like to see direct speedup and quality comparisons against within-request sparse-attention methods.
We thank the reviewer for the suggestion. We are currently conducting the requested experiments and consolidating the speedup and quality results. We will include them in our revised response.
We have now completed a direct comparison with Radial Attention, Sparse VideoGen2, RAPID, and DFSAttn. We adapted their public Wan2.1-14B implementations to Wan2.1-T2V-1.3B, updating the model-specific integration while preserving each method's core sparse-attention procedure. All methods were evaluated on a single NVIDIA H100 under the same generation setup. For CARNATOR, we used the same settings as in the original paper.
| Method | E2E latency (s) | E2E Speedup | DiT time (s) | DiT Speedup | CLIP-T | ΔCLIP-T | VBench-Q | ΔVBench-Q |
|---|---|---|---|---|---|---|---|---|
| Dense | 1138.6 | 1.00× | 974.2 | 1.00× | 0.2984 | +0.0000 | 0.6379 | +0.0000 |
| CARNATOR | 525.58 | 2.17× | 496.0 | 1.96× | 0.2810 | -0.0174 | 0.6361 | -0.0018 |
| Radial Attention | 731.00 | 1.56× | 697.28 | 1.40× | 0.2883 | -0.0101 | 0.6433 | +0.0054 |
| Sparse VideoGen2 SAP | 708.91 | 1.61× | 672.01 | 1.45× | 0.2914 | -0.0070 | 0.6342 | -0.0037 |
| RAPID | 703.75 | 1.62× | 666.87 | 1.46× | 0.2838 | -0.0146 | 0.6454 | +0.0075 |
| DFSAttn | 704.01 | 1.62× | 668.17 | 1.46× | 0.2925 | -0.0059 | 0.6459 | +0.0080 |
CARNATOR achieves the highest speedup: 2.17× end-to-end and 1.96× for DiT, compared with 1.56–1.62× and 1.40–1.46× for the within-request methods. The quality results show a trade-off: CARNATOR has a small VBench-Q decrease (-0.0018), while its CLIP-T decrease (-0.0174) is larger than those of the sparse-attention baselines. These results provide the requested direct comparison and suggest that cross-request reuse captures additional acceleration in this workload, while its quality impact depends on the metric.
We thank the reviewer for the insightful feedback. We address each point below.
W1 Workload Representativeness
Cross-request reuse remains an emerging research direction, and standardized benchmarks for evaluating reuse compatibility, semantic preservation, and workload diversity are still limited. Our evaluation is designed as a controlled reuse-rich setting to examine compatibility assessment and acceleration when relevant historical computation is available. This follows a similar experimental protocol to Chorus, which also constructs its workload from a semantically clustered VidProM subset, using 1,000 historical requests as a warm cache.
We recognize that broader request distributions may result in different cache availability, hit rates, and overall acceleration. Within our evaluated workload, we ensure fair comparisons by using the same historical cache, request sequence, backbone, and generation configurations across all methods. Developing a dedicated cross-request reuse benchmark that systematically captures workload locality, reuse compatibility, and semantic correctness is an important direction for our future work.
W2 Complementarity with Intra-Request Acceleration
We appreciate the reviewer for highlighting recent intra-request acceleration methods. CARNATOR exploits computational redundancy across requests, whereas intra-request methods reduce redundancy within individual generations. These approaches target different sources of redundancy and are complementary, as also discussed in Chorus.
To demonstrate composability, we evaluated CARNATOR with and without TeaCache on paired requests across three models. CARNATOR+TeaCache reduced mean E2E latency by 17.3–28.0% and DiT latency by 31.8–49.0%, while maintaining relatively stable generation quality. The table reports latency changes from CARNATOR to CARNATOR+TeaCache and the corresponding quality differences (ΔCLIP-T / ΔVBench-Q):
Q1 Generation Diversity under Cross-Request Reuse
We thank the reviewer for this insightful perspective. Cross-request computation reuse may introduce historical-cache bias and reduce generation diversity, particularly through latent reuse, which preserves parts of historical generation states. Sparse-attention reuse may also influence output variation by constraining attention connectivity. Beyond its technical implications, this is an important question concerning the long-term impact of generative AI on human society, as repeated reuse of historical content could gradually reduce the diversity and originality of AI-generated media.
CARNATOR primarily focuses on accelerating generation while maintaining generation quality, and diversity represents an additional dimension of this trade-off. We believe this is a valuable research direction, where adaptive reuse policies, such as selectively disabling reuse or introducing stochastic cache dropout, could help balance acceleration and generation diversity. A systematic evaluation of cross-seed diversity and the development of diversity-aware reuse strategies constitute important directions for future work.
We thank the reviewer again for the insightful review.