- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Existing speculative methods for dLLMs fail to capture all generation orders, which could lead to suboptimal acceptance rates. The paper proposes considering the permutation tree. To make this computationally feasible, the paper proposes several tricks to prune the tree. The speed improvements on several models are demonstrated.
Critical strengths
- The method is training-free and relevant to accelerating dllm inference. The speedup is promising.
Critical weaknesses
- I could not find any benchmark accuracies for CAPSpec in the submission. Did I miss it? Reporting accuracies is important to empirically prove that CAPSpec is lossless. In particular, the pruning still uses static draft confidence. The confidences of other tokens will likely change after a new token is committed. Using the precomputed confidences as pruning scores for all intermediate states may lead to accuracy degradation.
- It seems like ACP does not perform noticeably better than the baseline K1.
Questions for authors
- Can the authors provide the accuracy table and an explanation of why CAPSpec might be lossless?
- Can the authors clarify the relationship between the number of accepted nodes (e.g., in Table 2) and the number of mean accepted tokens (MAT) per forward pass?