- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper targets in-context generation pipelines that perform self-attention over conditioning and generation tokens in their forward pass. For in-context multi-reference generation, the paper claims that most reference tokens contribute nothing, because of redundancy and distracting details in reference samples. CARVE trains small routers that progressively delete these tokens along the depth of the network.
Critical strengths
S1. The methodology is novel, it is faster to keep the backbone frozen and to train small adapters that can reduce tokens at little cost to performance. Instead of masking tokens, the paper physically prunes them, making it easy for standard FA to work just as well.
S2. The DDS ablation gives us important insight on how DiTs use in-context learning and how layers influence generation and reference adoption.
S3. The paper presents a well ablated methodology section, with sufficient contribution from proposed elements. The ablations are correctly designed with each component switched off completely for analysis.
Critical weaknesses
W1. The paper in the abstract claims 2x performance improvement ("doubles inference efficiency") but measured speedup is 1.2x on bagel. Would be good if the authors can clarify this point.
W2. Close related works like ToPi and PKA are discussed in related works but not compared against. This comparison is very important to understand how CARVE compares with recent works in the field.
Questions for authors
See Weaknesses
3 comments
Response to Authors
Thank you for your response. The discussion period allows you to revise and upload a new manuscript incorporating changes from the review process. It would be great if you can incorporate these changes.
Authors' Response to Reviewer rcu7
Thank you for the suggestion. We have uploaded a revised PDF with updated efficiency descriptions.
Authors' Response to Reviewer rcu7
Thank you for your careful review and constructive feedback. We report the efficiency measurements and direct comparisons with ToPi and PKA in the responses below.
R3.Q1. Clarification of the speedup claim
Reviewer comment
Response
We report measured DiT latency and attention-compute reduction separately, with each efficiency result scoped to its backbone and metric.
(1) Qwen-Image: wall-clock speedup
(2) BAGEL: compute reduction rather than latency speedup
(3) Manuscript wording
We will revise the abstract and introduction to report inference latency and attention-compute reduction separately for each backbone.
R3.Q2. New comparisons with ToPi and PKA
Reviewer comment
Response
Neither PKA nor ToPi had publicly released official source code at the time of our experiments. We therefore independently reimplemented both methods following their paper descriptions on our Qwen-Image/MICo baseline.
Quality comparison. The following DreamOmni2Bench scores cover all 319 cases. PKA retains the previously reported epsilon=0.6 quality setting.
CARVE achieves the highest Overall score, 4.537, compared with 4.261 for ToPi and 4.3333 for PKA.
Efficiency configuration. For PKA timing, we use the paper's default KSA threshold epsilon=0.2, first-step condition KV caching, and previous-step mask reuse, as described in the PKA paper. Our Qwen-Image inference uses 25 steps, CFG=4.0, seed=0, and reference images of approximately 512 squared pixels. The complete 319-case run at this setting gives a mean DiT time of 37.544 s.
Across these runs with different hardware configurations, CARVE records the shortest DiT time: 33.472 s, versus 56.438 s for ToPi and 37.544 s for PKA.
We will include this comparison and expand the descriptions of the reproduction protocols, experimental configurations, and evaluation metrics in the revised manuscript.