- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ScanAR adapts unified autoregressive models to generate image tokens row by row. The first row is generated sequentially, while subsequent rows are predicted in parallel using the preceding row’s hidden states. The method retains the backbone, vocabulary, and output head, and supports both post-training and training from scratch. Experiments cover Emu3.5 text-to-image generation, ImageNet class-conditional generation, and U0 multimodal generation.
Critical strengths
-
The method introduces substantial parallelism without adding prediction heads or changing the tokenizer. Keeping the same output interface is useful for models that alternate between text and images, and the paper explains how training and inference handle the first row consistently.
-
The Emu3.5 results show a substantial practical gain: generation time falls by a lot, while GenEval increases. The vLLM experiment also reports higher throughput and lower peak memory than FlashAR.
Critical weaknesses
-
Preserving unified multimodal capabilities is the main distinction from prior acceleration methods, but the quantitative evidence is narrow. U0 is evaluated on embodied-scene transfer using one automated judge; interleaved generation and video are supported mainly by examples. This does not establish how reliably the adapted model preserves text quality, modality transitions, or temporal consistency.
-
The ImageNet results show a more mixed quality-speed tradeoff than the main text suggests. At XXL scale, ScanAR reaches FID 3.46 vs FlashAR’s 2.79, with only a small throughput advantage, 65.3 vs 63.4 images/s. ScanAR also trains from scratch for 300 epochs, whereas FlashAR adapts a pretrained model for 25 epochs. The emphasis on the best Inception Score obscures these differences.
Questions for authors
-
How many examples were used for the U0 evaluation, and what is the variability of the judge scores? Were missing views or incomplete outputs present, given that the evaluation prompt does not penalize mismatched view counts?
-
Can you provide quantitative comparisons for interleaved text-image and video generation, including output validity and quality before and after adaptation? These would directly support the paper’s main distinction from image-only acceleration methods.
8 comments
Q1: U0 evaluation size, score variability, missing views.
Evaluation size. Table 2 is computed on 300 paired prompts: 150 single-dimension and 150 multi-dimension scene edits (2–5 changed attributes). The prompts come from five embodied sources (AgiBotWorld-Beta, GenieSim, Intern-A1, mibot, OXE). Both models are evaluated on the identical prompt set, with the same judge and the same prompt template (Appendix B.1).
Variability. Per-sample scores (mean ± std over samples):
Depth Background Foreground Lighting Image Quality Multi-View Overall U0 7.44 ± 1.00 7.60 ± 1.39 7.27 ± 1.42 7.50 ± 1.63 8.05 ± 0.57 7.52 ± 1.14 7.52 ± 0.80 ScanAR 7.50 ± 0.91 7.36 ± 1.80 7.21 ± 1.42 7.50 ± 1.68 7.76 ± 0.71 7.60 ± 1.02 7.49 ± 0.84 Because both models share the same prompts, we also report the paired per-prompt difference in the overall score: −0.03, 95% bootstrap CI [−0.13, +0.06]. The interval contains zero, so the overall quality of the two models is statistically indistinguishable. ScanAR is numerically higher on Depth Faithfulness (+0.06) and Multi-View Consistency (+0.08), the two dimensions that most directly test conditional geometric control.
Missing or incomplete outputs. Every one of the 300 prompts produced a valid output for both models. In all 600 judge explanations, no view-count mismatch between depth maps and generated views is reported, and the single-view fallback rule (multi-view consistency = 10) is never triggered. The special rule in our prompt therefore had no effect on any score.
W2: ImageNet quality-speed trade-off at XXL.
The purpose of the ImageNet experiment is to show that ScanAR can be fitted both by training from scratch (LlamaGen, four scales) and by post-training an existing model (Emu3.5, U0). Its comparison point is therefore the from-scratch methods with the same 300-epoch budget. Against these, ScanAR achieves the highest IS at every size and FID close to raster LlamaGen, with 8× fewer sequential steps. FlashAR uses a larger total budget (300 pretraining epochs plus 25 post-training epochs) and starts from a converged raster model.
We will present FID first in the main table, as suggested.
ScanAR's main claim concerns post-training of unified models. There, under the identical FlashAR protocol, ScanAR is better than FlashAR on both quality (GenEval 82.36 vs. 80.29) and latency (4.69 s vs. 5.68 s).
Response to rebuttals
Thanks for adding the video and text-image tests. The U0 details also help answer my questions. The new results are useful, but scene consistency and some video motion scores still go down. Keeping the same output setup does not mean all abilities stay the same. Please explain these drops and show the ImageNet FID results clearly. I will keep my score at 3.
We thank the reviewer for the positive assessment. In particular, the reviewer noted that keeping the same output interface is useful for models that alternate between text and images, and that the paper explains how training and inference handle the first row consistently.
W1 / Q2: Quantitative evidence for unified capabilities; interleaved and video.