- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper observes that under full-token REPA/REG alignment, high-gradient patch tokens concentrate at the same, encoder-specific spatial positions across images. It proposes MaskAlign: two extra SiT blocks as a pre-mask token mixer, then random dropping of 25% of patch tokens during training, with both denoising and alignment losses computed on visible tokens. On ImageNet 256 (SiT-XL/2, 400K, w/o CFG), FID improves 7.9 → 5.5 (REPA) and 3.4 → 2.8 (REG), with 11.7% lower per-step time.
Critical strengths
- Consistent gains at lower cost. Improvements hold across REPA/REG, three alignment encoders, multiple budgets, and multiple FID feature spaces, while per-step time decreases.
- New diagnostic. The cross-sample analysis of alignment gradients is simple and novel.
Critical weaknesses
- Mechanism not isolated. The method masks the backbone input and the denoising loss, not just alignment, making it essentially MicroDiT (mixer + masking) on top of REG. In Table 4, masking alone (3.54) and mixing alone (3.20) are both worse than the baseline (3.01); only the combination helps (2.67). The key missing ablation is alignment-only masking with a full-token forward pass, plus comparisons to MicroDiT/TREAD.
- Weak causal evidence. The heatmap patterns (grid stripes, corner token) resemble known DINOv2 artifact/high-norm tokens, which is not discussed. Nothing links reducing the pattern to the FID gain. (Eq. 9) is circular, since a mask-trained model is naturally robust to masking. There are no seeds or error bars (CFG gains like 1.59 → 1.56 may be noise), and no parameter-matched baseline despite ~8% more parameters.
Questions for authors
- Results with alignment-only masking (full-token forward pass and denoising loss)? (Key to my assessment.)
- Why does mixing without masking hurt (3.01 → 3.20)? Multi-seed results?
- Is Fig. 2b computed with all tokens? Please quantify concentration and relate it to DINOv2 artifact tokens.
- Were CFG settings identical to REG in Table 2? Why does IS drop (321.4 → 310.0)?
- Wall-clock time or FLOPs to reach the same FID?