- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper targets efficient generation of high-dimensional discrete visual tokens (16×16×768 cubes from dimension-wise quantized DINOv2/RAE features). The prior method, CubiD, uses mask diffusion and needs up to 1536 steps, degrading sharply with fewer. The authors attribute this to parallel factorization error: independently sampling many correlated coordinates produces inconsistent tokens that a mask-trained denoiser never sees during training. They propose CUDiT, which replaces mask corruption with uniform-noise Discrete Flow Matching so the model learns from noisy content states. On ImageNet 256×256, CUDiT-XL achieves gFID 1.99 in 64 steps, matching CubiD-XL at 1536 steps with roughly 40× lower estimated compute. An ablation suggests the gain comes from the training distribution rather than the ability to revise tokens.
Critical strengths
-
Important research problem. Discrete generation on high-dimensional semantic tokens is a promising route toward unified multimodal models, but existing methods such as CubiD [3] require up to 1536 sampling steps for high-quality results, which limits practical use. Reducing this cost is a timely and well-motivated problem, and progress here could directly benefit future unified architectures.
-
Strong empirical efficiency gains. CUDiT-XL reaches gFID 1.99 in 64 steps, matching CubiD-XL at 1536 steps with roughly 40× fewer estimated FLOPs, and remains stable across 32 to 128 steps. The revisability ablation also offers a useful insight: training on noisy content states, rather than the ability to revise tokens alone, appears to drive the improvement. This makes the paper a valuable empirical reference for this setting.
Critical weaknesses
-
Limited novelty. The factorization analysis closely follows ReDi [1], which already characterizes factorization error via conditional total correlation and shows it grows in few-step generation. The method is also close to URSA [2], which applies uniform discrete diffusion with a similar timestep shift to visual generation and already shows its advantage over masked diffusion. CUDiT's genuine increments are the extension to high-dimensional cubes and the revisability ablation, but without discussing these works, the contribution is overstated and hard to assess.
-
Unfair baseline comparison. The masked baselines may not be at their best. Stronger samplers for masked diffusion (e.g., confidence-based unmasking or remasking) are not considered, and in the key ablation (Table 6) the mask variants reach gFID ~26 at 64 steps, far worse than the ~9 CubiD[3] reports at 64 steps in its own ablation. The reported gap may therefore be partly inflated.
-
Limited few-step range. The lowest budget reported is 32 steps. Results at 16 or 8 steps would better support the few-step claim, as the few-step literature typically targets this regime.
Minor:
-
I found the text font size in the main pipeline figure (Fig. 3) is too small and is hard to read.
-
The paper does not report the compute required for training (e.g., hardware or GPU hours).
Reference:
[1] Yoo et al. ReDi: Rectified Discrete Flow. NeurIPS 2025.
[2] Deng et al. Uniform Discrete Diffusion With Metric Path for Video Generation. ICLR 2026.
[3] Wang et al. Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens. CVPR 2026.
Questions for authors
-
How does CUDiT differ from ReDi in its factorization analysis and from URSA in its method? Please clarify the specific increment beyond these works.
-
Why do the mask variants (gFID 26 at 64 steps) perform much worse than CubiD’s own reported result (9 at 64 steps)? Did they use CubiD’s original masking schedule and hyperparameters? Please also clarify how the CTMC-Mask variant revises previously revealed tokens under an absorbing path.
-
Could you report CubiD at 64 steps with stronger samplers (e.g., confidence-based unmasking or remasking)? If the gap to CUDiT remains large, this would substantially strengthen the main claim.
-
How does CUDiT perform at 16 or 8 steps?
10 comments
Response to Reviewer Dxum (part 2/4)
[W2&Q2] Why do the mask variants (gFID 26 at 64 steps) perform much worse than CubiD’s own reported result (9 at 64 steps)? Did they use CubiD’s original masking schedule and hyperparameters? Please also clarify how the CTMC-Mask variant revises previously revealed tokens under an absorbing path.
[A2.1]
Why do the mask variants (gFID 26 at 64 steps) perform much worse than CubiD’s own reported result (9 at 64 steps)? Did they use CubiD’s original masking schedule and hyperparameters?
We thank the reviewer for pointing out this discrepancy. We clarify that the mask-based variants in Table 6 are controlled ablations within our CUDiT framework, rather than faithful reproductions of CubiD. Their purpose is to isolate the effects of token revisability and corruption support under matched experimental conditions. The main differences from CubiD are:
-
Architecture and training: CubiD uses a bidirectional Transformer for masked-token prediction, whereas our variants adopt a LightningDiT-B backbone with explicit timestep conditioning and a CTMC-based training objective.
-
Sampling: CubiD progressively unmasks tokens without revision, while our CTMC-Mask variant allows previously generated tokens to be revised. We additionally introduce an Irreversible Mask variant to isolate the effect of revisability.
-
Scheduler: All our variants share the same time-shift schedule, 64-step sampling budget, and temperature (), rather than CubiD's original cosine schedule, to ensure controlled comparisons.
These differences may explain the discrepancy in absolute gFID values. We acknowledge that the shared time-shift schedule may disadvantage mask-based generation. To further examine this factor, we conduct additional experiments using a cosine-based schedule for the mask variants:
| Method | Noise scheduler | Source | Revisable | gFID↓ | IS↑ |
|---|---|---|---|---|---|
| Irreversible Mask | time-shift | Mask | No | 26.64 | 87.7 |
| Irreversible Mask | cosine | Mask | No | 14.8 | 128.4 |
| CTMC-Mask | time-shift | Mask | Yes | 25.31 | 95.19 |
| CTMC-Mask | cosine | Mask | Yes | 11.5 | 144.0 |
| CTMC-Uniform | time-shift | Uniform | Yes | 3.95 | 192.2 |
Using the cosine schedule, which is better suited to mask diffusion, substantially improves generation quality, although a considerable performance gap remains compared with the uniform diffusion approach.
- Training budget and capacity: Our ablation models use a 0.6B-parameter backbone trained from scratch for 100 epochs, whereas CubiD's reported few-step result uses a larger backbone (0.9B) trained for 150 epochs. The corresponding intermediate checkpoint is not publicly available, preventing exact reproduction under our protocol.
Our 64-step evaluation using the publicly released CubiD-Huge-800epochs checkpoint and code yields a gFID of 21.17, compared with the 9.14 reported in CubiD's ablation study. The original 64-step ablation used a different checkpoint, which is not publicly available; therefore, this is not an exact like-for-like reproduction. Nevertheless, we carefully verified the public experimental configuration and repeated the 64-step evaluation multiple times, obtaining consistent results. Using the same public checkpoint and configuration at the default 1536 steps also produces results closely matching those reported in CubiD's main table (Table 5), corroborating our reproduction protocol on the publicly available assets. Taken together, these results suggest that, with the released checkpoint and code, CubiD's few-step degradation could be substantially more severe than the original ablation indicates. This discrepancy reinforces the practical importance of robust few-step generation and the performance gains achieved by CUDiT.
Response to Reviewer Dxum (part 3/4)
[A2.2]
Please also clarify how the CTMC-Mask variant revises previously revealed tokens under an absorbing path.
Thank you for the careful reading. The CTMC-Mask variant uses an absorbing-mask path for training corruption: training states contain clean content and MASK, without full-support content corruption. At inference, however, our sampler removes the monotonic freeze and additionally permits previously revealed coordinates to undergo content-to-content revisions. We do not claim that this modified inference sampler strictly follows the canonical reverse CTMC induced by the standard absorbing-mask probability path; it is designed to isolate the effect of revisability while keeping mask-based training fixed.
Concretely:
- Training corruption path. The forward corruption follows an absorbing mixture of clean content and the mask token (no full-support content corruption). Inference starts from all-MASK.
- Inference update. At each Euler step the denoiser predicts a clean posterior; we sample a target token and form jump rates toward that token. A site jumps with probability .
- How revision happens. Because the inference sampler does not impose the irreversible constraint, already-revealed content tokens remain eligible to jump. When they jump, they are typically rewritten content → content toward the newly sampled .
By contrast, Irreversible Mask uses the same absorbing-mask training corruption but forbids further jumps once a site leaves MASK, so revealed tokens stay fixed.
Response to Reviewer Dxum (part 1/4)
We sincerely thank the reviewer for the thoughtful and constructive review, and for recognizing the importance of efficient discrete generation for high-dimensional semantic representations and its potential relevance to future unified multimodal architectures. We greatly appreciate the recognition of CUDiT's substantial improvements in sampling efficiency and generation quality, as well as the insights from our controlled ablations highlighting the importance of training on noisy content states. All changes are marked in green in the revised manuscript.
[A1] We thank the reviewer for highlighting ReDi and URSA. We acknowledge that conditional total correlation (TC), uniform discrete diffusion, and CTMC sampling have been explored in prior work. CUDiT addresses a distinct challenge in high-dimensional, dimension-wise quantized visual representations. We clarify the differences below.
(1) Comparison with ReDi: Factorization analysis and methodology.
ReDi analyzes factorization error through Conditional TC and addresses it via iterative coupling rectification. In contrast, CUDiT focuses on the severe factorization error arising from parallel sampling across both spatial and channel dimensions in cubic representations. A 768×16×16 cube contains 196,608 categorical coordinates, introducing 768 times more prediction coordinates than spatial-only tokenization at the same resolution. Strong cross-channel dependencies make independent parallel sampling particularly challenging.
We further develop a linear-code model showing that, even with exact coordinate-wise marginals, the probability of obtaining a jointly valid sample can decrease exponentially when the parallel update size exceeds the intrinsic dimension. Unlike ReDi, which directly reduces Conditional TC through coupling rectification, CUDiT mitigates the consequences of factorization errors through full-support denoising, without iterative coupling updates or additional distillation.
(2) Comparison with URSA: Problem setting and methodology.
URSA studies uniform discrete diffusion and CTMC-based refinement for image and video generation. CUDiT instead targets high-dimensional discrete semantic representations produced by dimension-wise quantization, whose enormous and highly redundant product space makes few-step parallel generation particularly difficult.
Our key observation is that parallel factorization produces noisy, potentially inconsistent intermediate states, while absorbing-mask diffusion trains primarily on clean tokens and masks. Full-support uniform corruption addresses this train–inference mismatch by exposing the denoiser to noisy content states during training, improving robustness to sampling errors. We do not claim uniform diffusion or CTMC sampling as new primitives; rather, we identify and validate their effectiveness in this specific representation regime.
(3) Experimental validation.
Our controlled ablation distinguishes full-support corruption from token revisability. Under the same irreversible sampler, switching the corruption source from mask to uniform improves gFID from 26.64 to 6.52. Holding uniform corruption fixed, enabling revisability provides an additional improvement from 6.52 to 3.95. These results identify full-support uniform corruption as the larger contributor while also showing that revisability provides a meaningful additional benefit. Furthermore, CUDiT-XL achieves gFID 1.99 in 64 steps, compared with CubiD-XL's 2.06 in 1,536 steps.
In summary, CUDiT's contribution beyond ReDi and URSA lies in (i) identifying and quantitatively characterizing the factorization bottleneck in high-dimensional cubic representations, (ii) mitigating its consequences through full-support noisy-content training, and (iii) experimentally separating the larger gain from corruption support from the additional benefit provided by token revisability. We will clarify these distinctions in the revised manuscript.