The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index; 1 of the 5 sources its claims cite were checked for support.
Scalable Diffusion Models with Transformers
Open accessAbstract
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops—through increased transformer depth/width or increased number of input tokens—consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
Diffusion Transformers (DiTs) replace the standard U-Net backbone in latent diffusion models with a transformer operating on latent patches. DiT-XL/2 achieves state-of-the-art class-conditional ImageNet generation, reaching FID 2.27 at 256×256 and 3.04 at 512×512.
Key findings
- DiT block conditioning matters: adaLN-Zero outperforms cross-attention and in-context conditioning at all training stages while being the most compute-efficient; at 400K iterations its FID is nearly half that of the in-context model.
- Scaling DiT Gflops improves sample quality: across 12 models, transformer Gflops and FID-50K at 400K steps have a correlation of −0.93, with gains from increasing depth/width or number of input tokens.
- DiT-XL/2 sets state of the art: FID 2.27 on class-conditional ImageNet 256×256 with classifier-free guidance cfg=1.50, improving on LDM’s previous best 3.60; at 512×512 it reaches FID 3.04 versus ADM’s 3.85.
- Larger DiT models are more compute-efficient, and extra sampling compute cannot compensate for smaller models: DiT-L/2 with 1000 sampling steps uses 80.7 Tflops and gets FID-10K 25.9, while DiT-XL/2 with 128 steps uses 15.2 Tflops and gets FID-10K 23.7.
Methods
- Design: latent diffusion with a frozen off-the-shelf Stable Diffusion VAE (downsample factor 8); DiT patchifies latents, applies ViT-style positional embeddings, processes tokens through N transformer blocks, and linearly decodes to noise and covariance predictions. Design space includes patch sizes p=2,4,8; block variants in-context, cross-attention, adaLN, and adaLN-Zero; model sizes DiT-S/B/L/XL.
- Data and training: class-conditional ImageNet at 256×256 and 512×512; AdamW, constant learning rate 1×10⁻⁴, batch size 256, horizontal flips, EMA decay 0.9999, no learning-rate warmup or regularization; diffusion hyperparameters retained from ADM; implemented in JAX on TPU-v3 pods.
- Evaluation: FID-50K with 250 DDPM sampling steps using ADM’s TensorFlow evaluation suite; 12 DiT models swept over S/B/L/XL and p=8/4/2 at 400K steps; DiT-XL/2 trained for 7M steps at 256×256 and 3M steps at 512×512; additional comparisons of conditioning strategies and model versus sampling compute.
Limitations
- The paper does not state an explicit limitations section.
- Evident from the text: experiments are limited to class-conditional ImageNet at 256×256 and 512×512; text-to-image and other domains are left to future work.
- Evident from the text: DiTs use a frozen off-the-shelf VAE, so generation quality depends on that VAE; training hyperparameters were retained from ADM and not tuned; pixel-space DiT is mentioned as possible but not tested.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
28 Own result · 5 Own interpretation · 4 No basis given · 3 Sources not found · 2 Own method · 1 Partly supported · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As shown in Figure 2, LDMs achieve good performance while using a fraction of the Gflops of pixel space diffusion models like ADM.”
§ 3. Diffusion Transformers > 3.1. Preliminaries
What the sources say
- Partly supportedcites [48] sourceExperimental — accuracy not yet measured
Section 4.2 reports performance close to ADM on LSUN-Bedrooms while using four times fewer training resources, and Appendix D.4 describes competitive ImageNet performance with lower compute requirements. These passages support the performance-and-efficiency comparison, but our copy does not give a GFLOPs comparison with ADM; it reports training resources instead. (LLM, conf=0.85)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Larger DiT models are more compute-efficient.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Adaptive layer norm works best.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Transformer Gflops are strongly correlated with FID.”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Performance steadily improves in FID as model flops increase.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing transformer forward pass Gflops increases sample quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results demonstrate that different DiT configs obtain similar FID values when their total Gflops are similar (e.g., DiT-S/2 and DiT-B/4).”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, scaling both model size and the number of tokens yields notable improvements in visual quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all four configs, significant improvements in FID are obtained over all stages of training by making the transformer deeper and wider.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Scaling the transformer backbone yields better generative models across all model sizes and patch sizes.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 4
- Probably not a substantial claim. 6
- It may state two separate claims as one. 18
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Cross-attention adds the most Gflops to the model, roughly a 15% overhead.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“As with prior work using guidance, we observe that larger scales increase visual fidelity and decrease sample diversity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For both the 256 × 256 and 512 × 512 DiT-XL/2 models, we never observed FID saturate and continued training them as long as possible.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of the three block designs we explore, adaLN adds the least Gflops and is thus the most compute-efficient.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 2. Benchmarking class-conditional image generation on ImageNet 256×256. DiT-XL/2 achieves state-of-the-art FID.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When trained for only 2.35M steps (similar to ADM), XL/2 still outperforms all prior diffusion models with an FID of 2.55.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XL/2 again outperforms all prior diffusion models at this resolution, improving the previous best FID of 3.85 achieved by ADM to 3.04.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we did not find learning rate warmup nor regularization necessary to train DiTs to high performance.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the Gflops in the model—either by increasing transformer depth/width or increasing the number of input tokens—yields significant improvements in visual fidelity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find a strong negative correlation between model Gflops and FID-50K, suggesting that additional model compute is the critical ingredient for improved DiT models.”
- Also stated in: § 100 101 102 · boosted
“Transformer Gflops are strongly correlated with FID.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 100 101 102 · boosted
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, we also observe that DiT-XL/2 achieves higher recall values at all tested classifier-free guidance scales compared to LDM-4 and LDM-8.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing DiT model Gflops (via transformer size or number of input tokens) causes the training loss to decrease more rapidly and saturate at a lower value.”
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
“Note that scaled-up DiT models exhibit lower training losses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We did not tune learning rates, decay/warm-up schedules, Adam β1/β2 or weight decays.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“which have been shown to scale more effectively for visual recognition than traditional convolutional networks (e.g., ResNet [15]).”
What the sources say
- Not matchedcites [10] Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Even without these techniques, training was highly stable across all model configs and we did not observe any loss spikes commonly seen when training transformers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“diffusion models have been at the forefront of recent advances in image-level generative models [9,46]; yet, they all adopt a convolutional U-Net architecture as the de-facto choice of backbone.”
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [46] Ramesh, 2022, Hierarchical text-conditional image generation with clip latents
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“Note that prior work [9] measures Precision and Recall using 1000 real samples for 512 × 512 resolution; for consistency, we do the same.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 1,000- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“halving pwill quadruple T , and thus at least quadruple total transformer Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A smaller patch size p results in a longer sequence length and thus more Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper relies on this without support.
FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
“We show samples from the model in Figures 1, and we compare against state-of-the-art class-conditional generative models. We report results in Table 2.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Unlike prior works that employ text-to-image (T2I) U-Net [10, 33, 35, 40] for talking head generation, MoCha is built on a diffusion transformer (DiT) [26]. By incorporating text and speech conditions sequentially via cross-attention, it effectively captures both semantics and temporal dynamics.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [26]
In the citing paper
“Supervised learning, a foundational approach in AI, uses labeled datasets to guide models towards accurate predictions, and it has been integral to various applications, including image recognition and NLP [163], [164], [165].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [164]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Research works printed but not linked: 3
- Chen, Generative pre-training from pixels
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- Goodfellow, Generative adversarial nets
Cited by
Sorted by citations
Items 2,701–2,800 of 3,684
Lu, P., Chen, P.-W., Yeh, S.-H., Zhang, Z.-J., Chen, Y.-T., Wang, T., & Huang, C.-T. (2026) · Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference · doi:10.1109/isscc49663.2026.11409204
Goyal, A., Singh, S., MITTAL, A., Tadepalli, M., Kumar, P., & Putha, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.01659
Hsieh, S.-W., Chen, Y.-S., Tsai, P.-Y., Lin, M., Cheng, C.-Y., Hsu, L.-F., Huang, P.-H., Chih, H.-W., Chiang, P.-H., Chang, C.-M., et al. (2026) · Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference · doi:10.1109/isscc49663.2026.11409294
Rahman, Z., Sheng, A., & Meo, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.01509
Compositional Visual Planning via Inference-Time Diffusion ScalingPreprint
Zhang, Y., Luo, Y., Mishra, U. A., Shin, W. C., Chen, Y., & Xu, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.02646
Μοντέλα διάχυσης για δημιουργική επεξεργασία εικόνων
Katsantas, I. (2026) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.31510
Diffusion Models: A Systematic Review From Generative Theory to Applications in Group Activity
Wu, F., & Zhang, G. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401756
Topology-Induced Graph Transformer for Graph Representation Learning
Liang, P., Chen, Y., & He, X. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402319
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled DiffusionPreprint
Jiang, P., Li, J. Y., Ryu, M., Hu, R. L., Su, K., Wan, Z. Y., Hebert, L., Peng, H., Han, J., Kuzmin, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.06397
Pinterest Canvas: Large-Scale Image Generation at PinterestPreprint
Wang, Y., Tzeng, E., Shiau, R., Yang, J., Kislyuk, D., & Rosenberg, C. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.06453
RePer-360: Releasing Perspective Priors for 360$$^\circ $$ Depth Estimation via Self-modulation
Guan, C., Lin, C., Shen, Z., Zhang, J., & Wang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_18
Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion TransformersPreprint
Zhang, M., Dai, X., Yao, Y., & Yin, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.07472
Tian, Y., Zhao, X., Liu, Y., Yang, B., & Wu, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.08143
PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
Pham, T.-T., Nguyen, L., Nguyen, A., Nguyen, H., & Le, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38233-7_37
Huang, W., Fan, R., & Su, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3673750
BiGain: Unified Token Compression for Joint Generation and ClassificationPreprint
Liu, J., Tang, S., Cui, J., Xu, D., & Shen, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.12240
Knit-Edit: A Unified Multi-Task Editing Framework for Knitted Garments
Wu, Z., Fu, Q., Li, J., & Liu, J. (2026) · Electronics · doi:10.3390/electronics15061208
DiffusionHandover: Reliable Human-to-Robot Handover Generation With Anthropomorphic Hand
Yang, Y., Wang, S., Luo, Y., Li, D., Huang, Y., Yan, D., Duan, H., & Wang, P. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3674002
GAN-based fast calorimeter simulation of the ATLAS experiment
Corchia, F. A., & Rinaldi, L. (2025) · CERN Document Server (European Organization for Nuclear Research) · doi:10.1393/ncc/i2025-25276-9
LAM-assisted Acoustic Eavesdropping in Multi-speaker Scenarios via Commercial mmWave Radar
Liu, G., Wang, L., Jiang, M., Qiao, Q., Li, K., Dai, H., & Chen, G. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3789687
PRD$^{3}$M: Prototype Representation Dataset Distillation via Diffusion Model
Xiao, W., Ma, Y., Wu, S., Shan, Q., Wang, Y., & Su, J. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3673581
IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset DistillationPreprint
Wang, C., Chen, Y., Yang, Z., Zhou, J. T., & Zhang, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.13960
Zhang, Z., Zhao, X., & Curtis, A. (2026) · Water Resources Research · doi:10.1029/2025wr042519
Hyun, J., Hong, S., & Lee, Y. (2026) · IEEE transactions on circuits and systems for artificial intelligence. · doi:10.1109/tcasai.2026.3674441
NumColor: Precise Numeric Color Control in Text-to-Image Generation
Butt, M. A., Hernández, D., Gomez-Villa, A., Wang, K., Vázquez-Corral, J., & van de Weijer, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_9
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion TransformersPreprint
Gal, E., Eliasof, M., & Haber, E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.13663
CamLit: Unified Video Diffusion with Explicit Camera and Lighting ControlPreprint
Kuang, Z., He, C., Zakharov, E., Xue, Y., Saito, S., Maury, O., Bagautdinov, T., Zheng, Y., & Nam, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.14241
Maduabuchi, C. C., & Wang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_6
Causal Image Processing: A Mechanism-Based Framework for Secure Visual Intelligence
Arslan, B. (2026) · International Journal of Information Security Science · doi:10.55859/ijiss.1826477
Zheng, G., & Li, X. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3675911
Scale as Condition: A Conditional Transformer for Motor Imagery Decoding
Ma, X., Han, T.-S., Kim, H., Kim, H., & Kim, D.-H. (2026) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci69045.2026.11435099
PromptNeedling: Jailbreaking Text-to-Video Generative Models
Mu, Y., Li, H., Zhang, R., Jiang, W., & Fan, W. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432140
One-Step Image-Function Generation via Consistency Training
Liu, K., Liu, F., Gu, J., Zhang, S., Wang, Z., Bu, J., Han, B., & Wang, H. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3676205
Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
Yang, Y., Chang, D., Ling, Y., Du, R., & Ma, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_33
Importance-Aware Dynamic Compression for Efficient Diffusion Models Inference
Gu, C., Li, G., Ling, J., Lin, X., Song, Z., Cheng, J., & Liang, X. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3676332
Revisiting Autoregressive Models for Generative Image Classification
Sudakov, I. P., Babenko, A., & Baranchuk, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_28
Progressive Orthodontic Motion Planning Based on Hierarchical Diffusion Transformer
Fan, Y., Zhou, Y., Liu, W., Wei, G., Cui, Z., Shen, Y., Liu, Y., & Wang, W. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3676039
Tiered Social Recursion: A Functional Architecture for the Evolution of Consciousness
Tochilov, S. (2026) · PhilPapers (PhilPapers Foundation) · doi:10.5281/zenodo.19153449
DiffTile: High-Resolution Periodic Pattern Generation via Splice, Focus and Enhance
Lan, X., Niu, C., Xu, S., Gao, W., Zhang, L., Liu, J., & Yang, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3676838
Alonso, X. G. (2025) · UPCommons institutional repository (Universitat Politècnica de Catalunya)
Hu, X., Mun, H., He, Y., Meng, J., Liao, Y., & Seo, J.-S. (2026) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2026.3675444
Neural Network Parameter Mixed Error Diffusion Model Based on Channel Grouping and Half Convolution
Hu, K. (2025) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc68654.2025.11438183
Mijares, M. A. L. (2026) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Uncertainty-Gated Adapter for Visual Autoregressive Generation
Xu, Y., Xiong, G., & Su, X. J. (2025) · International Conference on Big Data and Data Mining (BDDM) · doi:10.1109/bddm68348.2025.11442247
ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors
Yu, H., Zhang, Y., Di, D., Zhang, R., & Zuo, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_15
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
Lobba, D., Sanguigni, F., Ren, B., Cornia, M., Cucchiara, R., & Sebe, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37602-2_4
CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis
Seyfarth, M., Müller, S. K., Ghanaat, A., Ayx, I., Fastenrath, F., Wild, P. S., Hertel, A., Papavassiliu, T., Dar, S. U. H., & Engelhardt, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_7
DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation
Ouyang, J., Teng, W., Chen, G., Zhao, Y., & Chen, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_35
Infinite Gaze Generation for Videos with Autoregressive Diffusion
Kang, J., Groth, C., Wu, T., Torrens, F., Sangkloy, P., Wetzstein, G., & Sun, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_5
Background-Noise-Driven Detection of Diffusion-Generated Images
Li, J., Ou, W., Meng, D., & Xu, Y. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3678476
High-Fidelity Digital Twin Channel Modeling for RIS-Assisted Wireless Communication Systems
Fang, Y., Xu, S., Fang, C., He, S. T., Li, C., Huang, Y., & Yang, L. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3679264
Zhang, Y., Shen, L., Yu, Z., Ma, C., & Gao, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3750724
PureConvNet: Rethinking Pure Convolutions for Efficient Diffusion-Based Image Generation
Cao, C., Wei, M., & Tian, T. (2025) · International Conference on Cyberworlds (CW) · doi:10.1109/cw68232.2025.00075
CIPHER: Counterfeit Image Pattern High-level Examination via RepresentationPreprint
Kim, K., Han, Y., Ju, S., Jean, Y., Kim, Y., Choi, M., Lim, S., Park, K., Baek, S., Hyeon, S., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.29356
Liu, T., Liu, Y., Li, B., & Hu, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.27987
LayerDiffusion: High-Fidelity Layered Virtual Try-On via Semantic-Aware Diffusion
Liao, F., Zou, X., & Wong, W. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3679372
LACON: Training Text-to-Image Model from Uncurated Data
Liang, Z., Wan, Z., Liu, H., Chen, D., Shen, Q., Zhu, H., & Chen, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_22
Blended and Generative All Sky Imager Nowcast
Nouri, B., & Fabel, Y. (2025) · elib (German Aerospace Center)
Enhancing Data Quality with a Novel Neural Parameter Diffusion Approach
Yang, J., Hu, K., Yu, Z., & Zhang, Z. (2026) · Data · doi:10.3390/data11040072
MIMO Channel Estimation Using Transformer-Based Generative Diffusion Models
Song, W., Zhang, J., Yang, S., Li, Y., Ni, Y., & Jin, S. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3680259
RawGen: Learning Camera Raw Image Generation
Kim, D., Lee, J., Punnappurath, A., Afifi, M., Han, S.-C., Levinshtein, A., & Brown, M. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37235-2_3
Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion
Dominici, E. A., Deixelberger, T., Vardis, K., & Steinberger, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_5
Identity-consistent and high-fidelity audio-driven portrait animation with enhanced latent diffusion
Ma, X., Zhao, J., Huang, X., Li, S., Li, Y., & Yin, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-46445-6
Rethinking Personalized T2I Diffusion Models from the Perspective of Redundancy
Wang, X., Lei, B., Xu, X., Wu, F., & Zhang, M. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02801-7
Adaptive Quantile Guidance in Diffusion Models: Multi-Dataset Learning for Pandemic Time Series
Odum, J., & Mller, J. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00080
Paper Espresso: From Paper Overload to Research Insight
Du, M., Tuan, L. A., Huang, D., & Ng, S.-K. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840141
Sheikhbahaee, Z., Safron, A., Sakthivadivel, D. A. R., Albarracin, M., & Rish, I. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-16955-6_7
Intelligence artificielle pour la configuration et l’achat de campagnes publicitaires en ligne
Benamara, I. (2024) · theses.fr (ABES) · doi:10.70675/2048fa06zeb3ez42cfz86b7z5c489d68e62e
OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
Wang, Y., Li, R., Tao, J., Yang, S., Chen, L., Yang, Z., Handz, Guo, Y., Shao, S., & Lu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_29
Deep Generative Models for Conditional Spatial Simulation
Bhavsar, F. (2024) · theses.fr (ABES) · doi:10.70675/1ec89744z12c9z49abzac9az4a29f3409a84
Li, J., Han, Q., Zhang, H., & Li, L. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02293-5
Internal methods for the generation and inpainting of images and videos
Cherel, N. (2024) · theses.fr (ABES) · doi:10.70675/c150b98az8511z4246zb69dz883db7f96d05
Towards explainable and interpretable deep neural networks
Jeanneret, G. (2024) · theses.fr (ABES) · doi:10.70675/ed07566bze7a3z4daazb9d7z03fd028f66ce
Improving control of neural networks facing visual perturbations
Cordier, T. (2025) · theses.fr (ABES) · doi:10.70675/a4edd425ze27ez4df1z890dz111029659b3b
DiffVecMap: A Robust Online Vectorized HD Map Construction Method With a Diffusion Model
Wu, K., Zhang, H., Shi, M., & Tang, S. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3682549
Re-Diffusion: Modeling Latent Residuals with Diffusion for Time-Series Forecasting
Zhang, B., Wang, H., Hu, Z., Wang, J., Zhang, H., & Hu, J. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792539
NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and ResultsPreprint
Zou, W., Liu, T., Wu, K., Zhuang, H., Wu, Z., Zhou, Z., Timofte, R., Yap, K., Chau, L., Wang, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.06945
A Synthetic Dataset Generation Method and System for Electric Power Safety Violations
Du, K., Li, Z., Li, N., & Xiong, C. (2025) · International Conference on Energy, Power and Grid (ICEPG) · doi:10.1109/icepg67373.2025.11466929
Extending Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
Xiang, J., Wang, T., Wang, J., Wang, P., Chen, C., & Wang, N. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3740150
LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
Wang, Q., Shen, Z., Chen, M., Yu, G., Pang, C., Zhao, W., & Zhou, W. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836200
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Karypidis, E., Gidaris, S., & Komodakis, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_14
Zhu, D., Li, P., & Jin, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.12209
Huang, Y., & Yang, Z. (2026) · Springer eBooks · doi:10.1007/978-981-95-3725-9_16
Jiang, Z., Qian, C., Zhang, H., Zhou, B., & Liu, L. (2026) · Geo-spatial Information Science · doi:10.1080/10095020.2026.2655551
OcularWorldSim: A Visual World Model for Ophthalmic Microsurgery With Sim-to-Real Transfer Learning
Chen, H., Zhu, L., Lian, L., Bai, Y., & Liu, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3684562
Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution
Stambaugh, C., & Rao, R. (2026) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2026.es2026-30
BiT‐MoFE: Unified illumination correction in capsule endoscopy
Ding, H., Tian, Y., Liu, T., Liu, H., & Wan, L. (2026) · Journal of intelligent medicine. · doi:10.1002/jim4.70034
MirrorTalk: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
Lu, R., Zhang, X., Qu, X., Wang, J., & Wang, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462039
ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation
Gao, L., Xu, Y., Koch, W., Ruffino, S., Rowe, L., Chalaki, B., Rivkin, D., Ost, J., Girgis, R., Bijelic, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_13
ReLo-IRR: Reflection-Guided Lora Framework for Image Reflection Removal
Wang, C., Wei, Y., Cao, H., & Min, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463607
Pamisetty, G., & Shree, A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462369
NCF-TTS: Enhancing Flow Matching Based Text-To-Speech with Neighborhood Consistency Flow
Shi, Y., Shi, J., Chen, M., Zhuang, Z., Qi, P., Wang, S., & Xiao, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463508
Generative Audio Extension and Morphing
Seetharaman, P., Nieto, O., & Salamon, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463473
SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning
Jovišić, N., Škipina, M., & Švenda, V. (2026) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech70133.2026.11685500
Wu, Y., Yang, G., Tang, C., Gao, Q., Wu, P., & Cui, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462093
A Training-Free Framework for High-Fidelity Appearance Transfer via Diffusion Transformers
Gu, S., Wang, Y., Wu, S., Ma, R., Wang, Q., Wang, L., & Yi, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464396
Coevolving Representations in Joint Image-Feature Diffusion
Kouzelis, T., Gidaris, S., & Komodakis, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37095-2_21
Yang, J., Wu, R., Shen, W., Li, M., Liu, Y., She, H., & Yuan, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37595-7_19
Zhang, H., Shen, Q., Ma, Y., Li, D., Pan, Y., Zhu, Y., & Luo, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464658
Metadata
- Authors
- Peebles, W., & Xie, S.
- Affiliations
- University of California, Berkeley (US)
- New York University (US)
- ORCID
- Xie, Saining
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 4172-4182
- OpenAlex
- W4390872297
- Semantic Scholar
- 736973165f98105fec3729b7db414ae4d80fcbeb
- Cited by
- 2,284
- References
- 59
- Citations by year
- 2026: 1007 · 2025: 925 · 2024: 315 · 2023: 37
- FWCI
- 244.26
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- diffusion models, latent diffusion models, diffusion transformer, scalability, image generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
