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 201–300 of 3,684
Rayzer: a Self-Supervised Large View Synthesis Model
Jiang, H., Tan, H., Wang, P., Jin, H., Zhao, Y., Bi, S., Zhang, K., Luan, F., Sunkavalli, K., Huang, Q., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00468 · Cited by 50
Watermarking techniques for large language models: a survey
Liang, Y., Xiao, J., Gan, W., & Yu, P. S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11474-6 · Cited by 51
Star: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
Xie, R., Liu, Y., Zhou, P., Zhao, C., Zhou, J. W., Zhang, K., Zhang, Z., Yang, J. Y., Yang, Z., & Tai, Y. Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01589 · Cited by 50
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Tewari, A., Yin, T., Cazenavette, G., Rezchikov, S., Tenenbaum, J. B., Durand, F., Freeman, B., & Sitzmann, V. (2023) · neural information processing systems · doi:10.52202/075280-0542 · Cited by 50
Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures
Sordo, Z., Chagnon, E., Hu, Z., Donatelli, J. J., Andeer, P. F., Nico, P., Northen, T. R., & Ushizima, D. M. (2025) · Journal of Imaging · doi:10.3390/jimaging11080252 · Cited by 51
Accelerating Diffusion Sampling with Optimized Time Steps
Xue, S., Liu, Z., Chen, F., Zhang, S., Hu, T., Xie, E., & Li, Z. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00792 · Cited by 51
Training-Free and Adaptive Sparse Attention for Efficient Long Video Generation
Xia, Y., Ling, S., Fu, F., Wang, Y., Li, H., Xiao, X., & Cui, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01483 · Cited by 49
Fast Sampling of Diffusion Models via Operator Learning
Zheng, H., Nie, W., Vahdat, A., Azizzadenesheli, K., & Anandkumar, A. (2022) · CaltechAUTHORS (California Institute of Technology) · doi:10.48550/arxiv.2211.13449 · Cited by 49
LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
Song, Y., Chen, D., & Shou, M. Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01835 · Cited by 49
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
Chen, Y., Li, Z., Wang, Y., Zhang, H., Li, Q., Zhang, C., & Lin, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37531-5_15 · Cited by 49
Automated residential layout generation and editing using natural language and images
Zeng, P., Gao, W., Li, J., Yin, J., Chen, J., & Lu, S. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106133 · Cited by 48
A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling
Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01964 · Cited by 48
VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
Han, J., Kokkinos, F., & Torr, P. H. S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72627-9_19 · Cited by 48
Goku: Flow Based Video Generative Foundation Models
Chen, S., Ge, C., Zhang, Y., Zhang, Y., Zhu, F., Yang, H., Hao, H., Wu, H., Lai, Z., Hu, Y., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02190 · Cited by 48
OminiControl: Minimal and Universal Control for Diffusion Transformer
Tan, Z., Liu, S., Yang, X., Xue, Q., & Wang, X. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01386 · Cited by 48
Distribution Matching Distillation Meets Reinforcement Learning
Jiang, D., Liu, D., Wang, Z., Wu, Q., Li, L., Li, H., Jin, X., Lu, C., Li, Z., Wang, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37550-6_16 · Cited by 48
All-in-one simulation-based inferencePreprint
Gloeckler, M., Deistler, M., Weilbach, C., Wood, F., & Macke, J. H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.09636 · Cited by 48
A Comprehensive Survey of Image Generation Models Based on Deep Learning
Li, J., Zhang, C., Zhu, W., & Ren, Y. (2024) · Annals of Data Science · doi:10.1007/s40745-024-00544-1 · Cited by 47
Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning
Wang, S., Zhou, T., Shen, Y., Li, Y., Huang, G., & Hu, Y. S. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3528438 · Cited by 50
Ross3d: Reconstructive Visual Instruction Tuning With 3D-Awareness
Wang, H., Zhao, Y., Wang, T., Fan, H., Zhang, X., & Zhang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00866 · Cited by 47
End-to-End Training for Autoregressive Video Diffusion via Self-resampling
Guo, Y., Yang, C., He, H., Zhao, Y., Wei, M., Yang, Z., Huang, W., & Lin, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_18 · Cited by 47
A Spectral Diffusion Prior for Unsupervised Hyperspectral Image Super-Resolution
Liu, J., Wu, Z., & Xiao, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3449073 · Cited by 46
World Models for Learning Dexterous Hand-Object Interactions from Human Videos
Goswami, R. G., Bar, A., Fan, D., Yang, T.-Y., Zhou, G., Krishnamurthy, P., Rabbat, M., Khorrami, F., & LeCun, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37138-6_33 · Cited by 47
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
He, H., Bai, C., Xu, K., Yang, Z., Zhang, W., Wang, D. V., Zhao, B., & Li, X. (2023) · neural information processing systems · doi:10.52202/075280-2832 · Cited by 47
Reconstruction Alignment Improves Unified Multimodal ModelsPreprint
Xie, J. L., Darrell, T., Zettlemoyer, L., & Wang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.07295 · Cited by 47
Generative technology for human emotion recognition: A scoping review
Ma, F., Yuan, Y., Xie, Y., Ren, H., Liu, I., He, Y., Ren, F., Yu, F. R., & Ni, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102753 · Cited by 47
GIVT: Generative Infinite-Vocabulary Transformers
Tschannen, M., Eastwood, C., & Mentzer, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_17 · Cited by 46
Progressive Autoregressive Video Diffusion Models
Xie, D., Xu, Z. W., Hong, Y., Tan, H. X., Liu, D., Liu, F., Kaufman, A. E., & Zhou, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00628 · Cited by 46
Scalable Image Tokenization with Index Backpropagation Quantization
Shi, F., Luo, Z., Ge, Y., Yang, Y., Shan, Y., & Wang, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01488 · Cited by 46
$A_{0}$: An Affordance-Aware Hierarchical Model for General Robotic Manipulation
Xu, R., Zhang, J., Guo, M., Wen, Y., Yang, H., Lin, M., Huang, J., Li, Z., Zhang, K., Wang, L., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01253 · Cited by 46
Shu, Q., Zhu, X., Xu, S., Wang, Y., & Liu, D. (2025) · Remote Sensing of Environment · doi:10.1016/j.rse.2025.114872 · Cited by 47
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
Lorenz, P., Durall, R., & Keuper, J. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00051 · Cited by 47
Video and Audio Deepfake Datasets and Open Issues in Deepfake Technology: Being Ahead of the Curve
Akhtar, Z., Pendyala, T. L., & Athmakuri, V. S. (2024) · Forensic Sciences · doi:10.3390/forensicsci4030021 · Cited by 45
Parallelized Autoregressive Visual Generation
Wang, Y., Ren, S., Lin, Z., Han, Y., Guo, H., Yang, Z., Zou, D., Feng, J., & Liu, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01209 · Cited by 45
Scaling Mesh Generation via Compressive Tokenization
Weng, H., Zhao, Z., Lei, B., Yang, X., Liu, J., Lai, Z., Chen, Z., Liu, Y., Jiang, J., Guo, C., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01036 · Cited by 45
Dream the Impossible: Outlier Imagination with Diffusion Models
Du, X., Sun, Y., Zhu, J., & Li, Y. (2023) · neural information processing systems · doi:10.52202/075280-2660 · Cited by 45
Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion ModelsPreprint
Li, S., Hu, T., Khan, F. S., Li, L., Yang, S., Wang, Y., Cheng, M., & Yang, J. J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.09608 · Cited by 45
An Introduction to Flow Matching and Diffusion ModelsPreprint
Holderrieth, P., & Erives, E. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.02070 · Cited by 45
The Latent Space: Foundation, Evolution, Mechanism, Ability, and OutlookPreprint
Yu, X., Chen, Z., He, Y., Fu, T., Dong, G., Yang, C., Xu, C., Ma, Y., Hu, X., Cao, Z., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.02029 · Cited by 46
LaRa: Efficient Large-Baseline Radiance Fields
Chen, A., Xu, H., Esposito, S., Tang, S., & Geiger, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73247-8_20 · Cited by 44
AV-DiT: Taming Image Diffusion Transformers for Efficient Joint Audio and Video Generation
Wang, K., Deng, S., Shi, J., Hatzinakos, D., & Tian, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755713 · Cited by 48
Diffusion Models for Intelligent Transportation Systems: A Survey
Peng, M., Chen, K., Guo, X., Zhang, Q., Zhong, H., Zhu, M., & Yang, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3613178 · Cited by 44
KV-Edit: Training-Free Image Editing for Precise Background Preservation
Zhu, T., Zhang, S., Shao, J., & Tang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01542 · Cited by 44
Generating realistic neurophysiological time series with denoising diffusion probabilistic models
Vetter, J., Macke, J. H., & Gao, R. (2024) · Patterns · doi:10.1016/j.patter.2024.101047 · Cited by 44
Diffusion Models for Medical Image Computing: A Survey
Shi, Y., Abulizi, A., Wang, H., Feng, K., Abudukelimu, N., Su, Y., & Abudukelimu, H. (2024) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010047 · Cited by 44
Machine learning for modelling unstructured grid data in computational physics: A review
Cheng, S. L., Bocquet, M., Ding, W., Finn, T. S., Fu, R., Fu, J., Guo, Y., Johnson, E., Li, S., Liu, C., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103255 · Cited by 45
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
Xue, Q., Yin, X., Yang, B., & Gao, W. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01754 · Cited by 43
Is tokenization needed for masked particle modeling?
Leigh, M., Klein, S. B., Charton, F., Golling, T., Heinrich, L., Kagan, M., Ochoa, I., & Osadchy, M. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/addb98 · Cited by 43
InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video DubbingPreprint
Yang, S., Kong, Z., Gao, F., Cheng, M., Liu, X., Zhang, Y., Kang, Z., Luo, W., Cai, X., He, R., et al. (2025) · arXiv (Cornell University) · Cited by 43
VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space MemoryPreprint
Yu, Y., Wu, X., Hu, X., Hu, T., Sun, Y., Lyu, X., Wang, B., Ma, L., Ma, Y., Wang, Z., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.04519 · Cited by 43
The Crack Diffusion Model: An Innovative Diffusion-Based Method for Pavement Crack Detection
Zhang, H., Chen, N., Li, M., & Mao, S. (2024) · Remote Sensing · doi:10.3390/rs16060986 · Cited by 42
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
Lan, Y., Hong, F., Yang, S., Zhou, S., Meng, X., Dai, B., Pan, X., & Loy, C. C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73235-5_7 · Cited by 42
StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
Huang, Y., Yang, H., Luo, C., Wang, Y., Xu, S., Zhang, Z., Zhang, M., & Peng, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681657 · Cited by 42
OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Li, H., Xu, M., Zhan, Y., Mu, S., Li, J., Cheng, K., Chen, Y., Chen, T., Ye, M., Wang, J., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00726 · Cited by 42
An Object is Worth 64×64 Pixels: Generating 3D Object via Image Diffusion
Yan, X., Lee, H.-H., Wan, Z., & Chang, A. X. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00017 · Cited by 42
Multi-Modal Generative AI: Multi-Modal LLMs, Diffusions, and the Unification
Wang, X., Zhou, Y., Huang, B., Chen, H., & Zhu, W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3635224 · Cited by 46
CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation
Zhang, H., Hong, D., Wang, Y., Shao, J., Wu, X., Wu, Z., & Jiang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01718 · Cited by 42
Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey
Zhang, J., Li, Y., Chen, A., Xu, M., Liu, K., Wang, J., Long, X., Liang, H., Xu, Z., Su, H., et al. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70494 · Cited by 42
LinFusion: 1 GPU, 1 Minute, 16K ImagePreprint
Liu, S., Yu, W., Tan, Z., & Wang, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.02097 · Cited by 42
A Survey on Diffusion Models for Recommender SystemsPreprint
Lin, J., Liu, J., Zhu, J., Xi, Y., Liu, C., Zhang, Y., Yu, Y. H., & Zhang, W. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.05033 · Cited by 42
ATI: Any Trajectory Instruction for Controllable Video GenerationPreprint
Wang, A., Huang, H., Fang, J. Z., Yang, Y., & Ma, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.22944 · Cited by 42
stDiff: a diffusion model for imputing spatial transcriptomics through single-cell transcriptomics
Li, K., Li, J., Tao, Y., & Wang, F. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae171 · Cited by 42
BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
Castillo, A., Escobar, M., Jeanneret, G., Pumarola, A., Arbeláez, P., Thabet, A., & Sanakoyeu, A. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00456 · Cited by 42
DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
Zhong, Y., Jiang, Q., Jingyi Yu, A., & Ma, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02103 · Cited by 41
Wu, Z., Zhou, P., Yi, X., Yuan, X., & Zhang, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00944 · Cited by 42
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
Kim, D., He, J., Yu, Q., Yang, C., Shen, X., Kwak, S., & Chen, L.-C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01714 · Cited by 41
FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems
Kim, J., Kim, B. S., & Ye, J. C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01146 · Cited by 41
UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
He, K., Liang, R., Munkberg, J., Hasselgren, J., Vijaykumar, N., Keller, A., Fidler, S., Gilitschenski, I., Gojčič, Ž., & Wang, Z. (2025) · neural information processing systems · doi:10.52202/085713-3615 · Cited by 41
EEdit ⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
Yan, Z., Ma, Y., Zou, C., Chen, W., Chen, Q., & Zhang, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01623 · Cited by 42
SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass
Meng, Y., Wu, H., Zhang, Y., & Xie, W. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00058 · Cited by 41
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation ModelPreprint
Cao, D., Ye, W., Zhang, Y., & Liu, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.02322 · Cited by 41
Generative AI in depth: A survey of recent advances, model variants, and real-world applications
Yazdani, S., Singh, A., Saxena, N., Wang, Z., Palikhe, A., Pan, D., Pal, U., Yang, J., & Zhang, W. (2025) · Journal of Big Data · doi:10.1186/s40537-025-01247-x · Cited by 40
SpaDiT: diffusion transformer for spatial gene expression prediction using scRNA-seq
Li, X., Zhu, F., & Min, W. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae571 · Cited by 43
Cai, M., Cun, X., Li, X., Liu, W., Zhang, Z., Zhang, Y., Shan, Y., & Yue, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00727 · Cited by 40
Align Video Diffusion Model with Online Video-Centric Preference Optimization
zhang, J., Wu, J., Chen, W., Ji, Y., Xiao, X., Huang, W., & Han, K. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00594 · Cited by 40
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear AttentionPreprint
Zhang, J., Wang, H., Jiang, K., Yang, S., Zheng, K., Xi, H., Wang, Z., Zhu, H., Zhao, M., Stoica, I., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24006 · Cited by 40
Retracted: Sora for Scenarios Engineering of Intelligent Vehicles: V&V, C&C, and Beyonds
Li, X., Miao, Q., Li, L., Ni, Q., Fan, L., Wang, Y., Tian, Y., & Wang, F. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3379989 · Cited by 39
RetractedPrecipitation Nowcasting Using Diffusion Transformer With Causal Attention
Li, C., Ling, X., Xue, Y., Luo, W., Zhu, L., Qin, F., Zhou, Y., & Huang, Y. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3510693 · Cited by 38
Zhao, L., Lyu, R., Lei, H., Lin, Q., Zhou, A., Ma, H., Wang, J., Meng, X., Shao, C., Tang, Y., et al. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3678550 · Cited by 39
Adversarial attacks and defenses on text-to-image diffusion models: A survey
Zhang, C., Hu, M., Li, W., & Wang, L. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102701 · Cited by 40
Arbitrary Motion Style Transfer with Multi-Condition Motion Latent Diffusion Model
Song, W., Jin, X., Li, S., Chen, C., Hao, A., Hou, X., Li, N., & Qin, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00084 · Cited by 41
A Conditional Diffusion Model With Fast Sampling Strategy for Remote Sensing Image Super-Resolution
Meng, F., Chen, Y., Jing, H., Zhang, L., Yan, Y., Ren, Y., Wu, S., Feng, T., Liu, R., & Du, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3458009 · Cited by 39
Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion
Nunes, L., Marcuzzi, R., Mersch, B., Behley, J., & Stachniss, C. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01399 · Cited by 39
MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
Song, K., Zhu, Y. C., Liu, B., Yan, Q., Elgammal, A., & Yang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73661-2_7 · Cited by 39
SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
Wang, J., Lin, Z., Wei, M., Zhao, Y., Yang, C., Loy, C. C., & Jiang, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00207 · Cited by 39
FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
Huang, L., Fang, R., Zhang, A., Song, G., Liu, S., Liu, Y., & Li, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73254-6_12 · Cited by 39
MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
Li, Q., Xing, Z., Wang, R., Zhang, H., Dai, Q., & Wu, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01126 · Cited by 39
Seed-Music: A Unified Framework for High Quality and Controlled Music GenerationPreprint
Bai, Y., Chen, H., Chen, J., Chen, Z., Deng, Y., Dong, X., Hantrakul, L., Hao, W., Huang, Q., Huang, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.09214 · Cited by 41
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion TransformerPreprint
Hu, J., Hu, S., Song, Y., Huang, Y., Wang, M., Zhou, H., Liu, Z., Ma, W., & Sun, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.07720 · Cited by 39
Generative Physical AI in Vision: A SurveyPreprint
Liu, D., Zhang, J., Dinh, A.-D., Park, E., Zhang, S., Mian, A., Shah, M., & Xu, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.10928 · Cited by 39
DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image
Gao, D., Rozenberszki, D., Leutenegger, S., & Dai, A. (2024) · ACM Transactions on Graphics · doi:10.1145/3658236 · Cited by 38
Customizing Text-to-Image Models with a Single Image Pair
Jones, M., Wang, S.-Y., Kumari, N., Bau, D., & Zhu, J.-Y. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687642 · Cited by 38
Improved Noise Schedule for Diffusion Training
Hang, T., Gu, S., Bao, J., Wei, F., Chen, D., Geng, X., & Guo, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00456 · Cited by 38
Unicombine: Unified Multi-Conditional Combination with Diffusion Transformer
Wang, H., Peng, J., He, Q., Yang, H., Jin, Y., Wu, J., Hu, X., Pan, Y., Gan, Z., Chi, M., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01703 · Cited by 38
RoboTTT: Context Scaling for Robot PoliciesPreprint
Jiang, Y., Chebotar, Y., Zheng, R., Hu, F., Ge, Y., Wu, J., Dai, T., Reed, S., Fei-Fei, L., Zhu, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.15275 · Cited by 38
Stable Diffusion Segmentation for Biomedical Images with Single-Step Reverse Process
Lin, T., Chen, Z., Yan, Z., Yu, W., & Zheng, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72111-3_62 · Cited by 37
EnergyDiff: Universal Time-Series Energy Data Generation Using Diffusion Models
Lin, N., Pálenský, P., & Vergara, P. P. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3581472 · Cited by 38
Zero-Shot Detection of AI-Generated Images
Cozzolino, D., Poggi, G., Nießner, M., & Verdoliva, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72649-1_4 · Cited by 37
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images
Gu, J., Gao, Q., Zhai, S., Chen, B., Liu, L., & Susskind, J. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00030 · Cited by 39
MARCA: Mamba Accelerator with Reconfigurable Architecture
Li, J., Huang, S., Xu, J., Liu, J., Ding, L., Xu, N., & Dai, G. (2024) · doi:10.1145/3676536.3676798 · Cited by 37
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
