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 501–600 of 3,684
On the use of deep learning for computer-generated holography
Yu, X., Zhang, H., Zhao, Z., Fan, X., Hu, S., Li, Z., Chen, W., Li, D., Shi, S., Xiong, W., et al. (2025) · iScience · doi:10.1016/j.isci.2025.112507 · Cited by 20
DreamTeacher: Pretraining Image Backbones with Deep Generative Models
Li, D., Ling, H., Kar, A., Acuna, D., Kim, S. W., Kreis, K., Torralba, A. B., & Fidler, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01531 · Cited by 19
Coarse-to-fine mechanisms mitigate diffusion limitations on image restoration
Wang, L., Yang, Q., Wang, C., Wang, W. W., & Su, Z. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104118 · Cited by 22
Wang, C., Zhou, Y., Wang, Q., Wang, Z., & Zhang, K. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758301 · Cited by 20
EmotiCrafter: Text-to-Emotional-Image Generation Based on Valence-Arousal Model
Dang, S., He, Y., Ling, L., Qian, Z., Zhao, N., & Cao, N. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01412 · Cited by 20
SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
Liu, J., Zou, C., Lyu, Y., Ren, F., Wang, S., Li, K., & Zhang, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755331 · Cited by 24
DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
Kalaria, D., Harithas, S. S., Katara, P., Kwak, S., Bhagat, S., Sastry, S., Sridhar, S., Vemprala, S. H., Kapoor, A., & Huang, J. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696795 · Cited by 20
Römer, R., Zhang, Y., Li, Y., & Schoellig, A. P. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3693992 · Cited by 20
Fact Embedding through Diffusion Model for Knowledge Graph Completion
Long, X., Zhuang, L., Li, A., Li, H., & Wang, S. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645451 · Cited by 20
Scalable Ranked Preference Optimization for Text-To-Image Generation
Karthik, S., Coşkun, H., Akata, Z., Tulyakov, S., Ren, J., & Kag, A. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01710 · Cited by 20
BOOT: Data-free Distillation of Denoising Diffusion Models with BootstrappingPreprint
Gu, J., Zhai, S., Zhang, Y., Liu, L., & Susskind, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.05544 · Cited by 20
Hidden in the Noise: Two-Stage Robust Watermarking for ImagesPreprint
Arabi, K., Feuer, B., Witter, R. T., Hegde, C., & Cohen, N. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.04653 · Cited by 20
Timeline and Boundary Guided Diffusion Network for Video Shadow Detection
Zhou, H., Wang, H., Tian, Y., Xing, Z., Ma, J., Li, P., Wang, Q., & Zhu, L. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681236 · Cited by 19
SPOK: tokenizing geographic space for enhanced spatial reasoning in GeoAI
Fei, H., Lv, J., Li, G., & Yue, Y. (2025) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2025.2497810 · Cited by 19
DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer
Levi, E., Brosh, E., Mykhailych, M., & Perez, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00201 · Cited by 19
A review of deep learning based multimodal forgery detection for video and audio
Tan, D., Yang, Y., Niu, C., Li, S., Yang, D., & Tan, B. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07629-3 · Cited by 19
Emerging AI approaches for cancer spatial omics
Noorbakhsh, J., pour, A. F., & Chuang, J. H. (2025) · GigaScience · doi:10.1093/gigascience/giaf128 · Cited by 19
Unlimited-Size Diffusion Restoration
Wang, Y., Yu, J., Yu, R., & Zhang, J. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00123 · Cited by 21
DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays
Liu, X., Qiao, Z., Liu, R., Li, H., Zhang, J., Zhen, X., Qian, Z., & Zhang, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72775-7_26 · Cited by 19
ORSIDiff: Diffusion Model for Salient Object Detection in Optical Remote Sensing Images
Han, J., Sun, J., Wang, F., Sun, F., & Li, H. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3579272 · Cited by 19
Surveying Racial Bias in Facial Recognition: Balancing Datasets and Algorithmic Enhancements
Sumsion, A. W., Torrie, S. A., Lee, D.-J., & Sun, Z. (2024) · Electronics · doi:10.3390/electronics13122317 · Cited by 19
Distinguished Quantized Guidance for Diffusion-based Sequence Recommendation
Mao, W., Liu, S., Liu, H., Liu, H., Li, X., & Hu, L. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714955 · Cited by 19
Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
Xu, P., Jiang, B., Hu, X., Luo, D., He, Q., Zhang, J., Wang, C., Yun-sheng, W., Ling, C. X., & Wang, B. (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/cvpr52734.2025.02652 · Cited by 19
ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editing
Pan, Y., He, X., Mao, C., Han, Z., Jiang, Z., Zhang, J., & Liu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01540 · Cited by 19
Wang, H., Hai, J., Yang, D., Chen, C., Li, K., Peng, J., Thebaud, T., Moro-Velázquez, L., Villalba, J., & Dehak, N. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3682073 · Cited by 19
DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
Ye, H., & Xu, D. (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/cvpr52733.2024.02641 · Cited by 19
DOLLAR: Few-Step Video Generation Via Distillation and Latent Reward Optimization
Ding, Z., Jin, C., Liu, D., Zheng, H., Singh, K. K., Zhang, Q., Kang, Y., Lin, Z., & Liu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01669 · Cited by 19
Lu, Y., Ren, Y., Xia, X., Lin, S., Wang, X., Xiao, X., Ma, A. J., Xie, X., & Lai, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01562 · Cited by 19
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
Chen, J., Zou, D., He, W. L., Chen, J., Xie, E., Han, S., & Cai, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01825 · Cited by 19
PlayerOne: Egocentric World Simulator
Tu, Y., Luo, H., Chen, X., Bai, X., Wang, F., & Zhao, H. (2025) · neural information processing systems · doi:10.52202/085713-4861 · Cited by 19
JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing
Huang, X., He, H., Zhou, H., Yang, Q., Wen, S., & Han, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_19 · Cited by 19
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
Fan, W., Diao, H., Wang, Q., Da, H., & Liu, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37138-6_23 · Cited by 19
Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
Zheng, S., Feng, L., Wang, X., Zhou, Q., Cai, P., Zou, C., Liu, J., Lin, Y., Chen, J., Ma, Y., et al. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i16.38349 · Cited by 20
UnZipLoRA: Separating Content and Style from a Single Image
Liu, C., Shah, V., Cui, A., & Lazebnik, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01558 · Cited by 19
USP: Unified Self-Supervised Pretraining for Image Generation and Understanding
Chu, X., Li, R., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01717 · Cited by 19
Probabilistic Emulation of a Global Climate Model with Spherical DYffusionPreprint
Cachay, S. R., Henn, B., Watt‐Meyer, O., Bretherton, C. S., & Yu, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.14798 · Cited by 19
Scalable Behavior Cloning with Open Data, Training, and EvaluationPreprint
Allshire, A., Singh, H., Singh, R., Rashid, A., Choi, H., McAllister, D., Yu, J., Chen, Y., Huang, H., Abbeel, P., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.27375 · Cited by 19
Liu, J., Zeng, S., Ding, L., Soedarmadji, W., Zhou, H., Wang, Z., Li, J., Li, J., Dai, Y., Wen, K., et al. (2025) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/3706628.3708864 · Cited by 18
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
Wang, C., Guo, L., Wang, Y., Cheng, H., Yu, Y., & Wen, B. (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/cvpr52733.2024.02374 · Cited by 18
Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis
Cocchi, F., Baraldi, L., Poppi, S., Cornia, M., Baraldi, L., & Cucchiara, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43153-1_29 · Cited by 18
Tensor-decomposition-based A Priori Surrogate (TAPS) modeling for ultra large-scale simulations
Guo, J., Domel, G., Park, C., Zhang, H., Gümüş, Ö. C., Lu, Y., Wagner, G. J., Qian, D., Cao, J., Hughes, T. J. R., et al. (2025) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2025.118101 · Cited by 18
GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
Mu, Y., Zuo, X., Guo, C., Wang, Y., Lu, J., Wu, X., Xu, S., Dai, P., Yan, Y., & Cheng, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72986-7_4 · Cited by 18
Generative AI-Enabled Semantic Communication: State-of-the-Art, Applications, and the Way Ahead
Liang, C., & Li, D. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3649707 · Cited by 18
Sketch-guided scene image generation with diffusion model
Zhang, T., Xie, X., Du, X., & Xie, H. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104226 · Cited by 19
ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model
Heydari, M., Souden, M., Conejo, B., & Atkins, J. D. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889311 · Cited by 18
Customizing Text-to-Image Diffusion with Object Viewpoint Control
Kumari, N., Su, G., Zhang, R., Park, T., Shechtman, E., & Zhu, J.-Y. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687564 · Cited by 18
LLMGA: Multimodal Large Language Model Based Generation Assistant
Xia, B., Wang, S., Tao, Y., Wang, Y., & Jia, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72920-1_22 · Cited by 18
Algebraic language models for inverse design of metamaterials via diffusion transformers
Zheng, L., Kumar, S., & Kochmann, D. M. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01218-8 · Cited by 18
AIM 2025 Low-Light RAW Video Denoising Challenge: Dataset, Methods and Results
Yakovenko, A., Chakvetadze, G., Khrapov, I., Zhelezov, M. S., Vatolin, D., Timofte, R., Oh, Y., Kwon, J.-H., Park, J., Cho, N. I., et al. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00596 · Cited by 18
CCDM: Continuous Conditional Diffusion Models for Image Generation
Ding, X., Wang, Y., Zhang, K., & Wang, Z. J. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3660128 · Cited by 18
CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control
Popov, S., Raj, A., Krainin, M., Li, Y., Freeman, W. T., & Rubinstein, M. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00065 · Cited by 18
Liang, C., Bai, S., Chai, W., Xie, W., Zhao, H., Vinci, L., Lin, J., & Chang, B. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00646 · Cited by 18
Pathwise Test-Time Correction for Autoregressive Long Video Generation
Xiang, X., Duan, Z., Zhang, G., Zhang, H., Gao, Z., Wu, J., Zhang, S., Wang, T., Fan, Q., & Guo, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_5 · Cited by 18
Representation Alignment for Just Image Transformers is not Easier Than You Think
Shin, J., Kim, J., & Shim, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_33 · Cited by 18
Replication in Visual Diffusion Models: A Survey and Outlook
Wang, W., Sun, Y., Yang, Z., Hu, Z., Tan, Z., & Yang, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3713990 · Cited by 18
4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion
Wang, C., Zhuang, P., Ngo, T. D., Menapace, W., Siarohin, A., Vasilkovsky, M., Skorokhodov, I., Tulyakov, S., Wonka, P., & Lee, H.-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/cvpr52734.2025.01651 · Cited by 18
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
Liang, Y., Sha, Z., Shi, Z., Song, Z., Wan, M., & Zhou, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01064 · Cited by 18
Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion ModelsPreprint
Mishra, U. A., Xue, S., Chen, Y., & Xu, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.03360 · Cited by 18
DiffsFormer: A Diffusion Transformer on Stock Factor AugmentationPreprint
Gao, Y., Chen, H., Wang, X., Wang, Z., Wang, X., Gao, J., & Ding, B. (2024) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2402.06656 · Cited by 18
Real-Time Robot Execution with Masked Action ChunkingPreprint
Wang, H., Zhang, G., Yan, Y., Shang, Y., Kompella, R. R., & Liu, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.20130 · Cited by 18
Chen, S., Xing, Z., Tian, Y., Geng, X., Lin, Y., Lai, J., He, X., Zhai, F., Gao, J., & Zhu, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.21605 · Cited by 18
WorldScore: A Unified Evaluation Benchmark for World Generation
Duan, H., Yu, H., Chen, S., Fei–Fei, L., & Wu, J. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02573 · Cited by 17
HGDRec:Next POI Recommendation Based on Hypergraph Neural Network and Diffusion Model
Pan, Y., Zeng, J., Wang, Z., Tang, H., Wen, J., & Gao, M. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3562352 · Cited by 17
Latent-based Diffusion Model for Long-tailed Recognition
Han, P.-F., Ye, C., Zhou, J., Zhang, J., Hong, J., & Li, X. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00270 · Cited by 18
UTDM: a universal transformer-based diffusion model for multi-weather-degraded images restoration
Yu, Y., Li, W., Bai, L., Duan, J., & Zhang, X. (2024) · The Visual Computer · doi:10.1007/s00371-024-03659-x · Cited by 17
Shen, Y., Dreizin, D., Íñigo, B., & Unberath, M. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102501 · Cited by 17
Current-diffusion model for metasurface structure discoveries with spatial-frequency dynamics
Li, E., Wang, Y., Jin, L., Zong, Z., Zhu, E., Wang, B., Wang, Q., Yang, Z., Yin, W.-Y., & Wei, Z. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01162-z · Cited by 17
Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph
Di, D., Yang, J., Luo, C., Xue, Z., Chen, W. R., Yang, X., & Gao, Y. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02298-y · Cited by 17
Few-Shot Defect Image Generation Based on Consistency Modeling
Shi, Q., Wei, J., Shen, F., & Zhang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73116-7_21 · Cited by 17
InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment
Guo, Z., Zhao, K., & Zhang, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462690 · Cited by 17
Han, P., Pan, Y., Pan, E., Jin, Q., Jiang, J., Zhang, Z., Liu, Z., Kang, J., & Gong, L. (2026) · npj Heritage Science · doi:10.1038/s40494-025-02274-w · Cited by 17
The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
Wang, R., Huang, H., Zhu, Y., Russakovsky, O., & Wu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01637 · Cited by 17
HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts
Liu, X., He, Y., Guo, L., Li, X., Jin, B., Li, Y., Chan, C.-M., Xue, W., Luo, W., Liu, Q., et al. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02736-z · Cited by 17
A Survey on Multimodal Wearable Sensor-based Human Action Recognition
Ni, J., Guo, B., Haque, S. T., Ngu, A. H. H., & Ding, C. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3716688 · Cited by 17
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Mao, X., Rui, S., Ying, K., Zheng, B., Li, C., Chi, M., & Zhang, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_31 · Cited by 17
Videoauteur: Towards Long Narrative Video Generation
Xiao, J., Cheng, F., Qi, L., Gui, L., Zhao, Y., Lin, S., Cen, J., Ma, Z., Yuille, A., & Jiang, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01781 · Cited by 17
Generating Multi-Image Synthetic Data for Text-to-Image Customization
Kumari, N., Yin, X., Zhu, J.-Y., Misra, I., & Azadi, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01534 · Cited by 17
GAS: Generative Avatar Synthesis from a Single Image
Lu, Y., Dong, J., Kwon, Y., Zhao, Q., Dai, B., & la Torre, F. D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01197 · Cited by 17
A Comprehensive Survey on Generative AI for Video-to-Music Generation
Ji, S., Wu, S., Wang, Z., Li, S., & Zhang, K. (2026) · ACM Computing Surveys · doi:10.1145/3816020 · Cited by 17
LoCo: Training-Free Layout-to-Image Synthesis with Localized Constraints
Zhao, P., Li, H., Jin, R., & Zhou, S. K. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754905 · Cited by 17
One-Step Diffusion Distillation via Deep Equilibrium Models
Geng, Z., Pokle, A., & Kolter, J. Z. (2023) · neural information processing systems · doi:10.52202/075280-1816 · Cited by 17
Xu, Y., Tang, F., Cao, J., Kong, X., Zhang, Y., Li, J., Deußen, O., & Lee, T. (2026) · ACM Transactions on Graphics · doi:10.1145/3797956 · Cited by 17
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of RandomnessPreprint
Zhang, B., Luo, W., & Zhang, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.18762 · Cited by 17
White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?Preprint
Yu, Y., Buchanan, S., Pai, D., Chu, T., Wu, Z., Tong, S., Bai, H., Zhai, Y., Haeffele, B. D., & Ma, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.13110 · Cited by 17
Text2PDE: Latent Diffusion Models for Accessible Physics SimulationPreprint
Zhou, A., Li, Z., Schneier, M., Buchanan, J. R., & Farimani, A. B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.01153 · Cited by 20
AniSora: Exploring the Frontiers of Animation Video Generation in the Sora EraPreprint
Jiang, Y., Xu, B., Yang, S., Yin, M., & Liu, J. (2025) · Qeios · doi:10.32388/hifc4x · Cited by 17
SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing modelPreprint
Chen, G., Lin, D., Yang, J., Zhang, Y., Fei, Z., Li, D., Chen, S., Ao, C., Pang, N., Wang, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.21818 · Cited by 17
MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., & Xu, Q. (2024) · arXiv · doi:10.48550/arxiv.2411.13807 · Cited by 16
KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding
Xiao, L., Zhuang, L., Li, A., Wei, J., Li, H., & Wang, S. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i8.28732 · Cited by 17
LaDiffGAN: Training GANs with Diffusion Supervision in Latent Spaces
Liu, X., Zeng, B., Gao, S., Li, S., Feng, Y., Li, H., Liu, B., Liu, J., & Zhang, B. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00118 · Cited by 17
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
Wu, L., Lin, L., Zhang, J., Ma, Y., & Liu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73347-5_7 · Cited by 16
Latent diffusion transformer for point cloud generation
Ji, J., Zhao, R., & Lei, M. (2024) · The Visual Computer · doi:10.1007/s00371-024-03396-1 · Cited by 16
Toward deep learning sequence–structure co-generation for protein design
Wang, C., Alamdari, S., Domingo-Enrich, C., Amini, A. P., & Yang, K. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103018 · Cited by 18
SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer
Wang, H., Hai, J., Lu, Y.-J., Thakkar, K., Elhilali, M., & Dehak, N. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890066 · Cited by 16
Representation learning with unconditional denoising diffusion models for dynamical systems
Finn, T. S., Disson, L., Farchi, A., Bocquet, M., & Durand, C. (2024) · Nonlinear processes in geophysics · doi:10.5194/npg-31-409-2024 · Cited by 16
Turbo3D: Ultra-fast Text-to-3D Generation
Hu, H., Yin, T., Luan, F., Hu, Y., Tan, H., Xu, Z., Bi, S., Tulsiani, S., & Zhang, K. (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/cvpr52734.2025.02204 · Cited by 16
SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation
Bokhovkin, A., Meng, Q., Tulsiani, S., & Dai, A. (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/cvpr52734.2025.00067 · Cited by 16
ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations
Patel, M., Kim, C., Sheng, C., Baral, C. R., & Yang, Y. (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/cvpr52733.2024.00866 · Cited by 17
Zhai, S., Ye, Z., Liu, J., Xie, W., Hu, J. S., Peng, Z., Xue, H., Chen, D., Wang, X., Yang, L., 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/cvpr52734.2025.02498 · Cited by 16
Object-Centric Diffusion for Efficient Video Editing
Kahatapitiya, K., Karjauv, A., Abati, D., Porikli, F., Asano, Y. M., & Habibian, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_6 · Cited by 16
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
