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 701–800 of 3,684
Yu, H. L., Liang, W., Fan, L., Wang, Y., & Wang, F. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3384835 · Cited by 13
RetractedDiffusion-Based Pose Refinement and Multi-Hypothesis Generation for 3D Human Pose Estimation
Kang, H., Wang, Y., Liu, M., Wu, D., Liu, P., Yuan, X., & Yang, W. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10445850 · Cited by 14
Diffusion Model for Image Generation - A Survey
Hu, X., Jin, Y., Liang, J., Liu, J., Luo, R., Li, M., & Peng, T. (2023) · International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR) · doi:10.1109/aihcir61661.2023.00073 · Cited by 15
Zhong, H. X., Lu, N., Chen, Y., Chui, E. C., Liu, Z., Qin, X., Li, J., Wang, S., Yang, J., Wang, Z., et al. (2024) · EClinicalMedicine · doi:10.1016/j.eclinm.2024.102779 · Cited by 13
DiffMesh: A Motion-Aware Diffusion Framework for Human Mesh Recovery from Videos
Zheng, C., Liu, X., Peng, Q., Wu, T., Wang, P., & Chen, C. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00479 · Cited by 13
Diffusion Models and Generative Artificial Intelligence: Frameworks, Applications and Challenges
Kumar, P. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10266-z · Cited by 14
Retracted: T2VBench: Benchmarking Temporal Dynamics for Text-to-Video Generation
Ji, P., Xiao, C., Tai, H., & Huo, M. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00541 · Cited by 14
RetractedBridging Different Language Models and Generative Vision Models for Text-to-Image Generation
Zhao, S., Hao, S., Zi, B., Xu, H., & Wong, K. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73004-7_5 · Cited by 13
PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-View Self-guidance
Liu, A., Li, Z., Chen, Z., Li, N., Xu, Y., & Plummer, B. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73383-3_9 · Cited by 13
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
Ciranni, R., Mariani, G., Mancusi, M., Postolache, E., Fabbro, G., Rodolà, E., & Cosmo, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888146 · Cited by 14
Self-Guided Generation of Minority Samples Using Diffusion Models
Um, S., & Ye, J. C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_24 · Cited by 13
EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation
Zhang, Z., Chen, H., Zhao, H., Lu, G., Fu, Y., Xu, S., & Wu, Z. (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/cvpr52734.2025.00202 · Cited by 13
CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control and Altering of T2I Models
Stracke, N., Baumann, S. A., Susskind, J. M., Bautista, M. Á., & Ommer, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73223-2_6 · Cited by 13
TVG: A Training-Free Transition Video Generation Method With Diffusion Models
Zhang, R., Chen, Y., Liu, Y., Wang, W., Wen, X., & Wang, H. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3547337 · Cited by 14
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
Li, Y., Zhang, Y., Liu, S., & Lin, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888554 · Cited by 13
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Kansy, M., Naruniec, J., Schroers, C., Groß, M. H., & Weber, R. M. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730668 · Cited by 13
Efficient Diffusion Transformer with Step-Wise Dynamic Attention Mediators
Pu, Y., Xia, Z., Guo, J., Han, D., Li, Q., Li, D., Yuan, Y., Li, J., Han, Y., Song, S., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72633-0_24 · Cited by 13
Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Yang, Z., Jiang, H., Hong, W., Teng, J., Zheng, W., Dong, Y., Ding, M., & Tang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73010-8_9 · Cited by 13
Financial Fine-Tuning a Large Time Series Model
Fu, X., Hirano, M., & Imajo, K. (2025) · IEEE Conference on Computational Intelligence for Financial Engineering & Economics · doi:10.1109/cifer64978.2025.10975735 · Cited by 13
Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
Liu, Z., Xie, C.-W., Li, P., Zhao, L., Tang, L., Zheng, Y. P., Liu, C., & Xie, H. (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/cvpr52734.2025.00801 · Cited by 13
Feng, Y., Yang, M., Yang, S., Zhang, S., Yu, J., Zhao, Z., Liu, Y., Jiang, J., & Guo, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01598 · Cited by 13
Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models
Kushwaha, S. S., Ma, J., Thomas, M. R. P., Tian, Y., & Bruni, A. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888882 · Cited by 13
Alfie: Democratising RGBA Image Generation with No $$$
Quattrini, F., Pippi, V., Cascianelli, S., & Cucchiara, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92808-6_3 · Cited by 13
AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
Yu, Z., Zou, Z., Shao, G., Zhang, C., Xu, S., Huang, J., Zhao, F., Cun, X., & Zhang, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755650 · Cited by 13
CoSwinNet: A conditional Swin Transformer multimodal surrogate model for subsurface multiphase flow
Feng, Z., Tariq, Z., Zhang, Z., Zhao, P., Zhao, R., Wang, W., Huang, X., Yan, B., Shen, X., & Zhang, F. (2025) · Fuel · doi:10.1016/j.fuel.2025.138067 · Cited by 13
Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis
Seo, J., Choi, H., Kwon, M., Choi, J., Jin, S., Lee, G., Kim, J., Lee, J., Gu, G., Han, D., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37314-4_31 · Cited by 13
DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses
Pang, Y., Zhu, B. B., Bin, B., Zheng, M., Tay, F. E. H., Lim, S.-N., Yang, H., & Li, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01303 · Cited by 13
PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive transformer
Ye, J.-T., He, Y., Zhou, Y., Zhu, Y., Xiao, K., Liu, Y., Yang, W., & Han, X. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730732 · Cited by 13
Tu, R.-C., Ma, Z.-A., Lan, T., Zhao, Y., Huang, H., & Mao, X.-L. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.1088 · Cited by 14
Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
Chao, C.-H., Sun, W.-F., Liang, H., Lee, C., & Krishnan, R. G. (2025) · neural information processing systems · doi:10.52202/085713-3258 · Cited by 13
GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
Ma, S., Ge, Y., Wang, T., Guo, Y., Ge, Y., & Shan, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02262 · Cited by 13
Wei, T., Zhou, Y., Chen, D., & Pan, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01555 · Cited by 13
Reangle-A-Video: 4D Video Generation as Video-to-Video Translation
Jeong, H., Lee, S., & Ye, J. C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01039 · Cited by 13
Ji, K., Ye, S., Jin, Z., Chen, K., Xu, L., Ma, Y., Jingyi Yu, A., & Wang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00948 · Cited by 14
ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting
Zhang, Y., Guo, W., Pan, C., Zhu, Z., Jin, T., & Zhao, Z. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755014 · Cited by 13
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
Pu, Y., Zhuo, L., Zhu, K., Xie, L., Zhang, W., Chen, X., Gao, P., Qiao, Y., Dong, C., & Liu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_22 · Cited by 13
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
Prabhudesai, M., Ke, T.-W., Li, A., Pathak, D., & Fragkiadaki, K. (2023) · neural information processing systems · doi:10.52202/075280-0770 · Cited by 13
“Principal Components” Enable a New Language of Images
Wen, X., Zhao, B., Elezi, I., Deng, J., & Qi, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01545 · Cited by 13
Elucidating The Design Space of Classifier-Guided Diffusion GenerationPreprint
Ma, J., Hu, T., Wang, W., & Sun, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.11311 · Cited by 13
You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANsPreprint
Luo, Y., Chen, X., Qu, X., Hu, T., & Tang, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.12931 · Cited by 13
Accelerating Vision Transformers with Adaptive Patch SizesPreprint
Choudhury, R., Kim, J., Park, J., Yang, E., Jeni, L. A., & Kitani, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.18091 · Cited by 13
ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance GenerationPreprint
Xu, R., Zhou, D., Ma, F., & Yang, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.11000 · Cited by 13
Web World ModelsPreprint
Feng, J., Zhang, Y., Zhang, C., Lu, Y., Liu, S., & Wang, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.23676 · Cited by 13
ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action ModelsPreprint
Sun, G., Du, T., Feng, K., Luo, C., Ding, X., Shen, Z., Wang, Z., He, Y., & Li, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.17951 · Cited by 13
SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot PolicyPreprint
Li, P., Chen, Y., Xu, Y., Yang, J., Wu, X., Guo, J., Sun, N., Qian, L., Li, X., Xiao, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.03181 · Cited by 13
Revisiting Embodied Chain-of-Thought for Generalizable Robot ManipulationPreprint
Sun, N., Zhang, Y., Yang, Y., Zhao, W., Li, P., (85069), J. G., Song, W., Ding, P., Suo, R., Su, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.03784 · Cited by 13
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data AlonePreprint
Simple, A. I., :, Wei, Y., Ma, J., Wang, J., Zhou, W., Zuo, Y., Rui, K., Li, M., Zhang, J., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.25895 · Cited by 13
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Agarwal, N., Ali, A., Bala, M., Balaji, Y., Barker, E., Cai, T., Chattopadhyay, P., Chen, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.03575 · Cited by 13
RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
Liu, I., Xu, Z., Yifan, W., Tan, H., Xu, Z., Wang, X., Su, H., & Shi, Z. (2025) · ACM Transactions on Graphics · doi:10.1145/3731149 · Cited by 12
“The denoising MLP is conditioned on the transformer-outputted joint tokens, where these tokens are incorporated into the noise scheduler’s time embedding through AdaLN [Peebles and Xie 2023] within the Layer Normalization layers.”
CartoonDiff: Training-free Cartoon Image Generation with Diffusion Transformer Models
He, F., Li, G., Si, L., Yan, L., Hou, S., Dong, H., & Li, F. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447821 · Cited by 12
Progressive Semantic-Visual Alignment and Refinement for Vision-Language Tracking
Liang, Y., Wu, Q., Cheng, L., Xia, C., & Li, J. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3520354 · Cited by 12
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Bian, Y., Zhang, Z., Ju, X., Cao, M., Xie, L., Shan, Y., & Xu, Q. (2025) · Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers · doi:10.1145/3721238.3730673 · Cited by 12
Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal
Jin, Y., Li, X., Wang, J., Zhang, Y., & Zhang, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72658-3_1 · Cited by 12
Fu, Q., Xia, S., Kang, Y., Sun, M., & Tan, K. (2024) · Remote Sensing · doi:10.3390/rs16193644 · Cited by 12
Generation of Fundus Fluorescein Angiography Videos for Health Care Data Sharing
Wu, X., Wang, L., Chen, R., Liu, B., Zhang, W., Yang, X., Feng, Y., He, M., & Shi, D. (2025) · JAMA Ophthalmology · doi:10.1001/jamaophthalmol.2025.1419 · Cited by 12
Industrial Anomaly Detection Based on Improved Diffusion Model: A Review
Wang, J., Wang, Z., Wen, C., Liu, W., Liu, X., & Wang, D. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10517-y · Cited by 12
MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection
Beizaee, F., Lodygensky, G. A., Desrosiers, C., & Dolz, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96625-5_10 · Cited by 12
Frontiers of Generative AI for Network Optimization: Theories, Limits, and Visions
Yang, B. X., Liang, R., Li, W., Wang, H., Cao, X., Yu, Z., Lasaulce, S., Debbah, M. A., Alouini, M., Poor, H. V., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3656241 · Cited by 12
Cali, Ü., Halden, U., Andoni, M., Çatak, F. Ö., Chen, S., Couraud, B., Kantar, E., Knapper, S., Küçükdemiral, İ. B., Kusetoğulları, H., et al. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11545-2 · Cited by 12
4DIFF: 3D-Aware Diffusion Model for Third-to-First Viewpoint Translation
Cheng, F., Luo, M., Wang, H., Dimakis, A. G., Torresani, L., Bertasius, G., & Grauman, K. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72691-0_23 · Cited by 12
MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation
Mao, X., Jiang, Z., Wang, Q., Fu, C., Zhang, J., Wu, J., Wang, Y., Wang, C., Li, W., & Chi, M. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680684 · Cited by 12
ObjectMover: Generative Object Movement with Video Prior
Yu, X., Wang, T., Kim, S. Y., Guerrero, P., Chen, X., Liu, Q., Lin, Z., & Qi, 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/cvpr52734.2025.01647 · Cited by 12
MixDiT: Accelerating Image Diffusion Transformer Inference With Mixed-Precision MX Quantization
Kim, D., Hwang, J., Oh, C., & Park, J. (2025) · IEEE Computer Architecture Letters · doi:10.1109/lca.2025.3560786 · Cited by 12
Fime, A. A., Mahmud, S., Das, A., Islam, M. K., & Kim, J.-H. (2025) · IEEE Access · doi:10.1109/access.2025.3574298 · Cited by 12
A Comprehensive Survey on Text-to-Video Generation
Xie, F., Zeng, D., Shen, Q., & Tang, B. (2025) · Chinese Journal of Electronics · doi:10.23919/cje.2024.00.151 · Cited by 12
A Learning Framework for Atomic-Level Polymer Structure Generation
Jain, A., Srivastava, A., & Ramprasad, R. (2025) · Chemistry of Materials · doi:10.1021/acs.chemmater.5c01644 · Cited by 12
Lazy Diffusion Transformer for Interactive Image Editing
Nitzan, Y., Wu, Z., Zhang, R., Shechtman, E., Cohen‐Or, D., Park, T., & Gharbi, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72691-0_4 · Cited by 12
ProcessPainter: Learning to draw from sequence data
Song, Y., Huang, S., Yao, C., Ci, H., Ye, X., Liu, J., Zhang, Y., & Shou, M. Z. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687596 · Cited by 12
Shi, S., Gong, B., Chen, X., Zheng, D., Tan, S., Yang, Z., Li, Y., He, J., Zheng, K., Chen, 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/cvpr52734.2025.02129 · Cited by 12
From One to More: Contextual Part Latents for 3D Generation
Dong, S., Ding, L., Chen, X., Li, Y., Wang, Y., Wang, Y., Wang, Q., Kim, J., Gao, C., Huang, Z., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00771 · Cited by 12
Zheng, Z., Wang, X., Zou, C., Wang, S., & Zhang, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755479 · Cited by 12
Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning
Zhu, Q., Lu, K., Huo, M., & Li, Y. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085477 · Cited by 12
Smooth Cache: A Universal Inference Acceleration Technique for Diffusion Transformers
Liu, J., Geddes, J., Guo, Z., Jiang, H., & Nandwana, M. K. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00305 · Cited by 12
$I^{\mathbf{2}}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
Liao, Z., Wei, P., Zhang, R., Chen, S., Wang, H., & Ren, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02394 · Cited by 12
Differentially Private Fine-Tuning of Diffusion Models
Tsai, Y., Li, Y., Yu, C.-M., Ren, X., Chen, P.-Y., Chen, Z., & Buet-Golfouse, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00434 · Cited by 12
Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation
Liu, S., Cheng, Y., Chen, Z., Ren, X., Zhu, W., Li, L., Bi, M., Yang, X., & Yan, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01639 · Cited by 12
TokBench: Evaluating Your Visual Tokenizer before Visual Generation
Wu, J., Luo, D., Zhao, W., Xie, Z., Wang, Y., Li, J., Xie, X., Liu, Y., & Bai, X. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3838671 · Cited by 12
DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
Wang, W., Huang, M., Tu, Y., & Mao, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01538 · Cited by 12
Synthetic Video Enhances Physical Fidelity in Video Synthesis
Zhao, Q., Ni, X., Wang, Z., Cheng, F., Yang, Z., Lu, J., & Wang, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01128 · Cited by 12
Decoupled Diffusion Sparks Adaptive Scene Generation
Zhou, Y., Ye, N., Ljungbergh, W., Li, T., Yang, J.-Z., Yang, Z., Zhu, H., Petersson, C., & Li, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02577 · Cited by 12
Multi-Identity Human Image Animation with Structural Video Diffusion
Wang, Z., Li, Y., Zeng, Y., Guo, Y., Lin, D., Xue, T., & Dai, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01110 · Cited by 12
Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
Guan, K., Wang, X., Lai, Z., Cheng, X. H., Zhang, P., Liu, K., Song, R., & Cao, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_8 · Cited by 12
SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets
Yang, Y., Liu, F., Lu, Y., Zhao, Q., Wu, P., Zhai, W., Yi, R., Cao, Y., Ma, L., Zha, Z.-J., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00487 · Cited by 12
DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer
Jiang, J., Hong, G., Zhang, M., Hu, H., Zhan, K., Shao, R., & Nie, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3712641 · Cited by 12
Ambient Diffusion Omni: Training Good Models with Bad Data
Daras, G., Rodríguez-Muñoz, A., Klivans, A. R., Torralba, A. B., & Daskalakis, C. (2025) · neural information processing systems · doi:10.52202/085713-1274 · Cited by 12
SpectralAR: Spectral Autoregressive Visual Generation
Huang, Y., Chen, W., Zheng, W., Duan, Y., Zhou, J., & Lu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01470 · Cited by 12
Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
Chen, Y., Tan, W., (16642), L. Z., Li, F., Yang, G., & Zhu, L. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836459 · Cited by 12
ELT: Elastic Looped Transformers for Visual Generation
Goyal, S., Agrawal, S., Anil, G. G., Jain, P., Paul, S., & Kusupati, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_17 · Cited by 12
Deeply Supervised Flow-Based Generative Models
Shin, I., Yang, C., & Chen, L.-C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01535 · Cited by 12
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
Liu, Y., Lin, X., Li, X., Baihan, Y., Wang, C., Sunkavalli, K., Hold-Geoffroy, Y., Tan, H., Zhang, K., Xie, X. S., et al. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811180 · Cited by 12
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts
Han, Y., Wang, R., Zhang, C., Hu, J., Chen, P., Fu, B., & Zhang, H. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228924 · Cited by 12
Complexity Matters: Rethinking the Latent Space for Generative Modeling
Hu, T., Chen, F., Wang, H., Li, 李. J., Wang, W., Sun, J., & Li, Z. (2023) · neural information processing systems · doi:10.52202/075280-1285 · Cited by 12
Exploring Vision Transformers as Diffusion LearnersPreprint
Cao, H., Wang, J., Ren, T., Qi, X., Chen, Y., Yao, Y., & Zhang, L. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.13771 · Cited by 12
Memory Encoding ModelPreprint
Yang, H., Gee, J. C., & Shi, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.01175 · Cited by 12
Shang, F., Fu, J., Yang, Y., Huang, H., Liu, J., & Ma, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.00377 · Cited by 12
The Surprising Effectiveness of Skip-Tuning in Diffusion SamplingPreprint
Ma, J., Xue, S., Hu, T., Wang, W., Liu, Z., Li, Z., Ma, Z.-M., & Kawaguchi, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.15170 · Cited by 12
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion ModelsPreprint
Moon, T., Choi, M., Yun, E., Yoon, J., Lee, G., Cho, J., & Lee, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.05927 · Cited by 12
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion ModelsPreprint
Sadat, S., Hilliges, O., & Weber, R. M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.02416 · Cited by 12
Han, Y., Chen, H., Han, A., Wang, Z., Liu, X., Zhang, Y., Zhang, S., & Zou, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.16663 · Cited by 12
PDE-Transformer: Efficient and Versatile Transformers for Physics SimulationsPreprint
Holzschuh, B., Liu, Q., Kohl, G., & Thuerey, N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.24717 · Cited by 12
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
