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 601–700 of 3,684
MinD-3D: Reconstruct High-Quality 3D Objects in Human Brain
Gao, J., Fu, Y., Wang, Y., Qian, X., Feng, J., & Fu, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72970-6_18 · Cited by 16
BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
Zhang, H., Gao, T., Shao, J., & 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/cvpr52734.2025.01203 · Cited by 16
Yang, C., Dong, X., Zhu, X., Su, W., Wang, J., Tian, H., Chen, Z., Wang, W., Lu, L., & Dai, J. (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/cvpr52734.2025.02322 · Cited by 16
DiffuMatting: Synthesizing Arbitrary Objects with Matting-Level Annotation
Hu, X., Xu, P., Luo, D., Ji, X., Peng, J., Jiang, Z., Zhang, J., Jin, T., Wang, C., & Ji, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_23 · Cited by 16
DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model
Huang, J., Yan, P., Cai, J., Liu, J., Wang, Z., Wang, Y., Wu, X., & Li, G. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00321 · Cited by 16
LoVA: Long-form Video-to-Audio Generation
Cheng, X., Wang, X., Wu, Y., Wang, Y., & Song, R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888085 · Cited by 16
Revelio: Interpreting and Leveraging Semantic Information in Diffusion Models
Kim, D., Thomas, X., & Ghadiyaram, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00443 · Cited by 16
Zhao, Q., Li, Y., Sun, Q., & Yan, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_17 · Cited by 16
CoCoGesture: Towards coherent co-speech 3D gesture generation in the wild
Qi, X., Zhang, H., Wang, Y., Pan, J., Liu, C., Sun, M., Xue, W., Zhang, S., Han, S., Liu, Q., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103613 · Cited by 17
Gaussian Variation Field Diffusion for High-Fidelity Video-to-4D Synthesis
Zhang, B., Xu, S., Wang, C., Yang, J., Zhao, F., Chen, D., & Guo, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01162 · Cited by 16
ReRoPE: Repurposing RoPE for Relative Camera Control
Li, C. B., Yang, Y., Shao, J., Zhou, H., Schwarz, K., & Liao, Y. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811226 · Cited by 16
MDGR: Masked Diffusion Generative Recommendation
Mu, L., Deng, H., Xing, H., Hu, J., Zhang, Y., Zeng, X., & Zhang, J. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831862 · Cited by 16
Yahia, H. B., Korzhenkov, D., Lelekas, I., Ghodrati, A., & Habibian, A. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01808 · Cited by 16
AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation
Haji-Ali, M., Menapace, W., Siarohin, A., Skorokhodov, I., Canberk, A., Lee, K. S., Ordóñez, V., & Tulyakov, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01801 · Cited by 18
AV-Flow: Transforming Text to Audio-Visual Human-Like Interactions
Chatziagapi, A., Morency, L., Gong, H., Zollhöfer, M., Samaras, D., & Richard, A. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01324 · Cited by 16
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
Liu, X., Li, Z., Xiao, J. N., Chen, M., Li, J., & Gu, Q. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3699096 · Cited by 16
Denoising Task Routing for Diffusion ModelsPreprint
Park, B., Woo, S., Go, H., Kim, J., & Kim, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.07138 · Cited by 16
A Survey on Future Frame Synthesis: Bridging Deterministic and Generative ApproachesPreprint
Ming, R., Huang, Z., Wu, J., Ju, Z., Jiang, D., Hu, J., Peng, L., & Zhou, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.14718 · Cited by 16
LM4LV: A Frozen Large Language Model for Low-level Vision TasksPreprint
Zheng, B., Gu, J., Li, S., & Dong, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.15734 · Cited by 16
Simple Policy Gradients for Reasoning with Diffusion Language ModelsPreprint
Zhan, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.04019 · Cited by 16
There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingPreprint
Lei, J., Liu, K., Berner, J., Yu, H., Zheng, H., Wu, J., & Chu, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.12586 · Cited by 16
Enhancing Physical Plausibility in Video Generation by Reasoning the ImplausibilityPreprint
Hao, Y., Chen, C., Mian, A. S., Xu, C., & Liu, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24702 · Cited by 16
DyPE: Dynamic Position Extrapolation for Ultra High Resolution DiffusionPreprint
Issachar, N., Yariv, G., Benaim, S., Adi, Y., Lischinski, D., & Fattal, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.20766 · Cited by 16
Sui, J., Ma, X., Zhang, X., Pun, M.-O., & Wu, H. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3504569 · Cited by 16
A Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction
Shi, S., Kang, R., & Liatsis, P. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3550245 · Cited by 16
Sequential SAR-to-Optical Image Translation
Wei, J., Zhou, H., Ke, P., Ma, Y., & Tang, R. (2025) · Remote Sensing · doi:10.3390/rs17132287 · Cited by 15
AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
Sun, M., Wang, W. H., Li, G., Liu, J., Sun, J., Feng, W., Lao, S., Zhou, S., Qian, H., & Liu, J. (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/cvpr52734.2025.00690 · Cited by 15
Versatile cardiovascular signal generation with a unified diffusion transformer
Chen, Z., Miao, Y., Wang, L., Fan, L., Mandic, D. P., & Zhu, J. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01147-y · Cited by 15
MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask
Zhou, Y., Zhou, D., Wang, Y., Feng, J., & Hou, Q. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02294-2 · Cited by 17
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
Luo, W., Qin, H., Chen, Z., Wang, L., Zheng, D., Li, Y., Liu, Y., Li, B., & Hu, W. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01191 · Cited by 15
Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models
Romanelis, I., Fotis, V., Kalogeras, A. P., Alexakos, C., Munteanu, A., & Μουστάκας, Κ. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3636409 · Cited by 15
GameFactorly: Creating New Games with Generative Interactive Videos
Yu, J., Qin, Y., Wang, X., Wan, P., Zhang, D., & Liu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01078 · Cited by 15
Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
Ku, P.-J., Liu, A. H., Korostik, R., Huang, S.-F., Fu, S., & Jukić, A. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888830 · Cited by 15
IntrinsicEdit: Precise generative image manipulation in intrinsic space
Lyu, L., Deschaintre, V., Hold-Geoffroy, Y., Hašan, M., Yoon, J. S., Leimkühler, T., Theobalt, C., & Georgiev, I. (2025) · ACM Transactions on Graphics · doi:10.1145/3731173 · Cited by 15
Importance-Based Token Merging for Efficient Image and Video Generation
Wu, H., Xu, J., Le, H., & Samaras, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00474 · Cited by 15
Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
Jang, S., Choi, J. S., Jo, J., Lee, K., & Hwang, S. J. (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/cvpr52734.2025.00768 · Cited by 15
AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction
Zhang, X., Zhou, Y., Wang, K., Wang, Y., Li, Z., Jiao, S., Zhou, D., Hou, Q., & Cheng, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02438 · Cited by 15
SparseDM: Toward Sparse Efficient Diffusion Models
Wang, K., Chen, J., Li, H., Mi, Z., & Zhu, J. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209208 · Cited by 15
CAT: Content-Adaptive Image Tokenization
Shen, J.-H., Tirumala, K., Yasunaga, M., Misra, I., Zettlemoyer, L., Yu, L., & Zhou, C. (2025) · neural information processing systems · doi:10.52202/085713-0026 · Cited by 15
DyDiT++: Diffusion Transformers With Timestep and Spatial Dynamics for Efficient Visual Generation
Zhao, W., Han, Y., Tang, J., Wang, K., Luo, H., Song, Y., Huang, G. M., Wang, F., & You, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3654201 · Cited by 15
Data-Free Knowledge Distillation with Diffusion Models
Qi, X., Li, R., Peng, L., Ling, Q., Yu, J., Chen, Z., Chang, P., Han, M., & Xiao, J. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209042 · Cited by 15
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
Zeng, L., Yao, J., Liao, B., Tao, H., Liu, W., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_18 · Cited by 15
Walk Through Paintings: Egocentric World Models from Internet Priors
Bagchi, A., Bao, Z., Bharadhwaj, H., Wang, Y.-X., Tokmakov, P., & Hebert, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_26 · Cited by 15
REDUCIO! Generating 1K Video Within 16 Seconds Using Extremely Compressed Motion Latents
Tian, R., Dai, Q., Bao, J., Qiu, K., Yang, Y., Luo, C., Wu, Z., & Jiang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01788 · Cited by 15
JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
Liu, R., Hung, C.-Y., Majumder, N., Herremans, D., & Poria, S. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.48 · Cited by 16
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
Lin, H., Qin, C., Liu, Z., Pei, Q., Li, Y., Zhong, Z., Gao, X., Li, W., Zhang, W., Wang, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37258-1_2 · Cited by 15
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
Zou, K., Zheng, D., Liu, H., Hang, T., Liu, B., & Yu, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_13 · Cited by 15
Wang, R., Cai, Z., Pu, F., Xu, J., Yin, W., Wang, M., Ji, R., Gu, C., Li, B., Huang, Z., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37086-0_17 · Cited by 15
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Oshima, Y., Taniguchi, S., Suzuki, M., & Matsuo, Y. (2026) · New Generation Computing · doi:10.1007/s00354-026-00326-8 · Cited by 15
Diffusion Guided Language Modeling
Lovelace, J., Kishore, V., Chen, Y., & Weinberger, K. Q. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.887 · Cited by 15
STIV: Scalable Text and Image Conditioned Video Generation
Lin, Z., Liu, W., Chen, C., Lü, J., Hu, W., Fu, T.-J., Allardice, J., Lai, Z., Song, L., Zhang, B., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01508 · Cited by 15
Tread: Token Routing for Efficient Architecture-Agnostic Diffusion Training
Krause, F., Phan, T., Gui, M., Baumann, S. A., Hu, V. T., & Ommer, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01457 · Cited by 15
Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent
Liao, X., Zeng, X., Wang, L., Yu, G., Lin, G., & Zhang, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01052 · Cited by 15
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
Dufour, N., Picard, D., Kalogeiton, V. S., & Landrieu, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02143 · Cited by 15
ReGate: Enabling Power Gating in Neural Processing Units
Xue, Y., & Huang, J. (2025) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3725843.3756038 · Cited by 15
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Li, Y., Jiang, H., Kodaira, A., Tomizuka, M., Keutzer, K., & Xu, C. (2024) · neural information processing systems · doi:10.52202/079017-2863 · Cited by 15
Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone
Jiang, Z., Mao, C., Huang, Z., Ma, A., Lv, Y., Shen, Y., Zhao, D., & Zhou, J. (2023) · neural information processing systems · doi:10.52202/075280-1850 · Cited by 15
ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional Latent Diffusion ModelsPreprint
Chen, D.-Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.09330 · Cited by 15
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion ModelPreprint
Dong, Z., Yuan, Y., Hao, J., Ni, F., Mu, Y., Yan, Z., Hu, Y., Lv, T., Fan, C., & Hu, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.02054 · Cited by 15
Denoising Task Difficulty-based Curriculum for Training Diffusion ModelsPreprint
Kim, J. Y., Go, H., Kwon, S., & Kim, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.10348 · Cited by 15
VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion TransformersPreprint
Zheng, J., Zhao, F., Xu, Y., Dong, X., & Liang, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.18326 · Cited by 15
MEDIC: Zero-shot Music Editing with Disentangled Inversion ControlPreprint
Liu, H., Wang, J., Li, X., Wang, W., Chen, Q., Huang, R., Liu, Y., Xu, J., & Zhao, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.13220 · Cited by 15
CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion ModelsPreprint
Cheng, X., Chen, Z., & Jia, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.00433 · Cited by 16
Kaleido: Open-Sourced Multi-Subject Reference Video Generation ModelPreprint
Zhang, Z. X., Teng, J., Yang, Z., Cao, T., Wang, C., Gu, X., Tang, J., Guo, D., & Wang, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.18573 · Cited by 15
LoopNav: Benchmarking Spatial Consistency in World ModelsPreprint
Lian, K., Cai, S., Liang, Y., & Liu, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.22976 · Cited by 15
Diffusion Dynamics Models with Generative State Estimation for Cloth ManipulationPreprint
Tian, T., Li, H., Ai, B., Yuan, X., Huang, Z., & Su, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.11999 · Cited by 15
Physion-Eval: Evaluating Physical Realism in Generated Video via Human ReasoningPreprint
Zhang, Q., Jing, P., Yu, H.-X., Ding, F., Nie, F., Wang, W., Du, Y., Zou, J., Wu, J., & Shuai, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.19607 · Cited by 15
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement ModelsPreprint
Park, T., Lee, Y., Kim, D., & Bae, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.11011 · Cited by 15
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation ModelsPreprint
Yuan, Y., Huang, Y., Yao, X., Li, Y., Zhang, S., Han, L., Li, P., Sun, J., Jia, W., Zhang, Z., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.11324 · Cited by 15
Adaptive Double-Branch Fusion Conditional Diffusion Model for Underwater Image Restoration
Wang, Y., He, K., Qu, Q., Du, X., Liu, T., Lei, T., & Nandi, A. K. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3570372 · Cited by 14
Yao, J., Zhao, Z., & Zhao, J. Y. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102722 · Cited by 14
Zhao, H., Lou, H., Yao, L., & Zhang, Y. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/adb07a · Cited by 15
de Azevedo, F. P., Lourenço, N. C. C., & Martins, R. M. F. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128414 · Cited by 15
Chen, R., Gao, B., Qin, G., Chang, C., Kang, Y., Ren, H., Zou, D., Ma, Q., & Woo, W. L. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3588620 · Cited by 14
NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction
Lin, B., Jin, Y., Yan, W., Ye, W., Yuan, Y., Zhang, S., & Tan, R. T. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i4.28124 · Cited by 14
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers*
Liu, J., Teshome, W., Ghimire, S., Sznaier, M., & Camps, O. (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/cvpr52733.2024.02171 · Cited by 15
Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption
Huang, B., Li, C., Xu, C., Pan, L., Wang, Y., & Lee, G. H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00102 · Cited by 14
Med-LVDM: Medical latent variational diffusion model for medical image translation
Kui, X., Liu, B., Sun, Z., Li, Q., Zhang, M., Liang, W. P., & Zou, B. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107735 · Cited by 14
MetaIndux-TS: Frequency-Aware AIGC Foundation Model for Industrial Time Series
Wang, H., Ren, L., Li, Y., & Wang, Y. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3577203 · Cited by 14
Spatio-Temporal Probabilistic Forecasting of Wind Speed Using Transformer-Based Diffusion Models
Liu, H., Liu, J., Hu, T., & Ma, H. (2025) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2025.3591920 · Cited by 14
COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation
Liu, H., & Aliaga, D. G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72624-8_1 · Cited by 14
Diffusion-Based Surrogate Modeling and Multi-Fidelity Calibration
Shi, N., Yan, H., Guo, S., & Kontar, R. A. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3582171 · Cited by 13
Diff3DETR: Agent-Based Diffusion Model for Semi-supervised 3D Object Detection
Deng, J., Lu, J., & Zhang, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72754-2_4 · Cited by 14
ZoomLDM: Latent Diffusion Model for multi-scale image generation
Yellapragada, S., Graikos, A., Triaridis, K., Prasanna, P., Gupta, R., Saltz, J., & Samaras, D. (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/cvpr52734.2025.02184 · Cited by 14
NViST: In the Wild New View Synthesis from a Single Image with Transformers
Jang, W., & Agapito, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00970 · Cited by 14
Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images
Tang, Y., Zhang, Q., Liu, Y., & Hou, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3552408 · Cited by 14
FlowR: Flowing from Sparse to Dense 3D Reconstructions
Fischer, T., Bulò, S. R., Yang, Y.-H., Keetha, N., Porzi, L., Müller, N., Schwarz, K., Luiten, J., Pollefeys, M., & Kontschieder, P. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02572 · Cited by 14
Matrix3D: Large Photogrammetry Model All-in-One
Lu, Y., Zhang, J., Fang, T., Nahmias, J.-D., Tsin, Y., Quan, L., Cao, X., Yao, Y., & Li, S. (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/cvpr52734.2025.01051 · Cited by 14
AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images
Li, Y., Wu, S., Sun, W., Zhang, Z., Zhu, Y., Zhang, Z., Duan, H., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3639620 · Cited by 14
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
Wu, Y., Zhang, Z., Li, Y., Xu, Y., Kag, A., Sui, Y., Coskun, H., Ma, K., Lebedev, A., Ju, H., 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/cvpr52734.2025.00237 · Cited by 14
VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
Wang, H., Liu, F., Chi, J., & Duan, 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/cvpr52734.2025.01536 · Cited by 14
CharacterFactory: Sampling Consistent Characters With GANs for Diffusion Models
Wang, Q., Li, B., Li, X., Cao, B., Ma, L., Lu, H., & Jia, X. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3558668 · Cited by 14
HGPflow: extending hypergraph particle flow to collider event reconstruction
Kakati, N., Dreyer, E., Ivina, A., Bello, F. A. D., Heinrich, L., Kado, M., & Gross, E. (2025) · The European Physical Journal C · doi:10.1140/epjc/s10052-025-14443-z · Cited by 14
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Kumar, A., & Patel, V. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_14 · Cited by 14
DiTFastAttnV2: Head-Wise Attention Compression for Multi-Modality Diffusion Transformers
Zhang, H., Su, R., Yuan, Z., Chen, P., Shen, M., Fan, Y., Yan, S., Dai, G., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01522 · Cited by 14
Kim, J., Park, J., Song, Y., Kwak, N., & Rhee, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01479 · Cited by 14
Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers
Lv, Z., Pan, T., Si, C., Chen, Z., Zuo, W., Liu, Z., & Wong, K.-Y. K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00561 · Cited by 14
Rectified Point Flow: Generic Point Cloud Pose Estimation
Sun, T., Zhu, L., Huang, S., Song, S., & Armeni, I. (2025) · neural information processing systems · doi:10.52202/085713-5628 · Cited by 14
Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems
Hu, J., Song, B., Xu, X., Shen, L., & Fessler, J. A. (2024) · neural information processing systems · doi:10.52202/079017-0052 · Cited by 14
Flow Equivariant World Models: Structured Memory for Dynamic EnvironmentsPreprint
Lillemark, H. J., Huang, B., Zhan, F., Du, Y., & Keller, T. A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.01075 · Cited by 14
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
