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 301–400 of 3,684
FluxSpace: Disentangled Semantic Editing in Rectified Flow Models
Dalva, Y., Venkatesh, K., & Yanardag, P. (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/cvpr52734.2025.01221 · Cited by 37
Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation
Zhu, M., Zhu, Y., Li, J., Wen, J., Xu, Z., Liu, N., Cheng, R., Shen, C., Peng, Y., Feng, F., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128074 · Cited by 37
LATTICE: Democratize High-Fidelity 3D Generation at ScalePreprint
Lai, Z., Zhao, Y., Zhao, Z., Liu, H., Lin, Q., Huang, J., Guo, C., & Yue, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.03052 · Cited by 37
A Comprehensive Survey of Recent Transformers in Image, Video and Diffusion Models
Le, D. P. C., Wang, D., & Le, V.-T. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.050790 · Cited by 36
Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmission
Zhang, M., Wu, H., Zhu, G., Jin, R., Chen, X., & Gündüz, D. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3591456 · Cited by 36
TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
Huang, Y., Gong, R., Liu, J., Chen, T., & Liu, X. (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/cvpr52733.2024.00703 · Cited by 38
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Zi, B., Peng, W., Qi, X., Wang, J., Zhao, S., Xiao, R., & Wong, K. (2025) · neural information processing systems · doi:10.52202/085713-2536 · Cited by 36
One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
Surkov, V., Wendler, C., Mari, A., Terekhov, M. I., Deschenaux, J., West, R., Gülçehre, Ç., & Bau, D. (2025) · neural information processing systems · doi:10.52202/085713-3342 · Cited by 36
Discriminating Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Review
Li, N., Wang, Z., & Cheikh, F. A. (2024) · Sensors · doi:10.3390/s24102987 · Cited by 35
Medical image translation with deep learning: Advances, datasets and perspectives
Chen, J., Ye, Z., Zhang, R., Li, H., Fang, B., Zhang, L., & Wang, W. W. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103605 · Cited by 37
HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting
Lu, W., Xu, Y., Zhang, J., Wang, C., & Tao, D. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680693 · Cited by 35
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
Chu, X., Su, J., Zhang, B., & Shen, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72848-8_1 · Cited by 36
LaVin-DiT: Large Vision Diffusion Transformer
Wang, Z., Xia, X., Chen, R., Yu, D., Wang, C., Gong, M., & Liu, T. (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/cvpr52734.2025.01868 · Cited by 35
LT3SD: Latent Trees for 3D Scene Diffusion
Meng, Q., Li, L., Nießner, M., & Dai, A. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00069 · Cited by 35
StableIdentity: Inserting Anybody Into Anywhere at First Sight
Wang, Q., Jia, X., Li, X., Li, T., Ma, L., Zhuge, Y., & Lu, H. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613113 · Cited by 35
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
Li, T., Zheng, G., Jiang, R., Zhan, S., Wu, T., Lu, Y., Lin, Y., Deng, C., Xiong, Y., Chen, M., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02673 · Cited by 35
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution
Duan, Z.-P., Zhang, J., Jin, X., Zhang, Z., Xiong, Z., Zou, D., Ren, J. S., Guo, C., & Li, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01761 · Cited by 35
Designing DNA With Tunable Regulatory Activity Using Discrete DiffusionPreprint
Sarkar, A., Durán, A., Yu, Y., Lin, D.-W., Kang, Y., Somia, N., Mantilla, P., Zhou, J., Nagai, M., Tang, Z., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.23.595630 · Cited by 35
Improving AI models for rare thyroid cancer subtype by text guided diffusion models
Dai, F., Yao, S., Wang, M., Zhu, Y., Qiu, X., Sun, P., Qiu, C., Yin, J., Shen, G., Sun, J., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-59478-8 · Cited by 34
Li, J., Shen, Y., Zhou, W., & Hui, C. H. E. N. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103665 · Cited by 34
UniVS: Unified and Universal Video Segmentation with Prompts as Queries
Li, M., Li, S., Zhang, X., & Zhang, 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/cvpr52733.2024.00311 · Cited by 34
CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
Wang, Q., Luo, Y., Shi, X., Jia, X., Lu, H., Xue, T., Wang, X., Wan, P., Zhang, D., & Gai, K. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730755 · Cited by 34
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
Liu, H., Huang, R., Lin, X., Xu, W., Zheng, M., Chen, H., He, J., & Zhao, Z. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.990 · Cited by 35
Lightweight diffusion models: a survey
Song, W., Ma, W., Zhang, M., Zhang, Y., & Zhao, X. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10800-8 · Cited by 34
Is Diversity All You Need for Scalable Robotic Manipulation?
Shi, M., Chen, L., Chen, J., Lu, Y., Liu, C.-M., Ren, G., Luo, P., Huang, D., Yao, M., & Li, H. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3686184 · Cited by 34
FLUX that Plays MusicPreprint
Fei, Z., Fan, M., Yu, C., & Huang, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.00587 · Cited by 34
Flow Matching with General Discrete Paths: A Kinetic-Optimal PerspectivePreprint
Shaul, N., Gat, I., Havasi, M., Severo, D., Sriram, A., Holderrieth, P., Karrer, B., Lipman, Y., & Chen, R. T. Q. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.03487 · Cited by 34
AToken: A Unified Tokenizer for VisionPreprint
Lu, J., Song, L., Xu, M., Ahn, B., Wang, Y., Chen, C., Dehghan, A., & Yang, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.14476 · Cited by 34
Coupled data/physics-driven framework for accurate and efficient structural response simulation
Zhai, G., Spencer, B. F., Yan, J., Liao, W., Gu, D., Contiguglia, C. P., Demartino, C., & Xu, Y. (2025) · Engineering Structures · doi:10.1016/j.engstruct.2025.119636 · Cited by 33
Diffusion model for medical image denoising, reconstruction and translation
Wang, W., Xia, J., Luo, G., Dong, S., Li, X., Wen, J., & Li, S. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102593 · Cited by 33
OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers
Liang, H., Bao, J., Zhang, R., Ren, S., Xu, Y., Yang, S., Chen, X., Jingyi Yu, A., & Xu, 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/cvpr52733.2024.00053 · Cited by 33
M&M VTO: Multi-Garment Virtual Try-On and Editing
Zhu, L., Li, Y., Liu, N., Peng, H., Yang, D., & Kemelmacher-Shlizerman, I. (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/cvpr52733.2024.00134 · Cited by 33
Image Sculpting: Precise Object Editing with 3D Geometry Control
Yenphraphai, J., Pan, X., Liu, S., Panozzo, D., & Xie, S. (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/cvpr52733.2024.00406 · Cited by 33
Self-citationControllable Mind Visual Diffusion Model
Zeng, B., Li, S., Liu, X., Gao, S., Jiang, X., Tang, X., Hu, Y. B., Liu, J., & Zhang, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i7.28519 · Cited by 35
Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review
Fang, Y., Miao, H., Liang, Y., Deng, L., Cui, Y., Zeng, X., Xia, Y., Zhao, Y. L., Pedersen, T. B., Jensen, C. N., et al. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3651536 · Cited by 33
Multimodal learning with next-token prediction for large multimodal models
Wang, X., Cui, Y., Wang, J., Zhang, F., Wang, Y., Zhang, X., Luo, Z., Sun, Q., Li, Z., Wang, Y., et al. (2026) · Nature · doi:10.1038/s41586-025-10041-x · Cited by 33
Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
Müller, A., Lukovnikov, D., Thietke, J., Fischer, A., & Quiring, E. (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/cvpr52734.2025.01950 · Cited by 33
Matryoshka Diffusion ModelsPreprint
Gu, J., Zhai, S., Zhang, Y., Susskind, J., & Jaitly, N. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.15111 · Cited by 33
FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video GenerationPreprint
Zhang, S., Li, W., Chen, S., Ge, C., Sun, P., Zhang, Y., Jiang, Y., Yuan, Z., Peng, B., & Luo, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.05179 · Cited by 33
A multispecies foundation model for genome function prediction, gene annotation and sequence designPreprint
Boshar, S., Evans, B., Tang, Z., Adel, Y., Bornachot, Y., Sidbon, S., Lorbeer, F. K., Picard, A., Rajesh, C., Seitz, E., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.22.695963 · Cited by 41
Qin, R., Wang, F., Zheng, X., Ni, Q., Li, J., Xue, X., & Hu, B. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3373928 · Cited by 32
ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction
Zhang, Z., Hu, J., Cheng, W., Paudel, D. P., & Yang, J. (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/cvpr52733.2024.01827 · Cited by 32
Training-Free Multi-style Fusion Through Reference-Based Adaptive Modulation
Liu, X., Lu, Y., Wang, X., & Wu, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4398-4_11 · Cited by 32
Community Forensics: Using Thousands of Generators to Train Fake Image Detectors
Park, J., & Owens, A. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00772 · Cited by 32
Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Art
Fan, D., Meng, R., Xu, X., Liu, Y., Nan, G., Feng, C., Han, S., Gao, S., Xu, B., Niyato, D. T., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3671110 · Cited by 32
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion ModelsPreprint
Sadat, S., Kansy, M., Hilliges, O., & Weber, R. M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.02687 · Cited by 32
DART: Denoising Autoregressive Transformer for Scalable Text-to-Image GenerationPreprint
Gu, J., Wang, Y., Zhang, Y., Zhang, Q., Zhang, D., Jaitly, N., Susskind, J., & Zhai, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.08159 · Cited by 32
Han, T., Chen, Z., Guo, S., Xu, W., & Bai, L. (2024) · arXiv (Cornell University) · doi:10.13140/rg.2.2.19747.67366 · Cited by 32
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
Cui, J., Li, H., Zhan, Y., Shang, H., Cheng, K., Ma, Y., Mu, S., Zhou, H., Wang, J., & Zhu, S. (2024) · arXiv · doi:10.48550/arxiv.2412.00733 · Cited by 32
TEXGen: a Generative Diffusion Model for Mesh Textures
Yu, X., Yuan, Z., Guo, Y.-C., Liu, Y.-T., Liu, J., Li, Y., Cao, Y., Liang, D., & Qi, X. (2024) · ACM Transactions on Graphics · doi:10.1145/3687909 · Cited by 31
World-consistent Video Diffusion with Explicit 3D Modeling
Zhang, Q., Zhai, S., Martin, M. A. B., Miao, K., Toshev, A., Susskind, J., & Gu, 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/cvpr52734.2025.02020 · Cited by 31
FMBoost: Boosting Latent Diffusion with Flow Matching
Schusterbauer, J., Gui, M., Ma, P., Stracke, N., Baumann, S. A., Hu, V. T., & Ommer, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73030-6_19 · Cited by 31
Taming Data and Transformers for Audio Generation
Haji-Ali, M., Menapace, W., Siarohin, A., Balakrishnan, G., & Ordóñez, V. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02632-y · Cited by 31
A Survey of Multimodal Hallucination Evaluation and Detection
Chen, Z., Min, Y., Zhang, J., Yan, B., Wang, J., Wang, X., & Shan, S. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02756-9 · Cited by 31
VisualCloze: A Universal Image Generation Framework via Visual in-Context Learning
Li, Z. H., Du, R., Yan, J., Zhuo, L., Li, Z. H., Gao, P., Ma, Z., & Cheng, M.-M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01763 · Cited by 31
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Jiang, L., Qing, Y., Jia, Y., Liu, Z., Kang, H., & Lu, X. B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01014 · Cited by 31
Deep generative modeling of temperature-dependent structural ensembles of proteins
Janson, G., Jussupow, A., & Feig, M. (2025) · Communications Chemistry · doi:10.1038/s42004-025-01737-2 · Cited by 33
Harnessing Diffusion-Yielded Score Priors for Image Restoration
Lin, X., Yu, F., Hu, J., You, Z., Shi, W., Ren, J., Gu, J., & Dong, C. (2025) · ACM Transactions on Graphics · doi:10.1145/3763346 · Cited by 30
Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis
Li, T., Zheng, R., Yang, M., Chen, J., & Yang, M. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755075 · Cited by 32
A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
He, S., Ji, P., Yang, Y., Wang, C. K., Ji, J., Wang, Y., & Ding, H. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3704980 · Cited by 30
Video-T1: Test-Time Scaling for Video Generation
Liu, F., Wang, H., Cai, Y., Zhang, K., Zhan, X., & Duan, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01735 · Cited by 30
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Jiang, Y., Huang, S., Xue, S., Zhao, Y., Cen, J., Leng, S., Li, K., Guo, J., Wang, K., Chen, M., et al. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11697407 · Cited by 30
FlowTok: Flowing Seamlessly Across Text and Image Tokens
He, J., Yu, Q., Liu, Q., & Chen, L.-C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01544 · Cited by 30
IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image PromptsPreprint
Zeng, B., Li, S., Feng, Y., Yang, L., Li, H., Gao, S., Liu, J., He, C., Zhang, W., Liu, J., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.05375 · Cited by 30
ConceptAttention: Diffusion Transformers Learn Highly Interpretable FeaturesPreprint
Helbling, A., Meral, T. H. S., Hoover, B., Yanardag, P., & Chau, D. H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.04320 · Cited by 30
A study of enhanced visual perception of marine biology images based on diffusion-GAN
Yao, F., Zhang, H., Gong, Y., Zhang, Q., & Pan, X. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01832-w · Cited by 29
Yu, H., Liu, X., Tian, Y., Wang, Y., Gou, C., & Wang, F. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3376575 · Cited by 29
RetractedMSDMAT-BTS: Multi-scale diffusion model and attention mechanism for brain tumor segmentation
Gao, T., Hu, W., Chen, M., Chen, L., & Jiang, H. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107505 · Cited by 29
Liu, Y., Li, W., Guan, J., Zhou, S., & Zhang, 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/cvpr52734.2025.01663 · Cited by 29
Human Motion Video Generation: A Survey
Xue, H., Luo, X., Hu, Z., Zhang, X., Xiang, X., Dai, Y., Liu, J., Zhang, Z., Li, M., Yang, J. J., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3594034 · Cited by 29
AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
Qiu, L., Zhu, S., Zuo, Q., Gu, X., Dong, Y., Zhang, J., Xu, C., Li, Z., Yuan, W., Bo, L., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01970 · Cited by 32
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Xiong, T., Liew, J. H., Huang, Z., Feng, J., & Liu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01744 · Cited by 29
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance
Luo, Y., Rong, Z., Wang, L., Zhang, L., & Hu, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01027 · Cited by 30
Guiding generative models to uncover diverse and novel crystals via reinforcement learning
Park, H., & Walsh, A. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01262-4 · Cited by 31
FunDiff: diffusion models over function spaces for physics-informed generative modeling
Wang, S., Dou, Z., Shan, S., Liu, T.-R., & Lu, L. (2026) · Nature Communications · doi:10.1038/s41467-026-72292-0 · Cited by 29
Neighboring Autoregressive Modeling for Efficient Visual Generation
He, Y., He, Y., He, S., Chen, F., Zhou, H., Zhang, K., & Zhuang, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01766 · Cited by 29
SurGen: Text-Guided Diffusion Model for Surgical Video GenerationPreprint
Cho, J., Schmidgall, S., Zakka, C., Mathur, M., Kaur, D., Shad, R., & Hiesinger, W. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.14028 · Cited by 31
I2VControl-Camera: Precise Video Camera Control with Adjustable Motion StrengthPreprint
Feng, W., Liu, J. D., Tu, P., Qi, T., Sun, M., Ma, T., Zhao, S., Zhou, S., & He, Q. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.06525 · Cited by 29
CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal ConcatenationPreprint
Zheng, C., Zhang, W., Zhang, S., Zheng, J., Dong, X. M., Li, H., Wu, Y., Jiang, D., & Liang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.11325 · Cited by 29
Continuous Diffusion Scales Competitively with Discrete Diffusion for LanguagePreprint
Yang, Z., Guo, W., Zhang, S., Sahoo, S. S., Chen, Y., Vahdat, A., Mardani, M., & Thickstun, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.18530 · Cited by 29
GAIA-1: A Generative World Model for Autonomous Driving
Hu, A., Russell, L., Yeo, H., Murez, Z., Fedoseev, G., Kendall, A., Shotton, J., & Corrado, G. (2023) · arXiv · doi:10.48550/arxiv.2309.17080 · Cited by 28
“Transferring the scaling principles from large language models to the visual domain holds the potential for delivering consistent and expected performance improvements [92, 93, 43, 16, 94].”
BackgroundDataset Distillation via a Noise-Unconstrained Generative Model
Zhang, J., Dai, L., Ye, F., Chen, Z., Li, P. L., Yang, X., & Sheng, B. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3690778 · Cited by 28
A review of deep learning-based approaches to sign language processing
Tan, S., Khan, N., An, Z., Ando, Y., Kawakami, R., & Nakadai, K. (2024) · Advanced Robotics · doi:10.1080/01691864.2024.2442721 · Cited by 28
Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity
Pascual, S., Yeh, C., Tsiamas, I., & Serrà, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73021-4_15 · Cited by 28
Generative AI Agents in Autonomous Machines: A Safety Perspective
Jabbour, J., & Reddi, V. J. (2024) · International Conference on Computer Aided Design · doi:10.1145/3676536.3698390 · Cited by 28
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Shin, C., Choi, J., Kim, H., & Yoon, 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/cvpr52734.2025.00748 · Cited by 28
View Selection for 3D Captioning via Diffusion Ranking
Luo, T., Johnson, J., & Lee, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72751-1_11 · Cited by 28
Wcdt: World-Centric Diffusion Transformer for Traffic Scene Generation
Chen, Y., He, Y., Tian, A. X., Chen, D., Wang, J., Shi, T., Heydarian, A., & Liu, P. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127600 · Cited by 28
AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
Wu, Z., Yu, C., Wang, F., & Bai, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01259 · Cited by 28
Materialistic: Selecting Similar Materials in Images
Sharma, P., Philip, J., Gharbi, M., Freeman, B., Durand, F., & Deschaintre, V. (2023) · ACM Transactions on Graphics · doi:10.1145/3592390 · Cited by 28
Physics vs Distributions: Pareto Optimal Flow Matching with Physics ConstraintsPreprint
Baldan, G., Liu, Q., Guardone, A., & Thuerey, N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.08604 · Cited by 28
Patch distance based auto-encoder for industrial anomaly detection
Ma, Z., Li, J., & Wong, W. K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126537 · Cited by 27
DiffuSAR: Frequency Domain-Aware Diffusion Model for SAR Image Generation
Ying, Z., Ke, W., Zhai, Y., Long, Z., Zhou, J., Zhu, H., & Chen, C. L. P. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3563798 · Cited by 27
Lei, C., Xia, M., Wang, S., Liang, Y., Yi, R., Wen, Y., & Liu, Y. (2024) · Computer Aided Geometric Design · doi:10.1016/j.cagd.2024.102293 · Cited by 27
Perceptual Artifacts Localization for Image Synthesis Tasks
Zhang, L., Xu, Z., Barnes, C., Zhou, Y., Liu, Q., Zhang, H., Amirghodsi, S., Lin, Z., Shechtman, E., & Shi, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00697 · Cited by 27
SD-DiT: Unleashing the Power of Self-Supervised Discrimination in Diffusion Transformer *
Zhu, R., Pan, Y., Li, Y., Yao, T., Sun, Z., Mei, T., & Chen, C. W. (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/cvpr52733.2024.00806 · Cited by 27
Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos
Luo, M., Xue, Z., Dimakis, A. G., & Grauman, K. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72920-1_23 · Cited by 27
CleanDIFT: Diffusion Features without Noise
Stracke, N., Baumann, S. A., Bauer, K., Fundel, F., & Ommer, B. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00020 · Cited by 27
Generative Diffusion for Regional Surrogate Models From Sea‐Ice Simulations
Finn, T. S., Durand, C., Farchi, A., Bocquet, M., Rampal, P., & Carrassi, A. (2024) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004395 · Cited by 27
Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution
Liu, Q., Yin, X., Yuille, A., Brown, A., & Singh, M. (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/cvpr52734.2025.00263 · Cited by 27
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
