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 2,001–2,100 of 3,684
DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
Li, Y., Chang, H., Hou, R., Shan, S., & Xilin, C. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3623508 · Cited by 1
Fast and Slow Diffusion With Fuzzy Contextual Representation for Medical Image Translation
Tang, Y., Zheng, J., Ren, F., Huang, D., Zeng, D., & Wu, D. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3642000 · Cited by 1
Zhou, L., QU, X., Fu, T., Wu, J., Song, H., Fan, J., Ai, D., Xiao, D., Xian, J., & Yang, J. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3648852 · Cited by 1
VLM-Driven Skill Selection for Robotic Assembly Tasks
Kim, J.-J., Koh, D.-Y., & Kim, C.-H. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301118 · Cited by 1
Ying, Z., Ke, W., Zhai, Y., Liu, X., Zhou, J., Coscia, P., & Genovese, A. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113648 · Cited by 1
Deng, J., Wen, G., Lei, Z., Xu, Q., Su, Y., & Zhang, Z. (2025) · ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part A Civil Engineering · doi:10.1061/ajrua6.rueng-1786 · Cited by 1
Accelerating Diffusion-Based Denoising Model With Optimized Time Steps
Cho, J., & Yoo, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3652541 · Cited by 1
Elegantly Written V2: Next-Scale Prediction for Enhancing Online Chinese Handwriting
Liu, Y., Kong, Y., Ding, Y., Liu, F., Wang, L., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5676-2_2 · Cited by 1
Toward Accurate Image Generation via Dynamic Generative Image Transformer
Mao, Z., Huang, M., Lin, Y., Wang, Q., Zhang, L., & Zhang, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3653620 · Cited by 1
Assessing the Naturalness of Text-to-Speech Models for Brazilian Portuguese NPC Dialogue
Filho, A. C. F., Sousa, R. T., da Rosa, A. S., Mendes, L. L., Pinto, P. L. L., & Filho, A. R. G. (2025) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr67689.2025.00054 · Cited by 1
An Improved Diffusion Model for Generating Images of a Single Category of Food on a Small Dataset
Chen, Z., Xiao, Z., Wu, D., & Sang, Q. (2026) · Foods · doi:10.3390/foods15030443 · Cited by 1
Learning From Videos Through Graph-to-Graphs Generative Modeling for Robotic Manipulation
Chen, G., Wang, M., Cui, T., Yang, C., Hu, M., Lu, H., Peng, Z., Zhou, T., Jiang, X., Yang, Y., et al. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3658211 · Cited by 1
Consistency-Regularized GAN for Few-Shot SAR Target Recognition
Zhai, Y., Liu, S., Zhou, W., Zhang, H., Zhou, Z., Tian, X., & Chen, C. L. P. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3657831 · Cited by 1
FedPDM: Representation enhanced federated learning with privacy preserving diffusion models
Guo, W., Zhuang, F., Tong, Y., Zhang, X., Hu, Z., Zhao, J., & Dong, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115452 · Cited by 1
Wiegmann, A. L., Chidester, J. R., Skochdopole, A. J., & Rohrich, R. J. (2026) · Aesthetic Surgery Journal · doi:10.1093/asj/sjag035 · Cited by 1
Mhdaunet: enhancing semantic consistency in diffusion models via dual-path noise alignment
Bei, Y., Lv, H., Zuo, S., Wang, N., & Chen, Q. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01798-w · Cited by 1
Precise finger articulation in sign language video generation
Hsiao, P.-H., Jia-xuan, Y. U., Chen, K.-L., Chiang, P.-H. F., Chien, J., Wu, H., Chen, S.-T., & Jang, J. R. (2026) · Enterprise Information Systems · doi:10.1080/17517575.2026.2632279 · Cited by 1
Wang, R., Dong, X., Liu, X., & Hu, F. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109927 · Cited by 1
Realgeneral: Unifying Visual Generation Via Temporal in-Context Learning With Video Models
Lin, Y., Huang, M., Zhuang, S., & Mao, Z. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01391 · Cited by 1
Bao, W., & Xiang, X. (2024) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis61828.2024.10593679 · Cited by 1
LiteDiT: An Efficient Diffusion Transformer Model for Remote Sensing Image Synthesis Focus on Object
Cao, Y., Geng, S., Zhao, J., & Wang, X. (2024) · International Conference on Artificial Intelligence and Digital Technology (ICAIDT) · doi:10.1109/icaidt62617.2024.00033 · Cited by 1
Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
Wu, J., Pan, K., Chen, Y., Deng, J., Pang, S., & Xu, W. (2024) · IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom) · doi:10.1109/metacom62920.2024.00029 · Cited by 1
A survey of emerging approaches and advances in video generation
Soleimani, E., & Khodabandelou, G. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104851 · Cited by 1
Foundations of Generative Information Retrieval
Ai, Q., Zhan, J., & Liu, Y. (2024) · The information retrieval series · doi:10.1007/978-3-031-73147-1_2 · Cited by 1
VEGA: Implementing a Versatile and Efficient Deep Learning Processor with Graph-Based ALU
Wang, W., Chen, Y., Huo, G., He, G., & Xu, N. (2024) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · doi:10.1109/iccd63220.2024.00095 · Cited by 1
He, X., Fan, W., Wang, Y., Liu, C., Miao, R., Juan, X., & Wang, X. Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780207 · Cited by 1
A Discrete Index Graph Diffusion Model for 3D Meshes Synthesis
Chen, J., Chen, Y., Zhao, J., & Ma, C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3545657 · Cited by 1
Audio Diffusion with Large Language Models
Huang, Y., Kastner, K., Audhkhasi, K., Ramabhadran, B., & Rosenberg, A. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888073 · Cited by 1
An Efficient Lung Disease Classification from X-ray Image Using Graph Neural Network and Transformer
Jiang, Z., Manshor, N. B., Hamdan, H., & Limi, C. (2025) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.15.1.12590 · Cited by 1
Text-guided dynamic mouth motion capturing for person-generic talking face generation
Liu, K., Wei, J., Yuan, R., Chai, R., He, S., Ma, Z., & Yang, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113354 · Cited by 1
A conditional generative diffusion model of trabecular bone with tunable microstructure
Wang, X., Shi, G., Sivakumar, A., Ye, T., Sylvester, A. D., Stayman, W., & Zbijewski, W. (2025) · SPIE Medical Imaging: Clinical and Biomedical Imaging · doi:10.1117/12.3049125 · Cited by 1
Corgi: Cached Memory Guided Video Generation
Wu, X., Singer, U., Lin, Z., Madotto, A., Xia, X., Xu, Y., Crook, P., Xin, D., & Moon, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00450 · Cited by 1
Efficient Text-Guided 3D-Aware Generation With Score Distillation on 3D Distribution
Cheng, Y., Yin, F., Huang, X., Yu, X., Liu, J., Feng, S., Yang, Y., & Tang, Y. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3559931 · Cited by 1
ViFusion: In-Network Tensor Fusion for Scalable Video Feature Indexing
Wang, Y., Zhu, Y., Li, X., Zhang, Y., Wu, R., & Kutscher, D. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733461 · Cited by 1
MedDiTPro: A Prompt-Guided Diffusion Transformer for Multimodal Longitudinal Medical Data Synthesis
Zhong, Y., Wang, X., Wang, J., Zhang, X., & Ma, F. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737045 · Cited by 1
T4Di: A Hybrid TTT-Transformer Backbone for Scalable and Efficient Diffusion Model
Wu, X., Pan, H., Liu, R., Dong, B., Zheng, Y., & Ye, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9812-7_14 · Cited by 1
FiGVCL: Fine-Grained Benchmark and Method for Video Copy Localization
Luo, W., Liu, Y., Li, B., Hu, W., & Maybank, S. J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3595625 · Cited by 1
High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
Shen, Y., Zhou, K., Wang, H., Yang, Y., & Shao, 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/cvpr52734.2025.02008 · Cited by 1
GHS-VDG:Graph and Hybrid Spatio-Temporal Attention for Video Diffusion Generation
Xinyu, G., Du, F., Song, L., & Zhang, X. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11083971 · Cited by 1
Diffuse and Refine Latent Prior with Transformers For Neural ISP
Mo, Z., Li, W., & Ding, S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084701 · Cited by 1
ConceptVoid: Precision Multi-Concept Erasure in Generative Video Diffusion
Huang, Z., Jin, X., Wu, C., & Mao, W. (2025) · Mathematics · doi:10.3390/math13162652 · Cited by 1
StrucADT: Generating Structure-Controlled 3D Point Clouds With Adjacency Diffusion Transformer
Shu, Z., Shen, J., Chen, Z., Han, X., & Xin, S. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3600392 · Cited by 1
Wang, R., Li, S., Fan, L., Ma, W., Li, Z., & Ai, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04549-2_21 · Cited by 1
DM-Tune: Quantizing Diffusion Models with Mixture-of-Gaussian Guided Noise Tuning
Haghi, P., Falahati, A., Azad, Z., Wu, C., Song, R., Liu, C., Li, A., & Geng, T. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11132501 · Cited by 1
Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent
Ci, E., Guan, S., Ge, Y., Zhang, Y., Li, W., Zhang, Z., Yang, J., & Tai, Y. Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01783 · Cited by 1
Exponential Dissimilarity-Dispersion Family for Domain-Specific Representation Learning
Togo, R., Nakagawa, N., Ogawa, T., & Haseyama, M. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3608661 · Cited by 1
Barreiro, V., Heras, D. B., & Argüello, F. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3617098 · Cited by 1
Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
Ye, Z., & Chen, M. (2025) · neural information processing systems · doi:10.52202/085713-4111 · Cited by 1
CLaRE: CLIP with Latent Reconstruction Errors for Generated Face Detection
Thakur, U., Khan, M. H., Changlani, M., Dotsinski, A., Mahadevan, A. K., Kechagias, I., & Najdenkoska, I. (2025) · ACM Workshop on Deepfake, Deception, and Disinformation Security (3D-Sec) · doi:10.1145/3733813.3764366 · Cited by 1
Scaling Transformer-Based Novel View Synthesis with Models Token Disentanglement and Synthetic Data
Nair, N. G., Kaza, S., Luo, X., Patel, V. M., Lombardi, S., & Park, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02653 · Cited by 1
DiffusionCleft: Facial Anomaly Synthesis Guided by Text
Rosero, K., Harrison, L. M., Kane, A. A., Hallac, R. R., & Busso, C. (2025) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3716553.3750794 · Cited by 1
MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention
Jiang, C., Kim, S., Gao, L., Zarch, H. E., Ro, W. W., & Annavaram, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37627-5_34 · Cited by 1
EVALUATION AND COMPARISON OF TEXT-TO-AUDIO GENERATION MODELS FOR MEDIA APPLICATIONS
Mediakov, O., BABIAK, Y., & Basyuk, T. (2025) · Herald of Khmelnytskyi National University Technical sciences · doi:10.31891/2307-5732-2025-351-3 · Cited by 1
Edit-Your-Interest: Efficient video editing via Feature Most-Similar Propagation
Zuo, Y., Wang, Z., Li, L., Liu, X., Liu, F., & Jiao, L. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115113 · Cited by 1
Label-Consistent Dataset Distillation with Detector-Guided Refinement
Zou, Y., Li, G., Wang, Z., Gu, C., & ZHANG, C. (2026) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2025edp7147 · Cited by 1
Imbalance in Balance: Online Concept Balancing in Generation Models
Shi, Y., Ou, J., Chen, R., Yang, H., Wang, J., Tao, X., Wan, P., Zhang, D., & Gai, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01619 · Cited by 1
Li, Z., Chen, X., Wang, S., Yuan, B., Nou, S., & Rithea, N. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9575-4_12 · Cited by 1
Yin, L., Zhao, J., Pan, Z., Yu, Z., & Xu, R. (2025) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2025.3624564 · Cited by 1
Zhang, Y., Wei, Y., Zhang, Z., Fan, J., Zhang, H., & Yan, S. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755541 · Cited by 1
MelodyEdit: Zero-shot Music Editing with Disentangled Inversion Control
Liu, H., Wang, J., Li, X., Wang, W., Chen, Q., Huang, R., Liu, Y., Xu, J., Zhao, Z., & Xue, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755377 · Cited by 1
Yin, D., Guo, J., Lu, H., Wu, F., & Lu, D. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758290 · Cited by 1
Unleashing the Power of Each Distilled Image
Zhang, J., Chen, Z., & Dai, L. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3624626 · Cited by 1
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
Ramachandran, S. N., Lal, M. K., & Sra, S. (2025) · neural information processing systems · doi:10.52202/085713-3468 · Cited by 1
Post-Training Quantization for Audio Diffusion Transformers
Khandelwal, T., & Fuentes, M. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230962 · Cited by 1
DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
Amin, F., Afroz, S., Gharami, K., Moghadampanah, M., & Nikolopoulos, D. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_7 · Cited by 1
Efficient Medical Image Segmentation with Rectified Flow-Based Diffusion Transformer
Kato, S., Nishimura, M., Ueda, T., Song, Y., & Nishikawa, I. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4100-3_1 · Cited by 1
Rethinking Video Super-Resolution: Towards Diffusion-Based Methods without Motion Alignment
Zhan, Z., Pang, W., Zhu, X., & Bai, Y. (2025) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1109/icsps66615.2025.11347706 · Cited by 1
End-to-End Camera Pose Estimation with Camera Ray Token
Kim, J., & Ha, J.-E. (2025) · Electronics · doi:10.3390/electronics14234624 · Cited by 1
LeakDiT: Diffusion Transformers for Trace-Augmented Side-Channel Analysis
Lee, I., Bae, D., Hong, S., & Lee, S. (2025) · IEEE Computer Architecture Letters · doi:10.1109/lca.2025.3639372 · Cited by 1
Hu, Y., & Prasad, S. R. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00448 · Cited by 1
Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
Li, X., Chen, Q., Peng, X., Yu, K., Chen, X., & Lu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01199 · Cited by 1
An Interactive Drawing Assistant Harmonizing User Control and Creative Freedom in Image Generation
Chen, J., & Zhang, Z. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3770961 · Cited by 1
Unifying Generative Self-Supervised Paradigms with Diffusion Models
Zhou, L., & Yue, X. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3770999 · Cited by 1
Hybrid Autoregressive-Diffusion Model for Real-Time Sign Language Production
Ye, M., Ye, X., & Manoharan, S. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.31 · Cited by 1
CSI Prediction Using Diffusion Models
Sattari, M., Aliakbari, J., Amat, A. G. I., & Svensson, T. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3719116 · Cited by 1
DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment
Du, Z., Deng, G., Guo, X., Gao, X., Li, L., Cheng, K., Han, F., Yang, S., Liu, P., Zhong, P., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463059 · Cited by 1
DMP-TTS: Disentangled Multi-Modal Prompting for Controllable Text-to-Speech with Chained Guidance
Yin, K., Qiang, C., Zhao, S., Wang, X., Liang, Y., Cai, P., Xu, T., Zhang, C., & Chen, E. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462428 · Cited by 1
Martini, L., Zolezzi, D., Iacono, S., Oneto, L., & Vercelli, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-31543-8 · Cited by 1
FreeCus: Free Lunch Subject-Driven Customization in Diffusion Transformers
Zhang, Y., Wang, Z., Zhou, Q., & Yang, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01440 · Cited by 1
Mind the gap: navigating inference with optimal transport maps
Algren, M., Golling, T., Bello, F. A. D., & Pollard, C. S. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae98e3 · Cited by 1
Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI
Bubeck, N., Zhang, Y., Shit, S., Rueckert, D., & Pan, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05472-2_26 · Cited by 1
Beckmann, P. (2025) · Synthese · doi:10.1007/s11229-025-05174-5 · Cited by 2
Xu, Y., Tang, F., Wu, Y., Gao, L., Deussen, O., Yan, H., Li, J., Cao, J., & Lee, T.-Y. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763820 · Cited by 1
UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images
Zhao, Y., Gao, Y., Luo, Y., Duan, J., Lin, S., Xiong, L., & Lian, Z. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763923 · Cited by 1
ChromaFlow: End-to-End Flow Matching for Efficient Video Colorization
Liu, H., Li, C., Wong, T., & Liu, X. (2025) · SIGGRAPH Asia Technical Communications · doi:10.1145/3757376.3771391 · Cited by 1
CustomX: Unified Character, Action, and Scene Customization in Video World Models
Wang, Y., Wei, F., Zhang, H., Dai, B., & Lu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37419-6_23 · Cited by 1
CoDi: An Exemplar-Conditioned Diffusion Model for Low-Shot Counting
Šuštar, G., Pelhan, J., Lukežič, A., & Kristan, M. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3728653 · Cited by 1
Inference-Time Scaling for Visual AutoRegressive Modeling by Searching Representative Samples
Tang, W., Wan, X., Li, S., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5699-1_28 · Cited by 1
Wireless Channel Identification via Conditional Diffusion Model
Li, Y., Zheng, Z., Liu, C. K., & Fei, Z. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11310577 · Cited by 1
Liu, Y., Zuo, Y. N., An, Y., Song, L., & Tao, F. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02768-1 · Cited by 1
Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation
Wang, J., Lu, J., Chen, C., Xu, G., Yang, H., Chen, P., Zhang, N., Xu, Y., Wu, L., Shao, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37258-1_31 · Cited by 1
LatentEdit: Adaptive Latent Control for Consistent Semantic Editing
Liu, S., Chen, W., Tang, Y., & He, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5679-3_7 · Cited by 1
Sun, L., Wu, R., Zhang, Z., Li, R., Sun, Y., Liu, S., & Zhang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_23 · Cited by 1
Implicit Neural Representation Facilitates Unified Universal Vision Encoding
Gwilliam, M., Wang, X. (., Hu, X., & Yang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_2 · Cited by 1
Lan, Y., Liao, M., Chen, M., & Ou, Y. (2026) · Journal of Computing and Information Technology · doi:10.20532/cit.2025.1006253 · Cited by 1
Style Composition Within Distinct LoRA Modules for Traditional Art
Lee, J., Park, W., Shin, W., Lee, H., Na, H. M., & Kwak, N. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00466 · Cited by 1
Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
Li, M., Li, G., Mao, J., Ye, L., Ogawa, T., & Haseyama, M. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00708 · Cited by 1
UP-VTON: A Unified Virtual Try-On Framework Supporting Mask, Mask-Free, and Prompt-Driven Guidance
Jo, Y., Park, M., & Kang, D.-O. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00726 · Cited by 1
Efficient Dataset Distillation via Generative Pruning
Ma, Y., Li, M., Duan, G., Qin, K., Liang, S., & Zhang, D. (2026) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2026.3668524 · Cited by 1
Arshad, M. I., Lee, H., Lee, H., Kang, M., Kim, Y., & Bang, H. (2026) · IEEE Access · doi:10.1109/access.2026.3669078 · Cited by 1
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
