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 1,301–1,400 of 3,684
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
Cong, X., Li, Z., Dou, Z., Li, H., Taheri, O., Guo, C., Mittal, A., An, S., Komura, T., Matusik, W., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_36 · Cited by 5
ProGVC: Progressive-Based Generative Video Compression via Auto-Regressive Context Modeling
Li, D., Dong, R., Li, K., Chen, Y., Ding, D., & Li, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36846-1_20 · Cited by 5
ActionParty: Multi-subject Action Binding in Generative Video Games
Pondaven, A., Wu, Z., Gilitschenski, I., Torr, P. H. S., Tulyakov, S., Pizzati, F., & Siarohin, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_5 · Cited by 5
Yang, H. J., Lee, H., Shim, K., Kwak, J., Kim, H., Kim, D. S., Ngo, K. A., Ryu, S., Choi, J., Kim, Y., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3683120 · Cited by 5
Continuous Adversarial Flow Models
Lin, S., Yang, C., Lin, Z., Chen, H., & Fan, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_36 · Cited by 5
MMControl: Unified Multi-modal Control for Joint Audio-Video Generation
Li, L., Wang, W., Zhao, C., Feng, T., Zhao, Z., Chen, H., & Shen, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_37 · Cited by 5
Grouped Speculative Decoding for Autoregressive Image Generation
So, J., Shin, J., 국현호, & Park, E. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01426 · Cited by 5
SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
Park, B., Go, H., Nam, H., Kim, B.-H., Chung, H., & Kim, C. G. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02537 · Cited by 5
Nexus: Native Mesh Generation with Diffusion
Wang, H., Liu, Y.-T., Guo, Y.-C., Feng, Q.-Y., Zou, Z., Liang, D., Zhang, B., & Cao, Y. (2026) · ACM Transactions on Graphics · doi:10.1145/3811344 · Cited by 5
REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
Guo, C., Fu, J., Fang, J., Zhang, X., Wang, K., & Feng, G. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3718264 · Cited by 5
360Anything: Geometry-Free Lifting of Images and Videos to $$360^\circ $$
Wu, Z., Watson, D., Tagliasacchi, A., Fleet, D. J., Brubaker, M. A., & Saxena, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37035-8_8 · Cited by 5
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
Wang, X., Shi, H., Li, Z., Zhou, Y., Liu, X., Ma, Y., & Wan, P. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836018 · Cited by 5
Sample-Efficient Diffusion for Text-To-Speech Synthesis
Lovelace, J., Ray, S., Kim, K., Weinberger, K. Q., & Wu, F. F. (2024) · Interspeech (USB) · doi:10.21437/interspeech.2024-2235 · Cited by 6
CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence
Hou, Y., Fan, H., Zhang, J., Zhang, Y., Chen, H., Zhou, M., Yu, F., Zimmermann, R., & Yang, Y. (2025) · Engineering · doi:10.1016/j.eng.2025.12.025 · Cited by 5
Style-Friendly SNR Sampler for Style-Driven Generation
Choi, J., Shin, C., Oh, Y., Kim, H., Lee, J., & Yoon, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00553 · Cited by 5
Savgbench: Benchmarking Spatially Aligned Audio-Video Generation
Shimada, K., Simon, C., Shibuya, T., Takahashi, S., & Mitsufuji, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464978 · Cited by 5
Camera trajectory generation: A comprehensive survey of methods, metrics, and future directions
Dehghanian, Z., Ardehkhani, P., Vahedi, A., Beigy, H., & Rabiee, H. R. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104872 · Cited by 5
Primal: Physically Reactive and Interactive Motor Model for Avatar Learning
Zhang, Y., Feng, Y., Cseke, A., Saini, N., Bajandas, N., Heron, N., & Black, M. J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01182 · Cited by 5
LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
Chen, N., Huang, M., Meng, Y., & Mao, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00935 · Cited by 5
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
Wei, G., & Chellappa, R. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01928 · Cited by 5
Veila: Panoramic LiDAR Generation from a Monocular RGB Image
Liu, Y., Kong, L., Yang, W., Liang, A., Gao, J., Wu, Y., Xu, X., Li, X., Li, L., Chen, R., et al. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11697175 · Cited by 5
Efficient Training of Large Vision Models via Advanced Automated Progressive Learning
Li, C., Zhang, J., Lin, S., Yang, Z., Liang, J., Liang, X., & Chang, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3673336 · Cited by 5
CODA: Repurposing Continuous VAEs for Discrete Tokenization
Liu, Z., Ni, Z., Hua, Y., Deng, X., Ma, X., Zhong, C., & Huang, G. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01757 · Cited by 5
VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition Dataset
Kim, M., Sagong, M.-C., Nam, G. P., Cho, J., & Kim, I.-S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00936 · Cited by 5
DiTalker: A unified DiT-based framework for high-quality and style-controllable portrait animation
He, F., F, Y., Fan, L., Di, D., & Su, T. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104819 · Cited by 5
Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
Cao, H., Feng, Y., Gong, B., Tian, Y., Lu, Y., Liu, C., & Wang, B. (2025) · neural information processing systems · doi:10.52202/085713-2718 · Cited by 5
Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
Zhang, J., Jalali, M., Li, C. T., & Farnia, F. (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/cvpr52734.2025.00774 · Cited by 5
Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical PoetryPreprint
Jiang, J. B., Ling, Y., Li, B., Li, P., Piao, J., & Zhang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.06196 · Cited by 5
RNACG: A Universal RNA Sequence Conditional Generation model based on Flow-MatchingPreprint
Gao, L., & Lü, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.19838 · Cited by 5
Data Pruning in Generative Diffusion ModelsPreprint
Briq, R., Wang, J., & Kesselheim, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.12523 · Cited by 5
Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable DiffusionPreprint
Schaerf, L., Alfarano, A., Silvestri, F., & Impett, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.14524 · Cited by 5
Generative Modeling with Bayesian Sample InferencePreprint
Lienen, M., Kollovieh, M., & Günnemann, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.07580 · Cited by 5
Towards Fusing Point Cloud and Visual Representations for Imitation LearningPreprint
Donat, A., Jia, X., Huang, X., Taranović, A., Blessing, D., Li, G., Zhou, H., Zhang, H., Lioutikov, R., & Neumann, G. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.12320 · Cited by 5
Partition Generative Modeling: Masked Modeling Without MasksPreprint
Deschenaux, J., Tran, L., & Gülçehre, Ç. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.18883 · Cited by 5
Hierarchical protein backbone generation with latent and structure diffusionPreprint
Yim, J., Jaakik, M., Liu, G., Gershon, J. M., Kreis, K., Baker, D. A., Barzilay, R., & Jaakkola, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.09374 · Cited by 5
EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot ManipulationPreprint
Dong, Z., Ni, F., Yuan, Y., Li, Y., & Hao, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.10105 · Cited by 5
FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video GenerationPreprint
Kim, S., Lee, S., & Cho, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24241 · Cited by 5
Diff-Prompt: Diffusion-Driven Prompt Generator with Mask SupervisionPreprint
Yan, W., Lin, W., Guo, Z., Wang, Y., Feng, F., Yang, X., Wang, Z., & Jin, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.21423 · Cited by 6
Fang, T., Zhang, H., Xie, R., Han, Z., Tao, X., Zhao, T., Wan, P., Ding, W., Ouyang, W., Ning, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.16515 · Cited by 5
COMBAT: Conditional World Models for Behavioral Agent TrainingPreprint
Agarwal, A., Meshram, P. M., Singh, S., Suman, S., Lapp, A., Matiana, S., Castricato, L., & Frazier, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.00825 · Cited by 5
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language ModelsPreprint
Tong, J., Wang, Z., Ren, Y., Yin, P., Wu, H., Zhang, W., & Shen, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.04592 · Cited by 5
Utterance Alignment of Language Models for Effective User Simulation in Task-Oriented Dialogues
Luo, X., Wang, J., & Zhang, X. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3525981 · Cited by 4
Semantic-Guided Flow Matching for Fast and Accurate Remote Sensing Image Super-Resolution
Gong, Z., Yi, F., Guan, L., Dong, C., & Zeng, H. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3608455 · Cited by 4
Wang, Y., Wen, R., Ishii, H., & Ohya, J. (2025) · Journal of Imaging · doi:10.3390/jimaging11110395 · Cited by 4
Diff-DiT: Temporal Differential Accelerator for Low-bit Diffusion Transformers on FPGA
Tang, S., Zheng, P., Chen, R., Lv, Y., da Silva, B., & Ling, M. (2025) · doi:10.1109/iccad66269.2025.11240791 · Cited by 4
DreamCube: RGB-D Panorama Generation via Multi-Plane Synchronization
Huang, Y., Zhou, Y., Wang, J., Huang, K., & Liu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02311 · Cited by 4
Decoupling Privacy Noise from Optimization in Transformer Forecasting
Kantheti, B., & de Araújo, C. A. P. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8060156 · Cited by 4
ColorizeDiffusion: Improving Reference-Based Sketch Colorization with Latent Diffusion Model
Yan, D., Yuan, L., Wu, E., Nishioka, Y., Fujishiro, I., & Saito, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00498 · Cited by 4
Liu, J., Wang, Y., Jin, L., Bao, W., Zong, Z., He, S., & Wei, Z. (2025) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2025.3569099 · Cited by 4
Ma, X., Ma, Y., Wang, Y., Li, C., Liu, Y., Chen, X., Dai, J., Bi, N., & Men, K. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ade845 · Cited by 4
Unity in Diversity: Video Editing via Gradient-Latent Purification
Gao, J., Yang, K., Yao, X., & Hu, 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/cvpr52734.2025.02179 · Cited by 4
Sajid, M., Malik, K. R., Khan, A. H., Fuzail, M., & Li, J. (2025) · Cluster Computing · doi:10.1007/s10586-025-05618-0 · Cited by 4
Wu, Y., Xiang, Z., Tan, Y., Hu, J., Chen, D., Zhao, J., & Wei, H. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104962 · Cited by 4
CausalGenDiff: Generative causal diffusion bridges scRNA-seq and spatial transcriptomics
Sadia, R. T., Ahamed, M. A., & Cheng, Q. S. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104966 · Cited by 4
DiffusionSL: Sequence Labeling via Tag Diffusion Process
Huang, Z., Cao, P., Zhao, J., & Liu, K. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.860 · Cited by 4
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
Ni, Z., Wang, Y., Zhou, R., Lu, R., Guo, J., Hu, J., Liu, Z., Yao, Y., & Huang, G. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72640-8_17 · Cited by 4
A lightweight diffusion model for image generation based on improved MobileViT
Liu, Y., & Sun, W. (2024) · International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR) · doi:10.1145/3700906.3700917 · Cited by 4
Personalized and Controllable Voice Style Transfer With Speech Diffusion Transformer
Choi, H.-Y., Lee, S.-H., & Lee, S.-W. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3533362 · Cited by 4
Prompt suffix-attack against text-to-image diffusion models
Xiong, S., Du, Y., Wang, Z., & Sun, P. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129659 · Cited by 4
Generative artificial intelligence for ophthalmic images: developments, applications and challenges
Li, T., Wang, Z., Jiang, Z., Zhong, H., & Qin, Y. (2025) · The Visual Computer · doi:10.1007/s00371-025-03988-5 · Cited by 4
Exploring Diffusion Models for Oral Health Applications: A Conceptual Review
Tabejamaat, M., & Soliman, A. (2025) · IEEE Access · doi:10.1109/access.2025.3593933 · Cited by 4
V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow
Choi, J., Kim, J.-H., Li, J., Chung, J. S., & Liu, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889780 · Cited by 4
UltraTwin: Towards Cardiac Anatomical Twin Generation from Multi-view 2D Ultrasound
Yu, J., Duan, Y., Huang, Y., Wang, Y., Ling, R., Luo, W., Zhang, A., Xu, J., Ni, Q., Zhou, Y., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05325-1_58 · Cited by 4
Qin, Z., Cheng, B. C., Liang, S., Lu, B., & Han, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3613700 · Cited by 4
Li, J., Huang, S., Xu, J., Liu, J., Xu, N., & Dai, G. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3624278 · Cited by 4
AdaGen: Learning Adaptive Policy for Image Synthesis
Ni, Z., Wang, Y., Hua, Y., Zhou, R., Guo, J., Song, J., Zheng, B., & Huang, G. M. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3626772 · Cited by 4
DLTTS: Diffusion Model for Long-Tailed Time Series Generation in Industrial Scenarios
Hu, W., Zhang, H., Chen, W., Chen, K., Long, J., Shang, W., & Cao, Z. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3650739 · Cited by 4
Xie, Y., Li, Z., Jiang, F., Tao, R., & Zhu, H. (2026) · Energy · doi:10.1016/j.energy.2025.139897 · Cited by 4
Gu, Y., Zou, L., & Li, C. (2026) · ACM Transactions on Information Systems · doi:10.1145/3797895 · Cited by 4
CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
Wang, J., Reynaud, H., Erick, F. X., & Kainz, B. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00703 · Cited by 4
Causal Motion Tokenizer for Streaming Motion Generation
Jiang, B., Chen, X., Zeng, A., Sun, X., Yin, F., Zeng, X., Zhang, X., Yu, G., & Chen, T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00214 · Cited by 4
Learning a Unified Template for Gait Recognition
Huang, P., Hou, S., Huang, J., & Huang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01158 · Cited by 4
A Semantic Conditional Diffusion Model for Enhanced Personal Privacy Preservation in Medical Images
Wang, S., Zhao, Z., Zhao, Y., Wang, L., Zhang, Y., Wang, J., Qiao, S., & Lv, Z. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3511583 · Cited by 4
A Semi-Supervised Domain Adaptation Method for Sim2Real Object Detection in Autonomous Mining Trucks
Guo, L., Guo, Y., Liu, J., Zhang, Y., Song, Z., Zhang, X., & Liu, H. (2025) · Sensors · doi:10.3390/s25051425 · Cited by 4
Unleashing the Potential of Synthetic Images: A Study on Histopathology Image Classification
Benito-Del-Valle, L., Álvarez-Gila, A., Egusquiza, I., & Saratxaga, C. L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91721-9_9 · Cited by 4
VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors
Koo, J., Guerrero, P., Huang, C.-H. P., Ceylan, D., & Sung, 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/cvpr52734.2025.01648 · Cited by 4
Zhou, X., Liu, J., Yu, S., Yang, H., Li, C., Tan, T., & Wang, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05127-1_1 · Cited by 4
Li, S., Bai, H., Gao, Y., Lv, C., Yuan, H., Li, C., Hua, W., & Xie, T. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613146 · Cited by 4
Difforecast: Image Generation Based Highway Traffic Forecasting with Diffusion Model
Chi, P., & Ma, X. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386463 · Cited by 4
Xie, Y., Wang, C., Liu, K., Xuanyuan, Z., He, Y., Cheng, H., Nüchter, A., Li, L., Huai, R., Tang, S., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3394520 · Cited by 4
Improving Text Generation on Images with Synthetic Captions
Koh, J., Park, S., & Song, J. (2024) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai63651.2024.00121 · Cited by 4
Pham, K.-N., Chen, J., & Chen, Q. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681079 · Cited by 4
D$$^2$$Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods
Susladkar, O., Deshmukh, G., Mittal, S., & Shastri, P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78172-8_5 · Cited by 4
Diffusion Model Compression for Image-to-Image Translation
Kim, G., Kim, B., Park, E., & Cho, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0917-8_9 · Cited by 5
Zero-Shot Head Swapping in Real-World Scenarios
Kang, T., Jeong, S., Jang, H., & Choo, 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/cvpr52734.2025.01009 · Cited by 4
An Image-like Diffusion Method for Human-Object Interaction Detection
Hui, X., Qu, H., Rahmani, H., & Liu, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01307 · Cited by 4
XMoP: Whole-Body Control Policy for Zero-Shot Cross-Embodiment Neural Motion Planning
Rath, P. K., & Gopalan, N. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127979 · Cited by 4
AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
Hatanpää, V., Ku, E., Stock, J., Emani, M. K., Foreman, S., Jung, C., Madireddy, S., Nguyen, T., Sastry, V. K., Sinurat, R. A. O., et al. (2025) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3712285.3772094 · Cited by 4
ConsistEdit: Highly Consistent and Precise Training-free Visual Editing
Yin, Z., Chen, L.-H., Ni, L. M.-S., & Dai, X. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763909 · Cited by 4
Generating 360° Video is What You Need For a 3D Scene
Zhang, Z., Hold-Geoffroy, Y., Hašan, M., Chen, Z., Luan, F., Dorsey, J. O., & Hu, Y. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763876 · Cited by 4
Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation
Huang, Z., Zhou, Y., Xu, X., Xu, C., Xing, X., Qin, J., & He, S. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3649047 · Cited by 4
CGTGait: Collaborative Graph and Transformer for Gait Emotion Recognition
Zhou, J., Xiong, H., Lu, J., Lin, Z., & Feng, B. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411435 · Cited by 4
Self-attention as the backbone: A survey on Vision Transformers
Waseem, A., Ruiu, P., Nixon, S., Lagorio, A., & Tistarelli, M. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104791 · Cited by 4
Samson, G. (2024) · International Journal of Electronics and Telecommunications · doi:10.24425/ijet.2024.149550 · Cited by 4
DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images
Yang, B., Zhang, M., Zhao, Y., Zhang, Z., Hu, X., & Gong, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3528474 · Cited by 4
AToM: Adaptive Token Merging for Efficient Acceleration of Vision Transformer
Shin, J., Kang, M., Han, Y., Park, J., & Kim, L. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3540638 · Cited by 4
DehazeDiff: Image Dehazing via Mask-guided Diffusion Model
Luo, L., Wang, Y., & Li, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04515-8 · Cited by 4
Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
Cho, J., Youwang, K., Yang, H., & Oh, T.-H. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02122 · Cited by 4
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
Yuan, Z., Wang, S., Shang, Y., Zhang, H., Fang, T., Xie, R., Yan, S., Dai, G., & Wang, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755638 · Cited by 4
Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
Lee, S., & Kwak, J.-G. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763940 · Cited by 4
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
