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 801–900 of 3,684
BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video GenerationPreprint
Gu, Y., Li, X., Hu, Y., Chen, M., & Zhuang, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.10774 · Cited by 12
Meng, X., Zhang, Z., Zhang, Z., Liao, J., Qin, L., & Wang, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.14256 · Cited by 12
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State ReformulationPreprint
Gourevitch, S., Janati, Y., Shariatian, D., Simsekli, U., Moulines, É., Xing, E. P., & Durmus, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.22765 · Cited by 12
$π_0$: A Vision-Language-Action Flow Model for General Robot Control
Black, K., Brown, N., Driess, D., Esmail, A., Equi, M., Finn, C., Fusai, N., Groom, L., Hausman, K., Ichter, B., et al. (2024) · arXiv · doi:10.48550/arxiv.2410.24164 · Cited by 13
“…transformer backbone that encodes the observations (which comes after the ViT image encoders) is not pre-trained on Internet data; (6) The action expert uses the DiT architecture [36] rather than the Gemma architecture, and hence incorporates the flow-matching timestep τ using AdaLN-Zero layers.”
Goku: Flow Based Video Generative Foundation Models
Chen, S., Ge, C., Zhang, Y., Zhang, Y., Zhu, F., Yang, H., Hao, H., Wu, H., Lai, Z., Hu, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.04896 · Cited by 11
LD-CSNet: A latent diffusion-based architecture for perceptual Compressed Sensing
Zheng, B., Sun, G., Dong, L., & Wang, S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106541 · Cited by 11
Redesigning the Decoder and Loss Function of Diffusion Transformer for PV Temporal Simulation
Fu, X., Chang, F., Li, Z., Sun, H., Zhang, Y. M., & Yang, D. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3627923 · Cited by 11
EEGCiD: EEG Condensation Into Diffusion Model
Chen, J., Pi, D., Jiang, X., Gao, F., Bi, W., & Chen, Y. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3486203 · Cited by 12
GMT: Guided Mask Transformer for Leaf Instance Segmentation
Chen, F., Tsaftaris, S. A., & Giuffrida, M. V. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00126 · Cited by 11
ECE-TTS: A Zero-Shot Emotion Text-to-Speech Model with Simplified and Precise Control
Liang, S., Zhou, R., & Yuan, Q. (2025) · Applied Sciences · doi:10.3390/app15095108 · Cited by 11
Generative Semantic Communication for Joint Image Transmission and Segmentation
Yuan, W., Ren, J., Wang, C., Zhang, R., Wei, J., Kim, D. I., & Cui, S. R. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162317 · Cited by 11
FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention
Ju, X., Ye, W., Liu, Q., Wang, Q., Wang, X., Wan, P., ZHANG, D., Gai, K., & Xu, Q. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01460 · Cited by 11
3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
Luo, Y., Zhou, S., Lan, Y., Pan, X., & Loy, C. C. (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/cvpr52734.2025.01532 · Cited by 11
Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach
Li, J., Jiang, C., Jiang, J., Liang, P., Ma, J., & Nie, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3642842 · Cited by 11
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving Data Generation
Tu, J., Ji, W., Zhao, H., Zhang, C., Zimmermann, R., & Qian, H. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3712064 · Cited by 11
Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer
Hou, S., Liu, S., Yuan, R., Xue, W., Shan, Y., Zhao, M., & Zhang, C. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890309 · Cited by 11
Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-trained Diffusion Priors
Wang, R., Xiang, J., Yang, J., & Tong, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72992-8_25 · Cited by 11
Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas
Quattrini, F., Pippi, V., Cascianelli, S., & Cucchiara, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72986-7_14 · Cited by 11
Chu, H., Wu, W., Feng, G., & Zhang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01513 · Cited by 11
Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation
Mo, S., Xie, E., Wu, Y., Chen, J. S., Nießner, M., & Li, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72907-2_21 · Cited by 11
Dynamic Concepts Personalization from Single Videos
Abdal, R., Patashnik, O., Skorokhodov, I., Menapace, W., Siarohin, A., Tulyakov, S., Cohen‐Or, D., & Aberman, K. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730644 · Cited by 11
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
Zong, C., Wang, C., Qin, M., Feng, L., Wang, X., & An, B. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3672064 · Cited by 11
Applications of modular co-design for de novo 3D molecule generation
Reidenbach, D., Nikitin, F., Isayev, O., & Paliwal, S. (2026) · Digital Discovery · doi:10.1039/d5dd00380f · Cited by 14
Wang, B., Ning, Z., Ding, J., Gao, X., Yin, L., Jiang, D., Yang, J., & Liu, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01924 · Cited by 11
Omni 2 : Unifying Omnidirectional Image Generation and Editing in an Omni Model
Liu, Y., Duan, H., Zhu, Y., Liu, X., Liu, L., Xu, Z., Ma, G., Min, X., Zhai, G., & Callet, P. L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755405 · Cited by 11
Wang, Z., Müller, K., Filipovich, M. J., Launay, J., Ohana, R., Pariente, G., Mokaadi, S., Brossollet, C., Moreau, F., Cappelli, A., et al. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2532022123 · Cited by 11
A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives
Li, S., Ji, S., Wang, Z., Wu, S., Yu, J., & Zhang, K. (2026) · ACM Computing Surveys · doi:10.1145/3800682 · Cited by 11
LVMark: Robust Watermark for Latent Video Diffusion Models
Jang, Y., Jang, M., Lee, J., Yang, F., Oh, G., Jeong, J., & Kim, S. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3688194 · Cited by 11
DiffSwinTr : A diffusion model using 3D Swin Transformer for brain tumor segmentation
Zhu, J., Zhu, H., Jia, Z., & Ma, P. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23080 · Cited by 11
ContextMRI: Enhancing compressed sensing MRI through metadata conditioning
Chung, H., Lee, D., Wu, Z., Kim, B., Bouman, K. L., & Ye, J. C. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104353 · Cited by 11
Fast LiDAR Data Generation with Rectified Flows
Nakashima, K., Liu, X., Miyawaki, T., Iwashita, Y., & Kurazume, R. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127894 · Cited by 11
QR-LoRA: Efficient and Disentangled Fine-Tuning via QR Decomposition for Customized Generation
Yang, J., Ma, Y., Di, D., Cui, J., Li, H., Chen, W., Xie, Y., Yang, X., & Zuo, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01634 · Cited by 11
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Hassani, A., Hwu, W., & Shi, H. (2024) · neural information processing systems · doi:10.52202/079017-2065 · Cited by 11
WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
Liu, Z., Deng, X., Chen, S., Wang, A., Guo, Q., Han, M., Xue, Z., Chen, M., Luo, P., & Yang, L. (2025) · neural information processing systems · doi:10.52202/085713-1540 · Cited by 11
DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation
Zhang, H., Chen, K., Zhang, Z., Chen, H. H., Lyu, Y., Zhou, K., Zhang, Y., Yang, S., & Chen, Y.-C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_37 · Cited by 11
Guiding diffusion models to reconstruct flow fields from sparse data
Trepat, M. A., Medrano-Navarro, L., Liu, Q., Guastoni, L., & Thuerey, N. (2026) · Physics of Fluids · doi:10.1063/5.0304492 · Cited by 11
Edit: Efficient Diffusion Transformers with Linear Compressed Attention
Becker, P., Mehrotra, A., Chavhan, R., Chadwick, M., Morreale, L., Noroozi, M., Ramos, A. G. C. P., & Bhattacharya, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01823 · Cited by 11
Li, C., Wang, X., Li, M., Miao, B., Sun, P., Zhang, Y., Ji, X., & Zhu, Y. P. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01895 · Cited by 11
RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing
Qu, T., Ke, L., Zhan, X., Tang, L., Liu, Y., Peng, B., Yu, B., Yu, D., & Jia, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37718-0_35 · Cited by 11
Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
Wei, T., Chen, D., Zhou, Y., & Pan, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3663759 · Cited by 11
RAE-NWM: Navigation World Model in Dense Visual Representation Space
Zhang, M., Shen, W., Zhang, F., Qin, H., Pei, Z., & Meng, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_26 · Cited by 11
Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
Lv, Z., Si, C., Pan, T., Chen, Z., Wong, K.-Y. K., Qiao, Y., & Liu, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01390 · Cited by 11
Wu, J., Li, Z., Hui, Z., Zhang, Y., Kong, L., & Yang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01395 · Cited by 11
OmniFace: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer
Guo, X., Ye, F., Li, X., Tu, P., Zhang, P., Sun, Q., Zhao, S., Hou, X., & He, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_29 · Cited by 11
CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection
Li, W., Liu, X., Ma, J., & Yuan, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73001-6_15 · Cited by 11
Object Isolated Attention for Consistent Story Visualization
Luo, X., Cheng, J., Xie, Y., Zhang, X., Feng, T., Liu, Z., Ma, F., & Yu, F. R. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210189 · Cited by 11
Defining error accumulation in ML atmospheric simulatorsPreprint
Parthipan, R., Anand, M., Christensen, H. M., Hosking, J. S., & Wischik, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.14714 · Cited by 11
Park, M., Kang, T., Yun, J., Hwang, S., & Choo, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.14396 · Cited by 11
NaTex: Seamless Texture Generation as Latent Color DiffusionPreprint
Lai, Z., Zhao, Y., Zhao, Z., Yang, X., Huang, X., Huang, J., Yue, X., & Guo, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.16317 · Cited by 11
Du, S., Guo, J., Li, B., Cui, S., Xu, Z., Luo, Y., Wei, Y., Gai, K., Wang, X., Wu, K., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.23386 · Cited by 11
Gao, J., Liu, Y., Yang, B., Feng, J., & Fu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.06940 · Cited by 11
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational AutoencoderPreprint
Shi, M., Wang, H., Zhang, B., Zheng, W., Zeng, B., Yuan, Z., Wu, X., Zhang, Y., Yang, H., Wang, X., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.11749 · Cited by 11
Improving Reconstruction of Representation AutoencoderPreprint
Liu, S., Qin, C., Yin, H., Yan, Q., Duan, Z.-P., Li, C., Lyu, J., Guo, C.-L., & Li, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.08620 · Cited by 11
Beyond Pixel Histories: World Models with Persistent 3D StatePreprint
Garcin, S., Walker, T., McDonagh, S., Pearce, T., Bilen, H., He, T., Wang, K., & Bian, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.03482 · Cited by 11
Understanding Asynchronous Inference Methods for Vision-Language-Action ModelsPreprint
Agouzoul, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.08168 · Cited by 11
ERNIE-Image Technical ReportPreprint
Liu, J., Feng, Z., Zou, P., Qian, Z., Zhu, T., Xia, J., Dong, Y., Lin, Y., Xiong, H., Chen, A., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.25347 · Cited by 11
GPIC: A Giant Permissive Image Corpus for Visual GenerationPreprint
Chandrasegaran, K., Sargent, K., Agarwal, S., Jang, M., Poli, M., Niebles, J. C., Johnson, J., Wu, J., & Fei-Fei, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.30341 · Cited by 11
Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought SupervisionPreprint
Li, H., Li, G., Feng, Y., Zhao, C., Wang, Z., Li, Y., Wei, Q., Bao, S., Shen, H., Zhao, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.30552 · Cited by 11
Liang, J. E. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3396401 · Cited by 10
2D/3D Image morphing technology from traditional to modern: A survey
Lin, J., Gu, Y., Du, G., Qu, G., Chen, X., Zhang, Y., Gao, S., Liu, Z., & Gunasekaran, N. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102913 · Cited by 10
RoIPoly: Vectorized building outline extraction using vertex and logit embeddings
Jiao, W., Cheng, H., George Vosselman, A., & Persello, C. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.03.030 · Cited by 10
Unraveling the potential of diffusion models in small-molecule generation
Zhang, P. C., Baker, D., Song, M., & Bi, J. (2025) · Drug Discovery Today · doi:10.1016/j.drudis.2025.104413 · Cited by 10
Lin, X., Xia, Y., Li, Y. G., Huang, Y., Liu, S., Zhang, J., & Gao, Y. Q. (2025) · Nature Communications · doi:10.1038/s41467-025-61323-x · Cited by 10
D4D: An RGBD Diffusion Model to Boost Monocular Depth Estimation
Papa, L., Russo, P., & Amerini, I. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3404256 · Cited by 10
Seo, M., Cho, Y., Sung, Y., Stone, P., Zhu, Y., & Kim, B. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128590 · Cited by 10
PVNet: Point-Voxel Interaction LiDAR Scene Upsampling via Diffusion Models
Cheng, X., Wu, L., Wang, Z., Hou, J., Wen, J., & Xu, Y. D. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3620666 · Cited by 10
InstaFormer++: Multi-Domain Instance-Aware Image-to-Image Translation with Transformer
Kim, S.-H., Park, J., Park, J., Ha, E., Jung, H., Lee, T., & Kim, S. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01866-y · Cited by 10
Making Visual Sense of Oracle Bones for You and Me
Qiao, R., Yang, L., Pang, K., & Zhang, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01203 · Cited by 10
Panorama Generation From NFoV Image Done Right
Zheng, D., Zhang, C., Wu, X.-M., Cao, L., Lv, C., Hu, J.-F., & Zheng, W. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02013 · Cited by 10
DX2CT: Diffusion Model for 3D CT Reconstruction from Bi or Mono-planar 2D X-ray(s)
Jeong, Y. S., Yoo, H. B., & Chun, I. Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888986 · Cited by 11
Sun, Y., Chen, Z., Zheng, H., Deng, W., Liu, J., Min, W., Elazab, A., Wan, X., Wang, C., & Ge, R. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3588138 · Cited by 10
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNNPreprint
Shuai, R. W., Widatalla, T., Huang, P., & Hie, B. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.13.637498 · Cited by 10
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
Bai, T., Bai, W., Chen, D., Wu, T., Li, M., & Ma, R. (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/cvpr52734.2025.00553 · Cited by 10
CacheQuant: Comprehensively Accelerated Diffusion Models
Liu, X., Li, Z., & Gu, Q. (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/cvpr52734.2025.02167 · Cited by 10
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
Ren, J., Li, W., Wang, Z., Sun, H., Liu, B., Chen, H., Xu, J., Li, A., Zhang, S., Shao, B., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01687 · Cited by 10
Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models
Li, R., Li, R., Guo, S., & Zhang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73347-5_23 · Cited by 10
Prompt-to-Slate: Diffusion Models for Prompt-Conditioned Slate Generation
Tomasi, F., Fabbri, F., Carter, J., Kalomiris, E., Lalmas, M., & Dai, Z. (2025) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3705328.3748072 · Cited by 10
E.T. the Exceptional Trajectories: Text-to-Camera-Trajectory Generation with Character Awareness
Courant, R., Dufour, N., Wang, X., Christie, M., & Kalogeiton, V. S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73235-5_26 · Cited by 10
MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation
Sun, M., Wang, W., Qiao, Y., Sun, J., Qin, Z., Guo, L., Zhu, X., & Liu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680889 · Cited by 10
Hyper-3DG: Text-to-3D Gaussian Generation via HypergraphPreprint
Di, D., Yang, J., Luo, C., Xue, Z., Chen, W. R., Yang, X., & Gao, Y. (2024) · Research Square · doi:10.21203/rs.3.rs-4084374/v1 · Cited by 12
Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation
Zhang, Z., Liao, J., Meng, X., Qin, L., & Wang, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754869 · Cited by 10
LN3Diff++: Scalable L atent N eural Fields D iffusion for Speedy 3D Generation
Lan, Y., Hong, F., Zhou, S., Yang, S., Meng, X., Chen, Y., Lyu, Z., Dai, B., Pan, X., & Loy, C. C. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3633073 · Cited by 10
LazyMAR: Accelerating Masked Autoregressive Models Via Feature Caching
Yan, F., Wei, Q., Tang, J., Li, J., Wang, Y., Hu, X., Li, H., & Zhang, L. Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01443 · Cited by 10
Accelerating Diffusion Transformer via Gradient-Optimized Cache
Qiu, J., Liu, L., Wang, S., Lu, J., Chen, K., & Hao, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01636 · Cited by 10
Imperceptible Protection Against Style Imitation From Diffusion Models
Ahn, N., Ahn, W., Yoo, K., Kim, D., & Nam, S.-H. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3660109 · Cited by 10
Mücke, N. T., & Sanderse, B. (2026) · Computers & Fluids · doi:10.1016/j.compfluid.2026.107098 · Cited by 12
Sora as a World Model? A Complete Survey on Text-to-Video Generation
Puspitasari, F. D., Zhang, C., Cho, J., Haider, A., Eman, N. U., Amin, O., Mankowski, A., Umair, M., Zheng, J., Zheng, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.05131 · Cited by 10
Esteves, C., Suhail, M., & Makadia, A. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01596 · Cited by 10
When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization
Ramanujan, V., Tirumala, K., Aghajanyan, A., Zettlemoyer, L., & Farhadi, A. (2025) · neural information processing systems · doi:10.52202/085713-4178 · Cited by 10
MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows
Ma, G., Yao, J., Ning, Z., Jiang, Y., Xiong, L., Xie, L., & Zhu, P. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462227 · Cited by 10
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Wu, Y., Chen, J., Zhang, Z., Xie, E., Yu, J., Chen, J., Hu, J., Lu, Y., Han, S., & Cai, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01676 · Cited by 10
IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
Chen, Y., Gu, K., Wen, Y., Zhao, Y., Wang, T., & Nie, L. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11697087 · Cited by 10
Efficient Input-Level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
Zhai, S., Li, J., Liu, Y., Chen, H., Tian, Z., Qu, W., Shen, Q., Jia, R., Dong, Y., & Zhang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01409 · Cited by 10
X-Fusion: Introducing New Modality to Frozen Large Language Models
Mo, S., NGUYEN, T. Q., Huang, X., Iyer, S., Li, Y., Liu, Y., Tandon, A., Shechtman, E., Singh, K. K., Lee, Y. J., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00029 · Cited by 10
JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers
Byung-Ki, K., Dai, Q., Lee, H., Luo, C., & Oh, T.-H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02343 · Cited by 10
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
Gao, H., Tang, B., Song, Y., Fang, G., He, Z., Yang, J., & Shou, M. Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_25 · Cited by 10
Just-Dub-It: Video dubbing via Joint Audio-Visual Diffusion
Chen, A., korem, N. K., Halperin, T., Yosef, M. B., Jelerčič, U., Bibi, O., Patashnik, O., & Cohen‐Or, D. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811061 · Cited by 10
Xu, T.-X., Wang, Z., Wang, G., Hu, L., Zhang, Z., Zhang, P., Zhang, B., & Zhang, S. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811088 · Cited by 10
Wu, H., Wu, X., Li, C., Zhang, Z., Chen, C., Liu, X., Zhai, G., & Lin, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680939 · Cited by 10
Liu, X., Li, Z., Jiang, M., Chen, M., Li, J., & Gu, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755472 · Cited by 10
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
