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 1,401–1,500 of 3,684
Discrete Diffusion for Single-Cell Gene Expression ModelingPreprint
Bhattacharya, S., Gensbigler, C., Karim, S., & Lees, J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.19.705033 · Cited by 4
Pan-cancer virtual spatial transcriptomics from routine histology with PhoenixPreprint
Tran, M., Gindra, R. H., Putze, P., Senbai, 康. K., Palla, G., Šket, T., Falcomatà, C., Wang, C., Guo, R., Boxberg, M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.25.720812 · Cited by 4
HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images
Qin, Z., Zhang, Y., Liu, Y., & Campbell, D. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00386 · Cited by 4
VegeDiff: Latent Diffusion Model for Geospatial Vegetation Forecasting
Zhao, S., Chen, H., Zhang, X., Xiao, P., & Bai, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3564317 · Cited by 4
ConceptCraft: One-Shot Personalized Text-to-Image Generation via Object-Background Disentanglement
Chen, H., Zuo, Z., Zhao, L., Li, J., & Yang, J. J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3596242 · Cited by 4
Neural Shrödinger bridge matching for pansharpening
Cao, Z., Wu, X., Deng, L.-J., & Vivone, G. (2025) · Inverse Problems and Imaging · doi:10.3934/ipi.2025039 · Cited by 4
PiMMNet: Introducing Multi-Modal Precipitation Nowcasting via a Physics-informed Perspective
Yu, D., Du, W., Lin, K., Li, X., Ye, Y., Luo, C., & Chen, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755436 · Cited by 4
Chen, X., Wang, S., & Yao, L. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761076 · Cited by 4
DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model
Zhang, W., Lu, H., Ning, M., Huang, X., Wang, W., Huang, K., & Wang, Q. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763913 · Cited by 4
Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers
Sun, Y., Xu, Z., Zhou, H., Guan, J., Yang, Q., Wang, K., Liang, B., Li, Y., Feng, H., Wang, J., et al. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02752-z · Cited by 4
MixFusion: A Patch-Level Parallel Serving System for Mixed-Resolution Diffusion Models
Sun, D., Zhao, Z., & Wang, Y. (2026) · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming · doi:10.1145/3774934.3786420 · Cited by 4
Video Diffusion Models: A Survey
Melnik, A., Ljubljanac, M., Lu, C., Yan, Q., Ren, W., & Ritter, H. (2024) · arXiv · doi:10.48550/arxiv.2405.03150 · Cited by 4
TaQ-DiT: Time-Aware Quantization for Diffusion Transformers
Liu, X., Shi, H., Xu, Y., & Wang, Z. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3652275 · Cited by 4
PDT: Point Distribution Transformation with Diffusion Models
Wang, J., Lin, C. C., Liu, Y., Xu, R., Dou, Z., Long, X., Guo, H., Komura, T., Wang, W., & Li, X. S. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730717 · Cited by 4
LayerFlow: A Unified Model for Layer-aware Video Generation
Ji, S., Luo, H., Chen, X., Tu, Y., Wang, Y., & Zhao, H. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730662 · Cited by 4
CAFA: A Controllable Automatic Foley Artist
Benita, R., Finkelson, M., Halperin, T., Sterkin, G., & Adi, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01477 · Cited by 4
Feng, Z., Yan, B., Zhao, L., Shen, X., Zhao, R., Wang, W., & Zhang, F. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2026.136186 · Cited by 4
UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention
Zhang, Y., & Tai, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_12 · Cited by 4
Wu, Q., Yu, Y., Kong, C., Liu, Z., Wan, J. X., Li, H., Kot, A. C., & Chan, A. B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01034 · Cited by 4
Generating synthetic multi-national longitudinal cohorts for clinically grounded HIV research
Liang, Z. J., Li, Z., Jackson, N. J., Guo, K. H., Caro-Vega, Y. N., Moreira, R. I., Paredes, F., Bernadin, J., Varela, D., César, C., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-74492-0 · Cited by 4
Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks
Li, J., Cai, H., Dong, M., Pu, M., You, S., Wang, F., & Huang, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37520-9_4 · Cited by 4
Silhouette-Based Gait Foundation Model
Ye, D., Fan, C., Narayan, K., Wu, B., Luo, C., Li, J., & Patel, V. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_25 · Cited by 4
Ding, C., & Bhowmik, R. T. (2025) · Journal of the Society for Information Display · doi:10.1002/jsid.2111 · Cited by 4
Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
Zhang, Y., Wang, Z., Zheng, W., Zhu, Z. D., Zhou, J., & Lu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37718-0_7 · Cited by 4
CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs
Hagnberger, J., Musekamp, D., & Niepert, M. (2025) · neural information processing systems · doi:10.52202/085713-5360 · Cited by 4
X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents
Song, G., Xu, H., Zhao, X., Xie, Y. X., Gu, T., Li, Z., Zhang, C., & Luo, L. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763952 · Cited by 4
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Petsangourakis, G., Sgouropoulos, C., Psomas, B., Giannakopoulos, T., Sfikas, G., & Kakogeorgiou, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_25 · Cited by 4
MaskAttn-SDXL: Controllable Region-Level Text-to-Image Generation
Chang, Y., Chen, J., Cheng, A., & Bogdan, P. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729312 · Cited by 4
OmniX: From Unified Panoramic Generation and Perception To Graphics-Ready 3D Scenes
Huang, Y., Yu, J., Zhou, Y., Wang, J., Wang, X., Wan, P., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_30 · Cited by 4
Liu, Y., Zhang, M., Wang, Y., Li, H., Zheng, D., Zhang, W., Lu, C., & Yang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_7 · Cited by 4
TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers
Li, B., Yang, M., Tan, Z., Zhang, J., & Li, H. X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_33 · Cited by 4
Tuning-Free Visual Effect Transfer Across Videos
Jones, M., Abdal, R., Patashnik, O., Salakhutdinov, R., Tulyakov, S., Zhu, J.-Y., & Wang, K.-C. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_37 · Cited by 4
Computation-bandwidth-memory trade-offs: a unified paradigm for AI infrastructure
Fan, Y., Weng, Q., & Li, X. (2026) · Vicinagearth. · doi:10.1007/s44336-026-00041-4 · Cited by 4
EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos
Zhang, T., Xia, S., Wang, Y., & Jin, Q. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696502 · Cited by 4
A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
Elmoghany, M., Rossi, R., Yoon, S., Mukherjee, S., Bakr, E. M., Mathur, P., Wu, G., Lai, V. D., Lipka, N., Zhang, R., et al. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00731 · Cited by 4
StyleStream: Real-Time Zero-Shot Voice Style Conversion
Liu, Y., Lee, N., & Anumanchipalli, G. K. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-404 · Cited by 4
Turbulence generation and data assimilation in wall-bounded flows with a latent diffusion model
Steinbrenner, F., Turan, B., Teng, H., & Xiao, H. (2026) · Journal of Fluid Mechanics · doi:10.1017/jfm.2026.12069 · Cited by 4
A$$^2$$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks
Zheng, H., Li, G., Zhao, B., Luo, S., Jiang, H., Zhai, G., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_38 · Cited by 4
LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory
Zhen, D., Zheng, X., Zhang, R., Jiang, Z., Yan, Y., & Hu, X. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835846 · Cited by 4
AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
Yin, X., Xu, C., Zhou, H., Wei, B., & Cai, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37517-9_23 · Cited by 4
$$R_{\text {dm}}$$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation
Fan, L., Sun, P., Wen, T., Lu, S., & Song, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37035-8_23 · Cited by 4
Generative Refinement Networks for Visual Synthesis
Han, J., Liu, J., Wang, J., Peng, B., & Yuan, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_31 · Cited by 4
Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
Zhao, J., Wang, Z., Liao, Y., Zhang, C., & Ye, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792489 · Cited by 4
BeamCKMDiff: Beam-Aware Channel Knowledge Map Construction via Diffusion Transformer
Zhao, L., Wang, Y., Wang, X., Fei, Z., & Zeng, Y. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571730 · Cited by 4
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
Fu, X., Li, J., Hu, Y., Wang, Y., So, H. K.-H., Dai, J., Chu, X., & Han, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_25 · Cited by 4
EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation
Hong, D., Guo, Y., Chen, W., Liu, X., Zou, Z., Mao, Z., & Zhang, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.48550/arxiv.2607.10165 · Cited by 4
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
Cheng, Z., Zhang, X., Di, D., Fan, L., Ma, B., Li, H., & Yang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37461-5_34 · Cited by 4
ReferevErything: Towards Segmenting Everything we can Speak of in Videos
Bagchi, A., Bao, Z., Wang, Y.-X., Tokmakov, P., & Hebert, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02156 · Cited by 4
Lu, G., Du, Y., Tang, Y., Sun, Z., Qi, Y., Qi, Y., Wang, T., Ma, L., & Zou, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01416 · Cited by 4
SAFER: Sharpness Aware Layer-Selective Finetuning for Enhanced Robustness in Vision Transformers
Gopal, B., Yang, H., Horton, M., & Chen, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00381 · Cited by 4
DPUSegDiff: A Dual-Path U-Net Segmentation Diffusion model for medical image segmentation
Fan, Y., Song, J., Lu, Y., Fu, X., Huang, X., & Yuan, L. (2025) · Electronic Research Archive · doi:10.3934/era.2025129 · Cited by 4
Generating 3D-Consistent Videos from Unposed Internet Photos
Chou, G., Zhang, K., Bi, S., Tan, H., Xu, Z., Luan, F., Hariharan, B., & Snavely, N. (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/cvpr52734.2025.02601 · Cited by 4
DiffCamera: Arbitrary Refocusing on Images
Wang, Y., Chen, X., Xu, X., Liu, Y., & Zhao, H. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763827 · Cited by 4
Peng, M., Yao, R., Guo, X., & Ma, J. (2026) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv66570.2026.11623929 · Cited by 5
Rethinking Metrics and Diffusion Architecture for 3D Point Cloud Generation
Bastico, M., Ryckelynck, D., Corté, L., Tillier, Y., & Decencière, É. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00133 · Cited by 4
PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-Free Paradigm
Chang, T., Chen, X., Wei, Z., Zhang, X. H., Chen, Q., Luo, W., Song, P., & Yang, X. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3633891 · Cited by 4
Chen, H., Sun, D., Ma, C., Wang, S., Zhang, K., Wang, Z., & Wang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01657 · Cited by 4
Messina, F., Ronchini, F., Comanducci, L., Bestagini, P., & Antonacci, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463809 · Cited by 4
Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
Zheng, Y., Ren, Y., Xia, X., Xiao, X., & Xie, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01734 · Cited by 4
ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
Lai, Y., Liu, B., Guan, X., Zhao, Q., Li, H., & Hong, S. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840884 · Cited by 4
Early Estimation of Language to Latent Alignment in Diffusion Models
Ramos, V., Cohen, R., Szpektor, I., & Magalhães, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_36 · Cited by 4
MultiCOIN: Multi‐Modal COntrollable INbetweening
Tanveer, M., Zhou, Y., Niklaus, S., Amiri, A. M., Zhang, H., Singh, K. K., & Zhao, N. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70362 · Cited by 4
SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution
Im, J., & Nam, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460886 · Cited by 4
EnerBridge-DPO: Energy-Aware Markov Bridge Inverse Folding for Protein Sequence Design
Rong, D., Lu, H., Zhang, X., Zheng, W., Zhang, F., Zheng, S., & Liu, N. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c01697 · Cited by 4
Zhang, Y., Peng, D., Guo, Z., Zhang, Z., Yang, X., Sun, T., Sun, S., Zhang, Y., Li, Y., Zhao, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_22 · Cited by 4
Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
Chang, Y., Zhang, Y., Fang, Z., Wu, Y. N., Bisk, Y., & Gao, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73021-4_25 · Cited by 4
LoopAnimate: Loopable Salient Object Animation
Wang, F., Liu, P., Hu, H., Meng, D., Su, J., Xu, J., Zhang, Y., Ren, X., & Zhang, Z. (2024) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3696409.3700181 · Cited by 4
Forecasting when to forecast: Accelerating diffusion models with confidence-gated taylor
Guan, X., Jiang, L., Chen, H., Zhang, X., Yan, J., Wang, G., Liu, Y., Zhang, Z., & Wu, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114635 · Cited by 4
Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos
Zhao, Z., Song, S., Chen, T., Chen, Z., Sadiq, S. W., & Luo, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758257 · Cited by 4
Transition Matching: Scalable and Flexible Generative Modeling
Shaul, N., Singer, U., Gat, I., & Lipman, Y. (2025) · neural information processing systems · doi:10.52202/085713-4144 · Cited by 4
UniRes: Universal Image Restoration for Complex Degradations
Zhou, M., Ye, K., Delbracio, M., Milanfar, P., Patel, V. M., & Talebi, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01230 · Cited by 5
Understanding Flatness in Generative Models: Its Role and Benefits
Lee, T., Seo, K., Yoo, J., & Yoon, S. W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00467 · Cited by 4
Liu, Y., Zhang, Z., Ma-bao, B., Duojie, R., Cai, Y., Yu, Y., Wang, X. R., Gao, F., Huang, C., & Tashi, N. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463471 · Cited by 4
Synthetic Data for Model SelectionPreprint
Shoshan, A., Bhonker, N., Kviatkovsky, I., Fintz, M., & Medioni, G. G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.00717 · Cited by 4
U-DiT TTS: U-Diffusion Vision Transformer for Text-to-SpeechPreprint
Jing, X., Chang, Y., Yang, Z., Xie, J., Triantafyllopoulos, A., & Schuller, B. W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.13195 · Cited by 4
Zheng, H., Wang, Z., Yuan, J., Ning, G., He, P., You, Q., Yang, H., & Zhou, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.06389 · Cited by 4
Assessing Robustness via Score-Based Adversarial Image GenerationPreprint
Kollovieh, M., Gosch, L., Scholten, Y., Lienen, M., & Günnemann, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.04285 · Cited by 4
Exploring the Potentials and Challenges of Deep Generative Models in Product Design ConceptionPreprint
Mueller, P., & Mikelsons, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.11104 · Cited by 4
Scaling Particle Collision Data AnalysisPreprint
Wu, H., Chi, P., Zhu, Y., Liu, L., Hu, S., Wang, Y., Zhou, C., Wang, Q., Xin, Y., Liu, B. X., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.00129 · Cited by 4
Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion TransformerPreprint
Davies, T., Huang, Y., Liu, Y., Chen, X., Liu, H., & Hu, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.11865 · Cited by 4
Ultra-Resolution Adaptation with EasePreprint
Yu, R., Liu, S., Tan, Z., & Wang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.16322 · Cited by 4
TEXTRIX: Latent Attribute Grid for Native Texture Generation and BeyondPreprint
Zeng, Y., Bao, Y., Qian, J., Wu, S., Lin, Y., Zhu, H., Li, B., Zhang, F., Cao, X., & Yao, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.02993 · Cited by 4
Applying generative neural networks for fast simulations of the ALICE (CERN) experimentPreprint
Wojnar, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.16704 · Cited by 4
Wang, H., Zhang, G., Zhang, X., Chen, Z., Xu, H., Kwark, D. H., & Tu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.09550 · Cited by 4
UIKA: Fast Universal Head Avatar from Pose-Free ImagesPreprint
Wu, Z., Zhou, B., Hu, L., Liu, H., Sun, Y., Wang, X., Cao, X., Shen, Y., & Zhu, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.07603 · Cited by 4
Hu, D., Gupta, A., Gabidolla, M., Sahni, A., Coskun, H., Li, Y., Idelbayev, Y., Mahmood, A., Lebedev, A., Lahiri, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.08303 · Cited by 4
CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward FeedbackPreprint
Ge, W., Shen, G., Feng, J., Wang, L., Lu, H., Tian, X., Tao, X., & Chen, Y.-C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.16214 · Cited by 4
VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual DocumentsPreprint
Yi, H., Yang, Y., Wang, Y., Li, T., Guan, Z., Zong, T., Chen, J., Bao, C., Yang, T., Jin, H., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.00122 · Cited by 4
Zou, C., Li, C., Li, Y., Li, P., Wu, J., He, X., Liu, S., Zhong, Z., Huang, K., & Zhang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.05449 · Cited by 4
Untwisting RoPE: Frequency Control for Shared Attention in DiTsPreprint
Mikaeili, A., Patashnik, O., Tagliasacchi, A., Cohen‐Or, D., & Amiri, A. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.05013 · Cited by 4
Physically Grounded Generative Modeling of All-Atom Biomolecular DynamicsPreprint
Feng, B., Zhang, J., Zhang, X., He, C., Zhang, M., Barth, P., Li, Y., & Li, Y. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.15.705956 · Cited by 4
Adapting VACE for Real-Time Autoregressive Video DiffusionPreprint
Fosdick, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.14381 · Cited by 4
TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion AccelerationPreprint
Zhu, H., Huang, T., Wang, X., Zhao, T., Wang, J., Chen, W., Peng, X., Chen, F., Jun-hai Yong, A., & Wang, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.03792 · Cited by 5
ConTSG-Bench: A Unified Benchmark for Conditional Time Series GenerationPreprint
Lan, S., Gu, S., Xiong, Z., & Ren, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.04767 · Cited by 4
FlashMotion: Few-Step Controllable Video Generation with Trajectory GuidancePreprint
Li, Q., Xing, Z., Wang, R., Cao, H., Dai, Q., Dong, D., & Wu, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.12146 · Cited by 4
IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation ScenariosPreprint
Li, X., Sheng, L., Zhao, Y., Sun, Z., Zhang, Z., Wei, J., & He, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.26154 · Cited by 4
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in SimulationPreprint
Zhu, Y., Wang, Z., Yang, J., Xie, J., Jingyi Yu, A., Gu, J., & Wang, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.06311 · Cited by 4
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video GenerationPreprint
Jin, S., Kim, Y., Park, S., & Ye, J. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.12938 · Cited by 4
RiT: Vanilla Diffusion Transformers Suffice in Representation SpacePreprint
Zhang, L., Ning, M., & Agrawal, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.21981 · Cited by 4
On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow MatchingPreprint
Rashed, M., Madeira, D. F. V., Gholami, B., Guerbuez, C., Yang, Y., & Thuerey, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.02179 · 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
