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 1,001–1,100 of 3,684
Learning 4D Embodied World Models
Zhen, H., Sun, Q., Zhang, H., Li, J., Zhou, S., Du, Y., & Gan, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00507 · Cited by 8
Diagnosing Necrotizing Enterocolitis via Fine-Grained Visual Classification
Yung, K.-W., Sivaraj, J., Coppi, P. D., Stoyanov, D. V., Loukogeorgakis, S., & Mazomenos, E. B. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2024.3409642 · Cited by 8
Gao, X. Y., & Liu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681380 · Cited by 8
Lv, L., Pei, P., Ren, P., Wang, H., & Wang, G. (2025) · Energies · doi:10.3390/en18051191 · Cited by 8
Liu, X., Li, H., Qiao, Z., Huang, Y., Liu, X., Zhang, J., Qian, Z., Zhen, X., & Zhang, B. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02426-2 · Cited by 8
Conditional Protein Structure Generation with Protpardelle-1cPreprint
Lu, T., Shuai, R. W., Kouba, P., Li, Z., Chen, Y., Shirali, A., Kim, J., & Huang, P. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.18.670959 · Cited by 8
Geng, X., Li, Y., Ma, Z., Lu, Z., & Miao, Q. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111960 · Cited by 8
MatSwap: Light‐aware material transfers in images
Lopes, I., Deschaintre, V., Hold-Geoffroy, Y., & de Charette, R. (2025) · Computer Graphics Forum · doi:10.1111/cgf.70168 · Cited by 8
HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation
Biagini, D., Navab, N., & Farshad, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05114-1_30 · Cited by 8
FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation
Jiang, Y., Chen, Z., Ju, Z., Li, C., Dou, W., & Zhu, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755170 · Cited by 8
Elbatel, M., Kamnitsas, K., & Li, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72378-0_61 · Cited by 8
Fashion-VDM: Video Diffusion Model for Virtual Try-On
Karras, J., Li, Y., Liu, N., Zhu, L., Yoo, I., Lugmayr, A., Lee, C., & Kemelmacher-Shlizerman, I. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687623 · Cited by 9
DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation
Cao, Z., Hong, F., Wu, T., Pan, L., & Liu, Z. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3528247 · Cited by 9
Bayesian Flow Network Framework for Chemistry Tasks
Tao, N., & Abe, M. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01792 · Cited by 8
Leng, Z., Birdal, T., Liang, X., & Tombari, F. (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/cvpr52733.2024.01862 · Cited by 8
SF-Speech: Straightened Flow for Zero-Shot Voice Clone
Li, X., Shang, Z., Hua, H., Shi, P., Yang, C., Wang, L., & Zhang, P. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3557242 · Cited by 8
ICDM: Interference Cancellation Diffusion Models for Wireless Semantic Communications
Wu, T., Chen, Z., He, D., Yang, F., Tao, M., Xu, X., Zhang, W., & Zhang, P. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3643396 · Cited by 8
Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
Ma, Q., Ning, X., Liu, D., Niu, L., & Zhang, L. (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/cvpr52734.2025.02168 · Cited by 8
FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
Chen, Z. W., Gao, Q., Li, Z. J., Zhang, J., Zhang, Y., Zhao, J., & Shan, H. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3698474 · Cited by 8
Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
Kim, K., Lee, H., Park, J., Kim, S., Lee, K., Kim, S., & Yoo, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72943-0_9 · Cited by 8
Karaarslan, E., & Aydin, Ö. F. (2024) · doi:10.36227/techrxiv.170862194.43871446/v1 · Cited by 8
A Survey on Text-Driven 360° Panorama Generation
Wang, H., Xiang, X., Xia, W., & Xue, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3628738 · Cited by 8
DynVFX: Augmenting Real Videos with Dynamic Content
Yatim, D., Fridman, R., Bar-Tal, O., & Dekel, T. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3764008 · Cited by 8
Auto-Regressively Generating Multi-View Consistent Images
Hu, J., Yang, Y., Liu, J., Wu, J., Zhao, C., & Lu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00246 · Cited by 8
Rectified Diffusion Guidance for Conditional Generation
Xia, M., Xue, N., Shen, Y., Yi, R., Gong, T., & Liu, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01248 · Cited by 8
Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
Fortes, A., Wei, T., Zhou, S., & Pan, X. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763906 · Cited by 8
Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion
Ma, Y., Chen, J., Di, D., Xie, Q., Fan, L., Chen, W., Zhao, N., & Yang, X. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3794855 · Cited by 8
MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation
Chen, J., Zhu, L., Hu, Z., Qian, S., Chen, Y., Wang, X., & Lee, G. H. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01035 · Cited by 8
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
Li, B., Wang, J., Li, Y., Hu, Z., Qi, L., Dong, J., Wang, R., Qiu, H., Qin, Z., & Zhang, T. (2026) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp63933.2026.00112 · Cited by 8
GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
Paischer, F., Galletti, G., Hornsby, W. A., Setinek, P., Zanisi, L., Carey, N., Pamela, S. J. P., & Brandstetter, J. (2025) · neural information processing systems · doi:10.52202/085713-1647 · Cited by 8
FlexSED: Towards Open-Vocabulary Sound Event Detection
Hai, J., Wang, H., Guo, W., & Elhilali, M. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230975 · Cited by 8
Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
Chen, T., Ding, Z., Li, A., Zhang, C., Xiao, Z., Wang, Y., & Jin, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37627-5_27 · Cited by 8
Autoregressive Denoising Score Matching Is a Good Video Anomaly Detector
Zhang, H., Cao, C., Lv, Q., Min, L., & Yanning, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01121 · Cited by 8
SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
Zhao, Q., Zheng, G., Yang, T., Zhu, R., Leng, X., Gould, S. J., & Zheng, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37577-3_37 · Cited by 8
CollabVLA: Self-Reflective Vision–Language–Action Model Dreaming Together with Human
Sun, N., Li, Y., Wang, C., Mao, B., Liu, H., Yao, J., Li, K., Liu, J., Zhang, Y., Zhang, G., et al. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11697568 · Cited by 8
One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control
Mi, Z., Wang, Y., & Xu, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_3 · Cited by 8
Zhang, H., Farzanullah, M., Ghassemi, M., Sediq, A. B., Afana, A., & Erol‐Kantarci, M. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3648785 · Cited by 8
Li, G., & Chu, Z. (2026) · Multimedia Systems · doi:10.1007/s00530-025-02203-8 · Cited by 8
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-Centric Image Editing
Zhang, H., Liu, J., Liu, Z., Niu, L., Meng, F., Wu, Z., & Jiang, Y.-G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_26 · Cited by 8
Reconstruction by Generation: 3D Multi-object Scene Reconstruction from Sparse Observations
Zadaianchuk, A., Barcellona, L., Schuenemann, L., Gumbsch, C., Wang, Z., Irshad, M. Z., Despinoy, F., Aljundi, R., Gavves, E., & Zakharov, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_28 · Cited by 8
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
Zhou, K., Chen, Y., Zhan, F., Hua, H., Chen, G., Chang, X., Qu, A., Du, Y., Liu, Z., Liang, P. P., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_8 · Cited by 8
SPPO: Making Million-Token LLM Training Practical on Modest GPU Clusters
Chen, Q. J., Li, S., Gao, W., Sun, P., Wen, Y., & Zhang, T. (2026) · International Conference on Supercomputing · doi:10.1145/3797905.3800537 · Cited by 8
MV-S2V: Multi-View Subject-Consistent Video Generation
Song, Z., Gong, X., Liu, B., & Zhao, Z. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811131 · Cited by 8
DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow
Deng, K., Guo, Y.-C., Sun, J., Zou, Z., Li, Y., Cai, X., Cao, Y., Liu, Y., & Liang, D. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00130 · Cited by 8
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Yang, S., Lan, Y., Chen, H., & Pan, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01407 · Cited by 8
CharaConsist: Fine-Grained Consistent Character Generation
Wang, M., Ding, H., Peng, J., Zhao, Y., Chen, Y., & Wei, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01490 · Cited by 8
Ji, Y., Saratchandran, H., Moghadam, P., & Lucey, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02146 · Cited by 8
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Daras, G., Nie, W., Kreis, K., Dimakis, A. G., Mardani, M., Kovachki, N., & Vahdat, A. (2024) · neural information processing systems · doi:10.52202/079017-3207 · Cited by 8
CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
Phung, Q., Mai, L., Heilbron, F. C., Liu, F., Huang, J., & Ham, C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00258 · Cited by 8
Revisiting the Evaluation of Image Synthesis with GANs
Yang, M., Yang, C., Zhang, Y., Bai, Q., Shen, Y., & Dai, B. (2023) · neural information processing systems · doi:10.52202/075280-0417 · Cited by 8
Chen, G., Zhao, X., Zhou, Y., Qu, X., Chen, T., & Cheng, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01645 · Cited by 8
Scaling up Occupancy-Centric Driving Scene Generation: Dataset and Method
Li, B. R., Jin, X., Zhu, H., Liu, H., Li, R., Guo, J., Cai, K., Ch, M., Jin, Y., Zhao, H., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3696126 · Cited by 8
InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
Elata, N., Chung, H., Ye, J. C., Michaeli, T., & Elad, M. (2025) · neural information processing systems · doi:10.52202/085713-1203 · Cited by 8
DiT-Head: High Resolution Talking Head Synthesis Using Diffusion Transformers
Mir, A., Alonso, E., & Mondragón, E. (2024) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0012312200003636 · Cited by 8
DreamRelation: Bridging Customization and Relation Generation
Shi, Q., Qi, L., Wu, J., Bai, J., Wang, J., Tong, Y., & Li, X. (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/cvpr52734.2025.01466 · Cited by 8
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Gu, J., Shen, Y., Zhai, S., Zhang, Y., Jaitly, N., & Susskind, J. (2024) · neural information processing systems · doi:10.52202/079017-0178 · Cited by 8
Masked Diffusion Models Are Fast Distribution LearnersPreprint
Lei, J., Wang, Q., Cheng, P., Ba, Z., Qin, Z., Wang, Z., Liu, Z., & Ren, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.11363 · Cited by 8
Mojito: Motion Trajectory and Intensity Control for Video GenerationPreprint
He, X., Wang, S., Yang, J., Wu, X., Wang, Y., Wang, K., Zheng, Z., Ruwase, O., Shen, Y., & Wang, X. E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.08948 · Cited by 8
Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion TransformersPreprint
Zheng, S., Chen, G., Zhou, Q., Lin, Y., He, L., Zou, C., Cai, P., Liu, J., & Zhang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.04188 · Cited by 8
Hao, J., Wang, P., Wang, H., Zhang, X., & Guo, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.10001 · Cited by 8
AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective GuidancePreprint
Chen, T., Zhang, Y., & Chatterjee, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.00352 · Cited by 8
Zhang, Z., Kang, Z., Zhao, R., Feng, Y., Jiang, B., Ji, H., & Liu, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.14048 · Cited by 8
Shi, Y., Guo, D., Zhao, T., Gao, F., Shi, L., Yu, C., Mo, Z., Xiao, Q., Peng, X., Liao, Q., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.28565 · Cited by 8
Spherical Flows for Sampling Categorical DataPreprint
Chemseddine, J., Kornhardt, G., & Steidl, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.05629 · Cited by 8
LpWM: A Case for Sparse Representations in World ModelsPreprint
Kuang, Y., Dagade, Y., Lidec, Q. L., Maes, L., Balestriero, R., & LeCun, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.22764 · Cited by 8
Wang, Y., Lin, Y., He, X., Zheng, H., Yan, K., Fan, L., Huang, Y., & Ding, X. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3538744 · Cited by 7
A Diffusion-TGAN Framework for Spatio-Temporal Speed Imputation and Trajectory Reconstruction
Qian, Y., Li, X., Zhang, J., Meng, X., Li, Y., Ding, H., & Wang, M. C. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3591211 · Cited by 7
Liu, J., Wu, J., Gao, X., Hu, J., Xiong, B., Liu, X., Zhao, C., Pei, H., Feng, H., Li, Y., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02474 · Cited by 7
Han, T., Chen, Z., Guo, S., Xu, W., Ouyang, W., & Bai, L. (2025) · Communications Earth & Environment · doi:10.1038/s43247-025-02903-z · Cited by 7
Zhong, R., Hu, B., Feng, Y., Liu, Z., Qin, Q., Wang, X. V., Wang, L., & Tan, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104119 · Cited by 7
Perceptual-Centric Image Super-Resolution using Heterogeneous Processors on Mobile Devices
Huang, K., Yin, X., Gu, T., & Gao, W. (2024) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3636534.3690698 · Cited by 7
Eidex, Z., Safari, M., Qiu, R. L. J., Yu, D. S., Shu, H. G., Mao, H. Z., & Yang, X. (2024) · Medical Physics · doi:10.1002/mp.17600 · Cited by 8
An Energy-Efficient POSIT Compute-in-Memory Macro for High-Accuracy AI Applications
Wang, Y., Yang, X., Qin, Y., Zhao, Z., Guo, R., Yue, Z., Han, H., Wei, S., Hu, Y., & Yin, S. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3532654 · Cited by 7
E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance
Huang, T., Cao, P., Yang, L., Liu, C., Hu, M., Liu, Z., & Song, Q. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3542180 · Cited by 7
WeiPipe: Weight Pipeline Parallelism for Communication-Effective Long-Context Large Model Training
Lin, J., Liu, Z., You, Y., Wang, J., Zhang, W., & Zhao, R. J. (2025) · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming · doi:10.1145/3710848.3710869 · Cited by 7
SEED4D: A Synthetic Ego-Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark
Kästingschäfer, M., Gieruc, T., Bernhard, S., Campbell, D., Insafutdinov, E., Najafli, E., & Brox, T. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00753 · Cited by 7
Conditional generative AI for high-fidelity synthesis of hydrating cementitious microstructures
Liang, M., Feng, K., Xie, J., Wei, Y., Contera, S., Schlangen, E., & Šavija, B. (2025) · Materials & Design · doi:10.1016/j.matdes.2025.114251 · Cited by 7
StyDiff: a refined style transfer method based on diffusion models
Sun, Y., & Meng, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-17899-x · Cited by 7
Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data
Chen, Q., Zhou, X., Liu, C. P., Chen, H., Li, W., Jiang, Z., Huang, Z., Zhao, Y. J., Yu, D., He, J., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02225 · Cited by 7
DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
Wang, S., Sun, G., Ma, F., Hu, T., Qin, Q., Song, Y., Zhu, L., & Liang, J. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801623 · Cited by 9
Exploring Text-Guided Single Image Editing for Remote Sensing Images
Han, F., Si, L., Dong, H., Jiang, Z., Zhang, L., Chen, H., Liu, Y., & Du, B. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3584418 · Cited by 7
Constraint Decoupled Latent Diffusion for Protein Backmapping
Han, X., Sun, Y., Chen, K., Ren, Y., Liu, K., & Ye, Q. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01364 · Cited by 7
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
Son, S., Ryu, J., Lee, N., & Lee, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72855-6_22 · Cited by 7
Lee, B. H., Lim, S., & Chun, S. Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01733 · Cited by 7
Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction
Cartella, G., Cuculo, V., D’Amelio, A., Cornia, M., Boccignone, G., & Cucchiara, R. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01504 · Cited by 7
Cross-modality image synthesis from TOF-MRA to CTA using diffusion-based models
Koch, A., Aydin, O. U., Hilbert, A., Rieger, J., Tanioka, S., Ishida, F., & Frey, D. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103722 · Cited by 8
Wu, Y., Zhang, L., Yao, H., Du, J., Yan, K., Ding, S., Wu, Y., & Li, X. (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/cvpr52734.2025.01365 · Cited by 7
Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion
Dufour, N., Besnier, V., Kalogeiton, V. S., & Picard, D. (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/cvpr52733.2024.00599 · Cited by 7
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing
Dong, Z., & Zhang, S. Q. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00452 · Cited by 8
Monaco, S., Monaco, L., Apiletti, D., Cremonini, R., & Barbero, S. (2025) · Computers & Geosciences · doi:10.1016/j.cageo.2025.105992 · Cited by 7
Retracted: Exploring the Economic Feasibility of Advanced Air Mobility in the Early Stages
Guo, J., Chen, L., Li, L., Na, X., Vlacic, L., & Wang, F. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3422002 · Cited by 7
RetractedLearning to Generate Conditional Tri-Plane for 3D-Aware Expression Controllable Portrait Animation
Ki, T., Min, D., & Chae, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73232-4_27 · Cited by 7
LDM: Large tensorial SDF model for textured mesh generation
Xie, R., Huang, K., Luo, X., Chen, Y., Wang, L., Wang, Q., Ye, Q., Chen, W., Zheng, W., & Huo, Y. (2025) · Graphical Models · doi:10.1016/j.gmod.2025.101271 · Cited by 7
Learning to Drive from a World Model
Goff, M., Hogan, G., Hotz, G., Locmaria, A. D. P., Raczy, K., Schäfer, H., Shihadeh, A., Zhang, W., & Yousfi, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00184 · Cited by 7
Video is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation
Waseem, F., & Shahzad, M. S. (2025) · ACM Computing Surveys · doi:10.1145/3771724 · Cited by 7
TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers
Hwang, Y., Lee, H., & Kang, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228481 · Cited by 7
SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation
Kumar, S., Seetharaman, P., Salamon, J., Manocha, D., & Nieto, O. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230964 · Cited by 7
Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
Phunyaphibarn, P., Lee, P. Y., Kim, J., & Sung, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00388 · Cited by 7
DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion Model
Mao, R., Wu, H., Jia, Y., Nan, Z., Sun, Y., Zhou, S., Gündüz, D., & Niu, Z. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128518 · Cited by 7
Disentangled Clothed Avatar Generation with Layered Representation
Zhang, W., Yan, Y., Wu, S., Liao, M., & Yang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01054 · Cited by 7
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
