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 1,901–2,000 of 3,684
Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model AccelerationPreprint
Wei, Y., Diao, L., Chen, B., Cheng, S., Qian, Z., Yu, W., Xiao, N., Lin, W. T., & Du, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.12691 · Cited by 2
TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNetPreprint
Jeong, J., Lee, Y., Kwon, M., & Uh, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.04349 · Cited by 2
FlowLensing: Simulating Gravitational Lensing with Flow MatchingPreprint
Sayed, H., Reddy, P., Toomey, M. W., & Gleyzer, S. V. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.07878 · Cited by 2
Sortblock: Similarity-Aware Feature Reuse for Diffusion ModelPreprint
Chen, H., Zhang, X., Guan, X., Jiang, L., Wang, G., Chen, Z., & Liu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.00412 · Cited by 2
Populate-A-Scene: Affordance-Aware Human Video GenerationPreprint
Shan, M., He, Z., Ma, H., Juefei-Xu, F., Zhang, P., Hou, T., & Chuang, C.-Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.00334 · Cited by 2
SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video GenerationPreprint
Li, Z., Lyu, H., Shi, J., Zeng, Y., Fan, M., Zhang, H., & Liang, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.01960 · Cited by 2
Aquarius: A Family of Industry-Level Video Generation Models for Marketing ScenariosPreprint
Shi, H., Liang, J., Xie, R., Wu, X., Chen, C., & Liu, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.10584 · Cited by 2
Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via TransformersPreprint
Sherki, D., Oseledets, I. V., & Muravleva, E. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.01375 · Cited by 2
TweezeEdit: Consistent and Efficient Image Editing with Path RegularizationPreprint
Mao, J., Wang, K., Xiang, Y., & Chen, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.10498 · Cited by 2
Upcycling Text-to-Image Diffusion Models for Multi-Task CapabilitiesPreprint
Chavhan, R., Mehrotra, A., Chadwick, M., Ramos, A. G., Morreale, L., Noroozi, M., & Bhattacharya, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.11905 · Cited by 2
Thicker and Quicker: A Jumbo Token for Fast Plain Vision TransformersPreprint
Fuller, A., Yassin, Y., Kyrollos, D. G., Shelhamer, E., & Green, J. R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.15021 · Cited by 2
HandCraft: Dynamic Sign Generation for Synthetic Data AugmentationPreprint
Ríos, G. G., Bianco, P. D., Ronchetti, F., Quiroga, F., Stanchi, O., Ahón, S. P., & Hasperué, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.14345 · Cited by 2
Enhancing Reference-based Sketch Colorization via Separating Reference RepresentationsPreprint
Yan, D., Wang, X., Li, Z., Saito, S., Iwasawa, Y., Matsuo, Y., & Guo, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.17620 · Cited by 2
Scale-Wise VAR is Secretly Discrete DiffusionPreprint
Kumar, A., Nair, N. G., & Patel, V. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.22636 · Cited by 2
ENMA: Tokenwise Autoregression for Generative Neural PDE OperatorsPreprint
Koupaï, A. K., Boudec, L. L., Serrano, L., & Gallinari, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.06158 · Cited by 2
Rosso, H., & Mayo, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.23748 · Cited by 2
ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban GenerationPreprint
Guo, H., Shao, J., Chen, X., Tan, X., Miao, S., Shen, Y., & Liao, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.15221 · Cited by 2
Physics-Informed Neural Compression of High-Dimensional Plasma DataPreprint
Galletti, G., Gutenbrunner, G., Cranganore, S. S., Hornsby, W., Zanisi, L., Carey, N., Pamela, S. J. P., Brandstetter, J., & Paischer, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.04758 · Cited by 2
Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion TransformersPreprint
Zhang, J., Zhao, H., Wu, J., Sun, R., Zhao, X., & Deng, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.05605 · Cited by 2
Condition Errors Refinement in Autoregressive Image Generation with Diffusion LossPreprint
Zhou, Y., Li, H., & Shen, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.07022 · Cited by 2
VideoSketcher: Sequential Sketch Generation Using Video Model PriorsPreprint
Ren, H., Alaluf, Y., Bar-Tal, O., Schwing, A. G., Torralba, A. B., & Vinker, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.15819 · Cited by 2
De novo molecular structure elucidation from mass spectra via flow matchingPreprint
Mqawass, G., Le, T., Theis, F., & Clevert, D.-A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.19912 · Cited by 2
Factor Dimensionality and the Bias-Variance Tradeoff in Diffusion Portfolio ModelsPreprint
Bagchi, A., Tesfaye, M. H., & Shastri, O. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.10385 · Cited by 2
VideoMatGen: PBR Materials through Joint Generative ModelingPreprint
Hasselgren, J., Zeng, Z., Hašan, M., & Munkberg, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.16566 · Cited by 2
Fast Beam-Brainstorm: Few-Step Generative Site-Specific Beamforming with Flexible ProbingPreprint
Zhou, Z., Wang, Z., & Liu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.17622 · Cited by 2
Generative machine learning unlocks the first proteome-wide image of human cellsPreprint
Sun, H., Kahnert, K., Hansen, J. N., Leineweber, W. D., Li, M., Feng, W., Navarro, F. B., Axelsson, U., Ouyang, W., & Lundberg, E. K. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.31.715748 · Cited by 2
AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations ModelingPreprint
Mikuš, I., Muha, B., & Vlah, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.06475 · Cited by 2
Xue, Y., Liang, R., Zakharov, E., Bagautdinov, T., Cao, C., Nam, G., Saito, S., Pons-Moll, G., & Romero, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.20715 · Cited by 2
Wu, S., Li, X., Wang, Z., Li, Y., Cai, W., Su, Z., & Wang, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.24197 · Cited by 2
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion ModelsPreprint
Shen, Z., Huang, R., Liu, J., Zou, C., Cai, P., Zheng, S., Shi, Z., Feng, L., & Zhang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.26365 · Cited by 2
Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image DetectionPreprint
Zhou, S., Wu, S., Wei, J., Liu, K., Ran, R., Qin, C., & Yang, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.27875 · Cited by 2
Deep learning models for chemical perturbation prediction do not yet utilise drug molecular featuresPreprint
Bai, J., Prince, S., & Nitschke, G. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.13.724458 · Cited by 2
Zha, H., Ma, T., Yong, Y., Fu, H., Ma, R., Gao, W., Gong, R., Liu, X., Wang, W., & Chai, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.25550 · Cited by 2
Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid ObjectsPreprint
Kreber, J. U., Mack, L., & Stueckler, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.01950 · Cited by 2
TIDE: Task-Isolated Diffusion for Unified Video Editing and GenerationPreprint
Liu, Q., Yue, G., Yin, M., Zhang, L., Wu, Y., Wang, Y., Wang, Y., Yao, C., Chen, J., & Ma, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.08260 · Cited by 2
Transferring Contact, Not Just Motion: Compliant Grasping Across Dexterous HandsPreprint
Atar, S., Huang, Y., & Yip, M. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.15516 · Cited by 2
Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic ManipulationPreprint
Machado, B., Chapin, A., Dellandréa, E., & Chen, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.23420 · Cited by 2
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion ModelsPreprint
Domb, Y., Sackstein, H., & Solberg, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.23406 · Cited by 2
One Generator, Any Process: LLM-Conditioning for the LHCPreprint
Bahl, H., Plehn, T., Schiller, D., & Sivagnanalingam, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.23791 · Cited by 2
Variable-Length Generative Protein Design via Generalized Poisson FlowPreprint
Cheng, C., Ni, Z., Qu, Y., Chen, Y., Guo, R., Fan, J., & Liu, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.09039 · Cited by 2
Qu, Z., Wang, Z., Hancke, G. P., & Lau, R. W. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.24298 · Cited by 2
Optimizers for Diffusion Models: A Controlled BenchmarkPreprint
Bolatov, A., Shulgin, E., Li, D., Shtanchaev, A., Stich, S. U., Panov, M., Moulines, É., Richtárik, P., & Takáč, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.23055 · Cited by 2
From Scores to Samples: Elastic Forcing for Autoregressive Video GenerationPreprint
Zhang, C., Liu, Y., Shi, H., An, R., Li, H., Wu, Y., Cui, S., & Liu, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.35491 · Cited by 2
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot SystemPreprint
Wang, Z., Li, J.-N., Tang, Y., Yu, Y., Wu, B., Fang, M., Li, X., & Zhong, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.19600 · Cited by 2
DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
Song, Y., Liu, X., & Shou, M. Z. (2024) · arXiv · Cited by 1
“Their powerful capability to adapt to complex data distributions has led diffusion models to achieve remarkable success across several domains including image synthesis [18, 39, 49, 54, 57, 58, 64, 75, 89], image editing [5, 19, 24, 29, 66, 87, 88], and video generation [4, 9, 21, 62, 65, 71].”
GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
Russell, L., Hu, A., Bertoni, L., Fedoseev, G., Shotton, J., Arani, E., & Corrado, G. (2025) · arXiv · doi:10.48550/arxiv.2503.20523 · Cited by 1
“Flow matching time τ and action a t are injected into each transformer block through the adaptive layer norm [19], while we use cross-attention for the other conditioning variables c t .”
朱, 泽. (2024) · Computer Science and Application · doi:10.12677/csa.2024.144084 · Cited by 1
Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models
Nath, U., Singh, R., Shukla, A., Kulkarni, K., & Turaga, P. K. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02270-w · Cited by 1
DAP: Diffusion-based Affordance Prediction for Multi-modality Storage
Chang, H., Boyalakuntla, K., Liu, Y., Zhang, X., Schramm, L., & Boularias, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802575 · Cited by 1
ScaMo: Towards Text to Video Storyboard Generation Using Scale and Movement of Shots
Gu, X., Wang, X., Jin, C., & Song, R. (2024) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3696409.3700279 · Cited by 1
3DSignDiff: Towards 3D Sign Language Gesture Generation
Yu, R., Liu, Y., Bai, X., Yang, R., & Wu, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890302 · Cited by 1
Qi, X., Fu, R., Wen, Z., Wang, T., Qiang, C., Tao, J., Li, C., Lu, Y., Shi, S., Wang, Z., et al. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889461 · Cited by 1
AudioCache: Accelerate Audio Generation With Training-Free Layer Caching
Shi, Q., Du, Z., Lu, J., Liang, Y., Zhang, X., Wang, Y., Peng, J., & Yuan, K. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889043 · Cited by 1
Make Some Noise: Towards LLM audio reasoning and generation using sound tokens
Mehta, S., Jojić, N., & Gamper, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888809 · Cited by 1
GZSL-Lite: A Lightweight Generalized Zero-Shot Learning Network for SSVEP-Based BCIs
Wang, X., Liu, A., Cui, H., Chen, X., Wang, K., & Chen, X. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3553204 · Cited by 1
SinWaveFusion: Learning a single image diffusion model in wavelet domain
Kim, J., Kang, J., Kim, T.-W., & Oh, H. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105551 · Cited by 2
Survey on generative visual media detection and security
Duan, J., Liu, S., Guan, J., Jie, C. A. O., & He, R. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2024-0354 · Cited by 1
LOSA: Learnable Online Style Adaptation for Test-Time Domain Adaptive Object Detection
Liu, W., Luo, B., Liu, J., Nie, H., & Su, X. B. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3576444 · Cited by 1
Noise-to-Abundance Translation: Unsupervised Hyperspectral Unmixing Based on Diffusion Models
Dong, H., Zhang, X., Meng, H., & Jiao, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3582029 · Cited by 1
Dai, Q., Feng, H., Cui, W., Cai, X., Zheng, Y., & Zeng, M. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733322 · Cited by 1
So, J., Hong, S., Choi, J., Jo, W., Kim, S., Yoo, H., & Han, D. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11044273 · Cited by 1
ssEM Image Restoration via Diffusion Models With Multi-Output Joint Strategy for Noise Estimation
Yang, H., Cheng, A., Shi, J., Zhao, G., Chen, J., Huang, D.-S., & Zhang, R. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3584726 · Cited by 1
TrDPNet: A transformer-based diffusion model for single-image 3D point cloud reconstruction
Li, F., Li, T., Xiao, K., Wang, L., & Li, Y. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104503 · Cited by 1
GTF: Generator for Pairwise Thermal Face Image Synthesis
Lu, J., Zhao, C., Zhang, Y., Zhu, J., & Zheng, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9869-1_7 · Cited by 1
KDD Workshop on Evaluation and Trustworthiness of Agentic and Generative AI
Ling, Y., Dong, S., Chen, Z., Feng, Y., Hasan, S. A., Karypis, G., & Reddy, C. K. A. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737854 · Cited by 1
GenBEV: Generative Model With Semantic Compensation for Bird’s Eye View Segmentation
Yu, J., Fan, W., Guo, Y., Lyu, H., Gao, H., Lin, C., Han, M., & Cheng, X. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3589213 · Cited by 2
MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
Huang, J., Liu, T., Wu, Y., Qu, X., Liu, L., & Hu, 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/cvpr52734.2025.01708 · Cited by 1
Wang, Y., Liu, R., Xie, X., Wang, L., Yi, Z., & Ma, R. (2025) · Graphical Models · doi:10.1016/j.gmod.2025.101292 · Cited by 1
From a Single Design to Multiple Variations: AI-Guided in-App Image Generation
Hod, G., Or, D. B., & Regev, E. (2025) · IEEE Conference on Games (CoG) · doi:10.1109/cog64752.2025.11114405 · Cited by 1
Cai, C., Xiao, J. Y., He, X., Zou, Y., & Li, W. (2025) · Physics of Fluids · doi:10.1063/5.0283580 · Cited by 1
Zhang, Y., Chen, Y., Yu, H., Dai, J., Liu, B., Li, N., Wang, C., & Elazab, A. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3605332 · Cited by 1
Detection Token: Detecting adversarial examples for Vision Transformers with one additional token
Tang, Y., Liu, X., Li, B., Zhou, B., Wu, X., & Xu, W. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100353 · Cited by 1
Zhao, T., Liu, J., Li, X., Li, D., Li, J., Li, S., Hu, J., & Dai, G. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11132992 · Cited by 1
Yu, H., Jin, Y., He, Y., & Sui, W. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00401 · Cited by 1
Zhou, K., Huang, J., Kim, N. S., & Shanbhag, N. R. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11132463 · Cited by 1
Dataset Distillation for Super-Resolution Without Class Labels and Pre-Trained Models
Cho, S., Jung, Y., Cho, N. I., & Soh, J. W. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3611694 · Cited by 1
VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation
Huang, P., Fu, J., Guo, B., Li, Z., Wang, Y., & Guo, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05141-7_60 · Cited by 1
Enhancing anomaly detection with few-shot fine-tuned long text-to-image models
Liu, J., An, J., Lu, J., Yang, Z., Wang, J., Lu, P., Wang, Y., & Shen, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112174 · Cited by 1
Advancing multi-subject text-to-image synthesis via Attention Refinement and Inheritance
An, J., Liu, Y., Zhang, W., Wang, L., Chen, X., Yang, Z., Lin, Z., & Wang, W. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116348 · Cited by 1
Yang, G., Wei, Y., Niu, B., & Wang, Y. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3617254 · Cited by 1
An industrial defect detection method based on mixed noise synthesis
Ke, A., Luo, J., Yu, Y., Li, L., & Cai, B. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104388 · Cited by 1
Alternate Geometric and Semantic Denoising Diffusion for Protein Inverse Folding
Wang, C., Zhou, Y., Wang, Z., Zhai, Z., Shen, J., & Zhang, K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06066-2_21 · Cited by 1
Zhao, Z., Guo, Z., Du, J., Ma, F., & Pan, J. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209133 · Cited by 1
Multi-sentence Video Grounding for Long Video Generation
Feng, W. Q., Wang, X., Chen, H., Zhang, Z., & Zhu, W. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209951 · Cited by 1
Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models
Huang, H., Chang, X., & Yao, L. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761406 · Cited by 1
FLUX-Font: Stylized Font Generation Based on Fine-Tuning Pre-trained Diffusion Transformer
Li, Z., Wang, H., Zhang, Y., & Liu, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4395-3_23 · Cited by 1
Progressive Learning of Instance-Level Proxy Semantics for Few-Shot Action Recognition
Peng, F., Yang, X., Wang, Y., & Xu, C. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3632652 · Cited by 1
Multi-view Geometry-Aware Diffusion Transformer for Novel View Synthesis of Indoor Scenes
Kang, X., Xiang, Z., Zhang, Z., & Khoshelham, K. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227757 · Cited by 1
Pyramid Hierarchical Masked Diffusion Model for Imaging Synthesis
Xiao, X., Hu, Q., & Wang, G. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228442 · Cited by 1
SignMask: Structure-aware Masked Modeling for Holistic 3D Sign Language Production
Xia, Y., Zhan, Q., Luo, X., Shi, X., & Wang, Y. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3776750 · Cited by 1
LoRA Training for Text-to-Video Models: A Practical Guide to Fine-Tuning SOTA Video Generation
korem, N. K., Yosef, M. B., Halperin, T., & Bibi, O. (2025) · SIGGRAPH Asia Courses · doi:10.1145/3757371.3763260 · Cited by 1
STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation
Wang, J., Yao, Y., Feng, X., Wu, H., Wang, Y., Huang, Q., Ma, Y., & Zhu, X. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246734 · Cited by 1
One-shot Embroidery Customization via Contrastive LoRA Modulation
Ma, J., He, Q., He, G., Huang, C., Liu, C., Jin, X., & Wang, H. (2025) · ACM Transactions on Graphics · doi:10.1145/3763290 · Cited by 1
Learning-based 3D CAD model generation in mechanical engineering: A survey
Baumeister, F., Bönsch, J., Chaumet, C., Dörr, L., & Meyer, A. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104990 · Cited by 1
A Survey on Future Physical World Generation for Autonomous Driving
Chu, J., Liu, Z., Huo, H., Qin, J., Pan, Y., & Cheng, L. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3769748.3773345 · Cited by 1
Learning Human Motion with Temporally Conditional Mamba
Nguyen, V.-Q., Le, Q.-T., Huang, B., Vu, M. N., Le, N., Vo, T. N., & Nguyen, A. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763948 · Cited by 1
Multi-Scale Diffusion Transformer for Jointly Simulating User Mobility and Mobile Traffic Pattern
Liu, Z., Long, Q., Wang, H., & Li, Y. (2025) · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS) · doi:10.1145/3748636.3762763 · Cited by 1
ProDet: Learning Prototype-Based Region-Word Alignment for Open-Vocabulary Object Detection
Gao, Z., Shen, W., Chen, Y., Li, Q., & Wei, Z. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11290360 · Cited by 1
Lasala, A., Fiorentino, M. C., Bandini, A., & Moccia, S. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3617977 · Cited by 1
Liu, Y., Xue, Y., Crawford, N., Xue, J., & Huang, J. (2025) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3725843.3756064 · Cited by 1
Metadata
- Authors
- Peebles, W., & Xie, S.
- Affiliations
- University of California, Berkeley (US)
- New York University (US)
- ORCID
- Xie, Saining
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 4172-4182
- OpenAlex
- W4390872297
- Semantic Scholar
- 736973165f98105fec3729b7db414ae4d80fcbeb
- Cited by
- 2,284
- References
- 59
- Citations by year
- 2026: 1007 · 2025: 925 · 2024: 315 · 2023: 37
- FWCI
- 244.26
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- diffusion models, latent diffusion models, diffusion transformer, scalability, image generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
