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 2,401–2,500 of 3,684
Semantic Segmentation for Vision and IntelligencePreprint
Song, J., Yang, J., Jing, B., Zhang, Y., Bi, Z., Chen, K., Li, M., Niu, Q., Liu, J., Peng, B., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5137673
A High-Resolution Image Synthesis Model Based on Conditional GANs
张, 居. (2025) · Computer Science and Application · doi:10.12677/csa.2025.152049
SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space
Zhang, Z., Qin, H., Huang, J., Cheng, J.-K., Li, Y., Hui, L., Duan, Y., & Ma, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889186
Layer-Animate for Transparent Video Generation
Bai, J., Zhou, J., Wang, B., Chen, W., Yang, Y., Lei, Z., & Wang, F. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887999
Xie, F., Gao, D., Liu, R., Yang, M., Zhang, Y., & Wang, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890268
TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis
Li, M., Zhang, Z., Liao, J., Qin, L., & Wang, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889873
Multi-Style Facial Sketch Synthesis through Masked Generative Modeling
Sun, B., Guo, L., & Zheng, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890574
Multi-Modal Contextual Feature for the IP Consistent Generation
Dong, W., Xie, Q., & Yin, J. (2024) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic64248.2024.10913086
Lei, F., Min, K., Zhang, J., & Zhu, C. X. (2025) · Physics of Fluids · doi:10.1063/5.0256978
The diffusion model and its applications in bioinformatics
Wu, Z., Fu, Y., Chen, J., Ma, J., Wu, W., & Deng, M. (2025) · Scientia Sinica Mathematica · doi:10.1360/ssm-2024-0316
Understanding the Inference Performance of Spatial Temporal Diffusion Transformer
Li, Y., Wei, Y., Du, J., Dan, H., & Xiao, N. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2830-8_37
Residual Diffusion Model with Wavelet Transform for Low-Light Image Enhancement
Ding, B., Sun, B., Wang, Y., Dang, Z., & Sun, X. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-3564-1_14
Review on the Development of Image Transfer
Fu, R. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10958106
Structure Alignment Resampler: More Structure for the Specific ID Generation
Xie, Q., Dong, W., & Yin, J. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957791
The Enhancement of Advanced Text-to-Image Diffusion Generation Models: A Review
Sheng, H. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957764
Hong, R., Huang, Y., Liu, L., Geng, M., Wu, Z., Li, B., Wang, X., & Liu, Q. (2025) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2025.3565797
Enhancing Video Stylization with Integral Noise
Ostrowski, K., Piasecki, M., Kudelska, M., Bartkowiak, P., Wang, H., & Bullock, B. (2025) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc64010.2025.10993671
Musimple: A Simplified Music Generation System with Diffusion Transformer
Dai, Z., He, H., & Kong, Q. (2025) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw65056.2025.11011064
Generative Dataset Distillation Using Min-Max Diffusion Model
Fan, J., Zhou, Y., Ren, M. C. J., & Yang, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93806-1_5
HoloDiT: Exploring 3D Diffusion Transformer Models Using 2D Images
Li, H., Zhao, J., & Gu, D. (2025) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1145/3728725.3728727
Feature Reassembly and Co-Refinement for Human Motion Reconstruction
Li, Z., & Zhang, P. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11022302
Focus on What Matters: Guiding Vision Transformers Towards Justification
John, T., & Das, M. K. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8180-8_15
Prediction of future action start in untrimmed videos based on diffusion
Zhang, S., Liu, S., Wang, S., & Du, S. (2025) · International Conference on Generative Artificial Intelligence and Digital Media · doi:10.1145/3734921.3734940
Research on Robotics Diffusion Transformer in Robot Foundation Models Based on Diffusion Model
Yang, C., & Zhu, M. H. (2025) · International Conference on Intelligent Systems, Communications and Computer Networks (ISCCN) · doi:10.1145/3732945.3733004
A Lightweight Diffusion Model with Modified Sampler
Portnoy, M. G., & Ovalle-Magallanes, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96255-4_35
Audio2Lip: Speech-Driven 3D Face Animation Based on Facial Motion Prediction and Face Reconstruction
Wang, Z., Chen, B., Liang, Z., & Huang, H. (2025) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit65432.2025.11035020
Scene-guided Attention Network for Spatial Understanding in 3D Scenes
Jiang, Y., Zhang, J., Lin, C., Yu, Y., & Yang, Z. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733426
Wang, T., Misawa, N., Matsui, C., & Takeuchi, K. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11044312
Towards Defining an Efficient and Expandable File Format for AI-Generated Contents
Gao, Y., Feng, R., Li, X. S., Li, W., & Chen, Z. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043170
Enhancing Conditional Lace Image Generation in StyleGAN using Inversion Encoders
Li, L., Zhong, S., & Chen, K. (2024) · doi:10.1145/3703935.3704081
AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
Kartikasari, M., Putra, H. A., & Amien, M. (2025) · Teknika · doi:10.34148/teknika.v14i2.1215
Synthesizing Remote Sensing Images from Land Cover Annotations via Graph Prior Masked Diffusion
Deng, K., Wei, S., Pang, S., Jiang, H., & Su, B. (2025) · Remote Sensing · doi:10.3390/rs17132254
Generalized Visual Relation Detection With Diffusion Models
Gao, K., Chen, S., Zhang, H., Xiao, J., Zhuang, Y., & Sun, Q. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3588357
LDiT: Pseudo-label Noise Adaptation via Label Diffusion Transformer
Peng, J., Duan, P., Huang, M., & Xiong, S. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9994-0_27
A Continuous Diffusion Text Generation Model with a New Denoising Structure
Li, S., Cai, G., Jin, Y., & Shang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9994-0_16
Методы сжатия пространства для скрытых диффузионных моделей
Абрамов, В. Г., & Громов, М. А. (2025) · Sovremennye informacionnye tehnologii i IT-obrazovanie. · doi:10.25559/sitito.021.202501.90-102
Style Customization of Text-to-Vector Generation with Image Diffusion Priors
Zhang, P., Zhao, N., & Liao, J. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730707
From Pixels to Shapes: Generative AI for 2D Images and 3D Models
Huo, J., Xu, S., Chen, X., Peng, W., Wang, Y., Wang, Y., & Fang, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9815-8_9
Multimodal Instruction-Guided Image Editing Methods
Huang, L. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085723
Zhong, H., Xie, H., Wang, S., & Yong, H. (2025) · Computer Physics Communications · doi:10.1016/j.cpc.2025.109777
Diffusion-guided conditional model for lung nodule segmentation
Zhang, M., Liu, X., Sun, L., Zhu, W., Yang, Y., & Yan, F. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111259
Aerodynamic Performance Prediction of Airfoils with TransformersPreprint
Liu, B., Zhi, C., Da, X., & Li, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5370691
Image Generation based Data Enhancement Method of Target Detection for Mountain Road Scenes
Zhang, J., Zhao, H., & Cen, M. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090920
Generating and Controlling Inverse-Procedural PBR Material Graphs via Collaborative Diffusion Models
Kang, S. (2025) · Journal of Digital Contents Society · doi:10.9728/dcs.2025.26.7.1971
DA3Attacker: A Diffusion-Based Attacker Against Aesthetics-Oriented Black-Box Models
He, S., Zheng, S., Ming, A., Wang, Y., & Ma, H. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3594068
Innovative Data Augmentation Using Lightweight Diffusion Transformer for Imbalanced Fault DiagnosisPreprint
Wang, W., Chen, Y., Liu, Z., & Lu, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5356008
Innovative Data Augmentation Using Lightweight Diffusion Transformer for Imbalanced Fault DiagnosisPreprint
Wang, W., Chen, Y., Liu, Z., & Lu, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5356007
Active Diffusion Matching: Score-Based Iterative Alignment of Cross-Modal Retinal Images
Lee, K., Song, S. J., Lee, S., & Lee, K. M. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3598247
Concept Lancet: Image Editing with Compositional Representation Transplant
Luo, J., Ding, T., Chan, K. H. R., Min, H., Callison-Burch, C., & Vidal, R. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02654
Enhancing Prediction Robustness of Latent Diffusion Models through World Models
Na, Y., Park, R. Y., Seo, S., & Kwon, T. (2025) · Journal of the Korea Computer Graphics Society · doi:10.15701/kcgs.2025.31.3.21
Mahara, A., Deng, L., & Rishe, N. D. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084647
Attribute-Specified Generation And Style-Transfer Diffusion For Face Recognition Enhancement
Chang, C., Lee, M.-H., Chiu, Y.-H., Hsu, G.-S. J., & Chung, S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084423
A Zero-Shot High-Dimensional Feature Fusion With STF-GAN for Cross-Domain Image Reconstruction
Lu, H., Liu, D., Yang, L. T., Zhao, R., Lian, S., Yuan, S., & Su, J. (2025) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2025.3600191
From High Precision Denoising to Lightweight Generation with Quantized Diffusion ModelsPreprint
Aline, C., Sorensen, M., Holm, K., & Lindberg, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5393631
Light-DiT: An Importance-Aware Dynamic Compression Framework for Diffusion Transformers
Gu, C., Li, G., Zhang, X., Ling, J., Lin, X., Song, Z., Cheng, J., & Liang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-99857-7_25
Bidirectional Beta-Tuned Diffusion Model
Zheng, T., Zou, J., Jiang, P.-T., Zhang, H., Chen, J., Wang, J., & Li, B. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3604039
Морозов, В. В., & Dzekunov, D. (2025) · IEEE International Conference on Smart Information Systems and Technologies (SIST) · doi:10.1109/sist61657.2025.11139234
Dynamic Initial Noise Generation for Diffusion-Based Robotic Manipulation Policy
Mu, Y., Li, Y., & Lou, Y. (2025) · IEEE China Conference on System Simulation Technology and its Applications (CCSSTA) · doi:10.1109/ieeeconf65522.2025.11137018
Efficient Face Recognition via Representative Synthetic Data
Chang, C., Lee, M.-H., Chiu, Y.-H., Liao, Y.-M., Chung, S., & Hsu, G.-S. J. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152238
Towards Fine-Grained Spatial Control for Soccer Game Image Generation
Sangare, A. S., Maglo, A., Engel, B., & Chaouch, M. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00593
Himel, G. M. S., Ahmed, M., Shatabdy, S. N., Rahman, M. S., Hossain, M. S., Syeed, M. M. M., & Uddin, M. F. (2025) · International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM) · doi:10.1109/ncim65934.2025.11160069
Xu, C., Ahmad, H., Okadome, Y., Ishiguro, H., & Nakamura, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3611812
Lee, J., Xu, X., Kim, D., Kuang, T., Deng, H., Song, X., Soubra, Y., Dharia, R., Liebschner, M. A. K., Gateño, J., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05127-1_21
Ultra fast-inference depth completion with linear attention-based cascaded hourglass network
Wu, Z., & Hao, Y. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00381-9
Prompt-enhanced cross-attention diffusion transformer for aspect sentiment triplet extraction
Liu, Y., & Xia, H. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07874-8
Learning quantum phase transition in parametrized quantum circuits with an attention mechanismPreprint
Yin, Z., & Li, X. (2025) · Research Square · doi:10.21203/rs.3.rs-7019666/v1
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Han, T., Xu, W., Gong, J., Yue, X., Guo, S., Zhou, L., & Bai, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01667
Cfdc: a fast zero-shot classifier framework based on CLIP and diffusion models
Su, S., Xu, H., Jiang, W., Hu, Y., & Zhu, X. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02809-4
Xia, Z., Zhao, S., Han, J., & Chen, J. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00130
Advancing Computational Models and Algorithms for the Analysis of Single-Cell and Neural Data
Deng, K. (2025) · Deep Blue (University of Michigan) · doi:10.7302/25748
Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech
Li, Z., Edlund, J., Gu, Y., Phan, N., Juvela, L., & Kurimo, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465122
Meanflow-Accelerated Multimodal Video-to-Audio Synthesis Via One-Step Generation
Yang, X., Yang, J., Guo, X., Wang, H., Pan, N., & Huang, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461369
Rethinking Visual Autoregressive Sampling with Information-Grounding GuidancePreprint
Nguyen, K. D., Tran, H. L., Dinh, A.-D., Liu, D., Cai, W., Wang, X., & Xu, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23876
Research progress of diffusion model in crowd activity analysis
Wu, F., & Zhang, G. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03209-y
AtlFast3: Fast Simulation in ATLAS for LHC Run 3 and Beyond
Corchia, F. A., Bandieramonte, M., Beirer, J. F., Chapman, J. D., Dührssen, M., Ernst, F., Giannelli, M. F., Qiu, T., Schaarschmidt, J., Soberi, M. F. M., et al. (2025) · EPJ Web of Conferences · doi:10.1051/epjconf/202533701355
Home-made Diffusion Model from Scratch to HatchPreprint
Yeh, S.-Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.06068
FlexRibbon: Joint Sequence and Structure Pretraining for Protein ModelingPreprint
Zhu, J., Shi, Y., Bi, R., Jin, P., Liu, C., Zhang, Z., Huang, H., Guo, Z., Hu, P., Ju, F., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.08.681293
PWT: Advancing Alzheimer’s PET Synthesis from MRI with Enhanced Pathological Feature Preservation
Li, Q., Ren, Y., Zhang, H., Ge, W., Huang, J., Xie, J., Cheng, D., Zhang, T., Huang, Y., Xu, N., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189108
FLUX Model Based Image Generation of Ancient Chinese Artifacts via Low Rank Adaptation
Wang, J., Huang, S., & Zhao, Y. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193345
Watanabe, K., Frolov, S., Hassan, A., Dembinsky, D., Lucieri, A., & Dengel, A. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00032
A Mutil-conditional Diffusion Transformer for Versatile Seismic Wave GenerationPreprint
Duan, L., Zhang, Z., Zhou, L., Han, C., Bai, L., Guo, T., & Zhao, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.16874
Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
Lavoie, S., Noukhovitch, M., & Courville, A. C. (2025) · neural information processing systems · doi:10.52202/085713-3327
All-atom protein design via SE(3) flow matching with ProteinZenPreprint
Li, A. J., & Kortemme, T. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.18.683228
Laconic: A 3D Layout Adapter for Controllable Image Creation
Maillard, L., Durand, T., Rahary, A. R., & Ovsjanikov, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01677
Deep Learning for Regular Raster Spatio-Temporal Prediction: An Overview
Capone, V., Casolaro, A., & Camastra, F. (2025) · Information · doi:10.3390/info16100917
DiTSim: A Diffusion-Transformers Based Single-Cell ATAC-seq Data Simulator
Dong, S., Tang, S., Liu, D., & Chen, S. (2025) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-025-00773-9
Research on Improved Complex Image Acceleration Inference Based on Diffusion Transformer
兰, 慕. (2025) · Computer Science and Application · doi:10.12677/csa.2025.1510255
Sanchez, J. I. G., & Costa, P. D. P. (2025) · GENEA · doi:10.1145/3746268.3759431
DiffuseDoc: Document geometric rectification via diffusion model
Xiong, W., Zhou, H., Zhang, Y., Lü, T., & Ma, J. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104554
Retrieval Augmented 3D Garment Generation from Single Image
Zeng, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755034
Multifractal Comparison of Billboard and AI-Generated Music
Zhang, K. K., Sun, Y., & Xiong, H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758168
Yu, Y., Liang, M., Huang, W. P., zheng, J., Lu, K., Li, Y., Du, J., Xue, Z., & Liu, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755850
Li, R., Han, L., Shu, S., Liu, Y., Lin, Y., Ma, Y., Guo, J. M., Liu, Z., & Li, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755164
CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation
Zhang, R., Wen, B., Xie, H., Yao, Y., Zuo, S., Jiang-Lin, J.-Y., Shuai, H.-H., & Cheng, W.-H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755174
Noise-Optimized Distribution Distillation for Dataset Condensation
Liu, T., Liu, Y., Li, B., Hu, W., Li, Y., & Ma, C. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755602
Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
Kang, X., Xiang, Z., Zhang, Z., & Khoshelham, K. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754779
Xu, Y., Sun, Z., Li, Q., & Sun, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755255
Mu, L., Liu, B., Zhang, R., Mo, G., Jin, J., Zhang, K., & Huang, H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755671
Temporal-Conditioned Symbolic Alignment for Controllable Text-to-Music Generation
Zhang, Z., Wu, X., Xu, J., Ma, T., Yao, T., Wu, W., & He, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754812
A Plug-and-Play Sparse Signal Reconstruction Method Based on Diffusion Model
Zhang, S., Li, Y., Wang, Z., Wang, L., & Liu, Y. (2025) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2559087.2025.11204916
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
