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 2,501–2,600 of 3,684
EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models
Wang, K., Di, D., Su, T., & Fan, L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209379
A Novel Framework for Realistic 3D Scene Regeneration with Graph of Thoughts
Kou, Y., Zhang, K., Zhu, D., Min, X., & Zhai, G. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209258
Inversion-Free Image Editing via Rectified Flow
Peng, Z., Yue, C., Duan, T., & Zhang, D. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209009
MCSMoG: Multi-Conditional Diffusion for Stylized Motion Generation with Parametric Control
Yang, Y., Li, X., Chen, Y., Yue, G., Zhou, W., Su, Z., Wang, R., Zhou, F., & Zhao, B. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209286
DASA: Distribution-Aware Sparse Attention for Accelerating Diffusion Transformer
Ma, T., Guo, J., Huang, D., Song, X., Wang, Q., Han, H., Jin, P., Guan, X., Hao, Y., Wen, Y., et al. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3627864
A 28nm 31.2 TOPS/W Diffusion Transformer Accelerator Using Memory-in-Compute Architecture
Hwang, S., Zhou, K., Chiang, N., Sundaresha, V., & Shanbhag, N. R. (2025) · doi:10.1109/esserc66193.2025.11214030
Cost Savings from Automatic Quality Assessment of Generated Images
Giró-i-Nieto, X., Andreou, N., Liang, A., Baradad, M., Moreno-Noguer, F., & Martinez, A. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00115
Real-time Train Trajectory Optimization under Emergency Scenarios based on Diffusion-PSO Framework
Zhang, Y., Zhang, Z., Liu, S., Liu, L., & Dong, H. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221846
Huynh-Nguyen, H.-N., Dang, H. N., Nguyen, N.-S., & Nguyen, V. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.02848
Cui, Z., Nie, D., Xue, P., Wu, X., Zhang, D., & Wen, X. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761402
Wojciechowski, K., Gursoy, E., Haffemayer, A., Kleff, S., Bonnet, V., Lamiraux, F., & Mansard, N. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696253
AnyPortal: Zero-Shot Consistent Video Background Replacement
Gao, W., Lan, X., & Yang, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01765
EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-TuningPreprint
Cai, X., Wu, S., Chi, D., Zhuang, Y., Quan, X., Hao, J., & Guan, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.05553
Tang, C., Huang, Z., Wang, W., Feng, X., He, Y., Fan, S., Wang, K., Sun, W., & Liu, Y. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3622515
MMG: Manipulation-Aware Holistic Human Motion Generation from Sparse Tracking Signals
Shi, X., Xiao, R., Sheng, Y., Wang, L., Wu, J. G., Chen, X., Yin, J., & Liu, Q. (2025) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar67309.2025.00032
DGDiff: Immersive 3D Indoor Scene Synthesis via Dialog-Graph Conditioned Diffusion
Liu, Y., Zhang, X., Geng, Q., & Zhou, Z. (2025) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar67309.2025.00055
STARS: Semantics-Aware Text-guided Aerial Image Refinement and Synthesis
Townsell, D., Chen, L., Xie, M., Pan, C., & Zhang, W. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104561
Ding, C., Liu, A., & Zhang, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227415
CLIP-Enhanced Linear Alignment for AI-Generated Image Detection Using Latent Cross-Attention
Wang, Y., & Sun, T. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228586
Wang, Y., Su, J., Finkelstein, A., Kumar, R., Chen, K., & Jin, Z. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230986
Enhancing Sequential Recommendations with Sequence Diffusion Models for Long-Tail Users
Wu, Q., Feng, J., & Lin, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227732
Pal, A., Chai, A.-F., Rajanala, S., Phan, R. C. ‐., Wong, K., & Ting, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227843
DPCAI: Image Composition via Diffusion Prior and Compound Attention Injection
Yang, W., & Chen, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228263
Token Selection Acceleration: A Structure-Guided Approach for Diffusion Transformer Model
Zhong, W., Li, X., Wu, H., & Yuan, G. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227434
EDITS: Enhancing Dataset Distillation with Implicit Textual Semantics
Xia, Q., Du, J., Lu, G., Shu, Z., & Wang, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461694
Teefusion: Blending Text Embeddings to Distill Classifier-Free Guidance
Fu, M., Wang, G., Chen, X., Chen, Q.-G., Zhao, X., Luo, W., & Zhang, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01546
Biologically inspired spiking diffusion model with adaptive lateral selection mechanism
Feng, L., Zhao, D., Shen, S., & Zeng, Y. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109045
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer
Xie, Y., Sun, Y., Zhang, H., Liu, Y., & Tang, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464361
Masked Conditioning for Deep Generative ModelsPreprint
Mueller, P., Wiese, J., Mueller, S., & Mikelsons, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.16725
VISE: Velocity-Guided Interpolant Diffusion for Efficient Speech Enhancement
Yang, G., Wei, Y., Niu, B., Wang, Y., & Yu, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4367-0_15
Adaptive Dzip Transformer-Based Data Compression Technology for Digital Twin Systems
Pan, C., Zhang, C. Y., Shi, J., & Zhao, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3635831
StoryBench: A Dataset for Diverse, Explainable, Multi-hop Narrative Text-to-Image Generation
Ge, Y., Ye, K., Chen, S., Hao, A. X., Ma, X., Chang, K., Xiao, T., & Zhu, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_3
Decoupling Complexity from Scale in Latent Diffusion Model
Zhong, T., Tian, X., Wang, X., Jiang, B., Tao, X., & Wan, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_8
ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation
Peng, C., Hou, Q., Ren, Z., & Zhou, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01879
Oh, Y.-J., Kwon, J.-H., Park, J., & Cho, N. I. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461893
Xu, F., Almalıoğlu, Y., & Trigoni, N. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247274
CLAP: A Closed-Loop Diffusion Transformer Action Foundation Model for Robotic Manipulation
Li, M., Ye, D., Zhou, Y., & Yang, C. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246478
On Learning Closed-Loop Probabilistic Multi-Agent Simulator
Lu, J., Gupta, R., Moradipari, A., Han, K., Zhang, R., & Wang, Z. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246993
ULF-TTS: An Uncluttered Hybrid TTS System Using Language and Flow Matching Models
Park, J. H., Choi, S. J., Eom, Y., Shindell, A., Seo, M.-G., & Lee, G.-H. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249203
Towards Accurate and Smooth Human Motion Reconstruction from Sparse Tracking with State Space Model
Dong, K., Xue, J., Niu, Z., Liu, Q., Mao, S., Lü, K., & Lan, X. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3778860
Beyond Language: Transformers in Visual Computing and Image Generation
Pourtahmasbi, M., Nourbakhsh, A., Ghanbari, P., Talebi, M., & Pourtahmasbi, M. (2025) · 2025 7th International Conference on Pattern Recognition and Image Analysis (IPRIA) · doi:10.1109/ipria68579.2025.11263657
Tang, B., Zheng, H. W., Huang, R., & Huang, G. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.00493
Cosine-Similarity Methods for Efficient Training and Sampling in High-Dimensional Latent SpacesPreprint
Duan, X., & Chen, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.00684
Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis
Munia, N., & Imran, A.-A.-Z. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11252934
Prototype-Driven Class-Conditional Synthesis for High-Quality Chest X-ray Image Generation
Guo, B., Huang, P., Wang, Y., & Guo, Y. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254294
ICDSR: Integrated Conditional Diffusion Model for Single Image Super-Resolution
Hu, C., Wei, X. X., & Wu, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3639910
Recent advances in diffusion-based embodied imitation learning: a survey
Mu, L. I., Liu, X., Li, Q., Yu, X., Jingzhi, C. U. I., Zhao, L., Feng, H. A. N., Yang, X., Zhou, B., Niu, J., et al. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0307
Kim, K., Han, Y., Ju, S., Jean, Y., Kim, Y., Choi, M., Lim, S., Park, K., Baek, S., Hyeon, S., et al. (2025) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia67487.2025.11263770
Room Adjacency Extraction for High-Accuracy Floorplan Generation from Natural Language Descriptions
Takeuchi, Y., Qi, A. N., & YAMASHITA, A. (2025) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.91.1156
Song, Z., Dai, S. X., Keller, B., & Khailany, B. (2026) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3770743.3804078
Synthesizing Complex Micro-Doppler Signatures for Hand Gesture Recognition with Diffusion Models
Trịnh, T. T., Khai, N. V., Tram, P. V. B., Dang, K. N., Le, M., & Nguyen, X. (2025) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc67618.2025.11268652
MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention
Xie, Q. Y., Ma, Y., Di, D., Gao, X., & Yang, X. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3770948
DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
Park, M., Phunyaphibarn, P., Lee, P. Y., & Sung, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_10
Spanning Tree Autoregressive Visual Generation
Lee, S., Lee, C., Han, J., Song, H., You, T., Lim, H., Choi, S. J., Lee, H., & Yu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36839-3_15
Chen, P., Yang, Z., Feng, H., & Yan, R. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729871
Li, C., Zhang, J., Shi, Z., Li, Z., & Chang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_34
AKITalk: Audio-Implicit Keypoints for Identity-Preserving Talking-Head Video Synthesis
Takahashi, R., Li, R., Oshima, Y., Kuno, S., Morita, R., & Sukeda, I. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3769748.3773362
Li, X., & Yin, Z. (2026) · Physical review. B./Physical review. B · doi:10.1103/fq4j-2p2l
Idoko, S., Jadhav, P., & Singh, A. K. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3696443
HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
Mao, S., Zou, H., Xie, Q., Chen, S., & Kang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37627-5_8
ConStruct-LDM: Conditional Latent Diffusion Model for Structured Design
Arata, K., Amaya, I., Okamoto, N., & Hamagami, T. (2025) · IEEE Access · doi:10.1109/access.2025.3642266
ColorizeDiffusion v2: Enhancing Reference-based Sketch Colorization Through Separating UtilitiesPreprint
Yan, D., Wang, X., Iwasawa, Y., Matsuo, Y., Saito, S., & Guo, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.06895
Food Image Generation on Multi-Noun Categories
Pan, X., Chen, Y., He, J., & Zhu, F. M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00541
Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT
Li, H., Han, S., Mao, H., Shi, Y., Fang, C., Zhang, J., Wu, W., & Yu, H. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3687173
An Octave-based Multi-Resolution CQT Architecture for Diffusion-based Audio Generation
da Costa, M. D. V. M., & Moliner, E. (2025) · IEEE International Symposium on the Internet of Sounds (IS2) · doi:10.1109/is264627.2025.11284630
Lee, J., Choi, J., & Song, J. (2025) · Journal of the Korea Computer Graphics Society · doi:10.15701/kcgs.2025.31.5.17
Diffusion Transformer Policy Learning for Offline Reinforcement Learning
Wei, J., Lan, Y., & Yao, K. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290644
Image Classification Using a Diffusion Model as a Pre-Training ModelPreprint
Ukita, K., Ye, X., & Okita, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.06890
Efficient Image Sampling in Diffusion Models via Rough Set Selection and Mamba State Spaces
Yu, J., She, Z., & Shi, Y. (2025) · Informatica · doi:10.31449/inf.v49i30.12067
Kondori, N. (2025) · cIRcle (University of British Columbia) · doi:10.14288/1.0448491
Transforming Text into Motion: Fundamentals of Diffusion Transformers for Text-to-Video Generation
Halbeisen, C. (2025) · reposiTUm (TU Wien) · doi:10.34726/hss.2025.126680
CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather ForecastingPreprint
Liang, H., Zhang, Y., Meng, Q., He, S., & Yuan, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.13546
Towards Expressive and Robust Learning with Hyperbolic Geometry
Yu, T. (2025) · eCommons (Cornell University) · doi:10.7298/77zx-a395
InstanceGen: Image Generation with Instance-level InstructionsPreprint
Sella, E., Kleiman, Y., & Averbuch-Elor, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.05678
DiffBrush:Just Painting the Art by Your HandsPreprint
Chu, J., Jin, L., Wang, T., Xing, J., & Zhao, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.20904
Enhancing Diffusion Face Generation with Contrastive Embeddings and SegFormer GuidancePreprint
Rawat, D. S., Sherpa, E., Kirupanantha, R., & Hoang, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.09847
Discriminative protein sequence modelling with Latent Space DiffusionPreprint
Quinn, E., Jebali, G., Seince, M., & Bent, O. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.18551
Kuvien suojaaminen tekoälykuvageneraattoreilta harhauttavilla menetelmillä
Rantala, T. (2024) · UTUPub (University of Turku)
Latent Neural Representations Analysis and Distillation for Transformers
Zhao, T. (2024) · eScholarship (California Digital Library)
Towards Effective Theories for Deep Learning and Beyond
Zhai, X. (2024) · DSpace@MIT (Massachusetts Institute of Technology)
Diffusion-Based Generation of SVG Images
Jbara, H. (2023) · Qucosa (Saxon State and University Library Dresden)
Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion ModelsPreprint
Lewandowski, B., Birke, R., & Chen, L. Y. (2025) · arXiv (Cornell University)
The ATLAS collaboration (2025) · CERN Document Server (European Organization for Nuclear Research)
HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion ModelsPreprint
Sadat, S., Salehi, F., & Weber, R. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.22300
Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug DiscoveryPreprint
Kaech, B., Wyss, L., Borgwardt, K. M., & Grasso, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.26405
Video Diffusion based Digital Twin for Large Format Additive Manufacturing
Liu, L., Xie, H., Hoskins, D., Rowe, K. G., & Ju, F. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163898
UWLDM: Underwater Image Enhancement Based on Latent Diffusion Model
Yao, L., Yan, J., Chen, W., Feng, H., & Chen, H. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150329
Demystifying noise: Role of randomness in generative AI
Singh, G., Huang, X., Vandersanden, J., Öztireli, C., & Mitra, N. J. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721241.3734002
Ferreira, V. R. S., de Paiva, A. C., de Almeida, J. D. S., Bráz, G., Silva, A. C., & Renna, F. (2025) · Lecture notes in business information processing · doi:10.1007/978-3-032-08570-2_12
It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited StepsPreprint
Cisneros‐Velarde, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.21802
Deterministic diffusion models for Lagrangian turbulence: Robustness and encoding of extreme events
Li, T., Tuteri, F., Buzzicotti, M., Bonaccorso, F., & Biferale, L. (2025) · European Journal of Mechanics - B/Fluids · doi:10.1016/j.euromechflu.2025.204402
He, X., & Huang, D. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228786
Generative Artificial Intelligence
Herrmann, L., Jokeit, M., Weeger, O., & Kollmannsberger, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-89529-6_8
Sequence-adaptive video prediction in continuous streams using diffusion noise optimization
Azar, S. M., Bahrami, E., Pallotta, E., Francesca, G., Timofte, R., & Gall, J. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104969
Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
Lin, J., Gryspeerdt, E., & Clark, R. (2025) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.2511.19431
Generative Anchored Fields: Endpoint Learning for Generative ModelingPreprint
Deressa, D. W., Mareen, H., Lambert, P., & Van Wallendael, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.22693
Group Symmetries in Diffusion Models: Formulation, Generalization, and Enforcement
Bharthulwar, S. (2025) · Digital Access to Scholarship at Harvard (DASH) (Harvard University)
LayerPack: Training-Free Animation Inbetweening with Cross-Layer Consistency
Maruyama, A., Koga, S., Maejima, A., Koyama, Y., Shen, I.-C., & Igarashi, T. (2025) · SIGGRAPH Asia Posters · doi:10.1145/3757374.3771440
Investigation of transformer models capabilities in computer vision course laboratory practice tasks
Каунов, С. А., & Kunov, S. A. (2025) · Electronic scientific archive of UrFU (Ural Federal University)
Pi, P., He, L., Liu, Z., Tian, Q., Liu, Z., & Liu, H. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3638767
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
