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 3,301–3,400 of 3,684
Jang, H.-S., Cha, Y., & Choi, S. (2026) · Mathematics · doi:10.3390/math14183333
Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation
Shen, Y., Li, Y., Pan, Y., Zhang, Y., & Yao, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_11
SGP$$^2$$: Coarse-to-Fine Controllable Multi-modal Remote Sensing Image Generation
Chen, P., Yang, X., & Wang, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_1
Stylized Video Generation via Decoupled Data Synthesis and Gated Style Token Injection
Wei, X., Fang, Y., Li, Y., Wu, L., Yang, Q., Zhu, M., Wang, N., & Gao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37235-2_2
InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360$$^\circ $$ Image
Koo, G., Kim, H., Kim, Y., Lee, T., Lim, S., Yoon, S., Yeon, S., & Yoo, C. D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_4
InstaEdit: Instant Image Editing via Optimized Noise Prediction
Ma, N., & Shao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_33
FlowLess: Controlling Abstract Image Generation
Hertz, A., & Snavely, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_29
Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding
Lu, Y., Huang, X., & Yang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37032-7_6
RefRetouch: Personalized Image Retouching Without Test-Time Fine-Tuning
Weldengus, T. M., Liu, B., Kou, F., Lyu, Y., Chen, J., Fan, Q., & Zou, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37314-4_26
MUSHY: Multimodal Flow-Based Amortized Bayesian Inference for Spectroscopic Data FusionPreprint
Shen, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.15945
Wu, S., Liang, W., & Luo, K. H. (2026) · Proceedings of the Combustion Institute · doi:10.1016/j.proci.2026.106418
We, D., Yoon, Y., Boo, J., & Yoon, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_18
4DMulti: automated multicomponent identification at complex material interfacesPreprint
Zhang, H., Mao, Z., Chu, S., He, X., Guan, Y., Yang, A., Li, M., Zeng, X., & Xie, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.14348
Ye, Z., Song, C., Weng, Y., Liu, S., Wang, D., Mei, L., & Lei, C. (2026) · ACS Photonics · doi:10.1021/acsphotonics.6c01547
Wang, X., Wang, Y., Zhang, J., & Song, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_30
Tyagi, S., Rawat, P., Yadav, D., & Upadhyay, P. (2026) · Expert Systems · doi:10.1111/exsy.70422
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech SynthesisPreprint
Zhang, Z., Zuo, T., Li, H., Zhang, H., & Xie, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.13909
Li, Q., Tian, M., Yang, T., Liu, G., & Liu, S. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3732637
ResoSeg: Resonance Tagger using Transformer and Segment ModelPreprint
Li, C., Yin, J., Li, K., & Chen, J. (2026) · arXiv (Cornell University)
Noun Presence Loss with Dynamic Weighting for Compositional Text-to-Image Generation
Vu, T.-T. D., & Nguyen, V.-T. (2026) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr72750.2026.11685747
Latent Flow Matching with Scalable Interpolant Transformers for Few-Shot Chinese Font Generation
Wang, Q., Wang, X., & Peng, S. (2026) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc70586.2026.11686621
FlowATC: Aircraft Trajectory Prediction via Flow MatchingPreprint
Petit, M., Torun, E., Brusset, L., Kam, J., & Bayen, A. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.16528
Monitoring Building Aging and Damage with Diffusion Transformers: A Survey
Zhang, H., Xu, W., Zhang, P., Li, Z., Luo, Y., & Guo, H. (2026) · International Symposium on Machine Learning and Media Computing (MLMC) · doi:10.1109/mlmc69743.2026.11686789
GenCalib: A Training-Free Generative Calibration Framework for Sparse Spatial Tensor Reconstruction
Wang, X., Meng, F., Wang, T., Liao, Z., Gao, Y., Wang, S., & Wang, C. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684571
Cross-Timestep Condition-Aware Modulation for Text-Guided Image Editing
Guo, Y., & Chen, R. (2026) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc70586.2026.11686584
Bai, S., & Xu, Y. (2026) · International Conference on Artificial Intelligence and Product Design · doi:10.1145/3829918.3829990
Wang, H., Han, S., Wu, D., Zhang, W., & Cai, D. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111425
Mao, L., Peters, Y., Simpson, E. L., & Zhang, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.18928
Li, M., Cheng, Z., Zhang, H., Li, D., Zhang, B., Jia, X., Yu, H. L., & Wendin, S. N. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3727238
Huang, J., Huang, X., Li, S., & Ding, H. (2026) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2026.105596
Wang, Q., Li, M., & Tang, H. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835899
PULSE: Unlocking Practical Image Compression on Single-Thread CPUPreprint
Jia, Z., Zhang, T., Zheng, Z., Xie, W., Li, J., Li, B., Li, H., & Lu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.18602
Zheng, J., Li, B., Wu, W., Wang, C., & Huang, Y. (2026) · International Conference on Electronic Packaging Technology (ICEPT) · doi:10.1109/icept71373.2026.11690366
Adaptive Mean Flow for Responsive Closed-Loop Robot Control
Vaaler, A., Job, M., Holden, C., & Egeland, O. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3734902
Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation
Kim, D., Hong, J., Oh, C., Kim, Y., Lee, Y., & Park, J. (2026) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc71020.2026.00037
PACE-Net: Pretrained Asymmetric Color-Decoupled Enhancement Network for low-light image enhancement
Shi, W., Tian, W., Huang, Z., Lei, J., & Gao, X. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117082
FlashDiff: Accelerated and Guided Image Synthesis
Tran, A., Nguyen, V. Q., Do, N. B., Pham, N. K., Nguyen, T. D., & Bui, V. H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5644-0_12
Zhao, Y., Zhu, F., & Xu, L. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111472
Umgang mit Sprachmodellen (Large Language Models)
Siebertz, K. (2026) · Springer eBooks · doi:10.1007/978-3-662-74590-8_2
Flow Matching for Generating Weakly Labeled Bags of Foundation-Model Mammography Representations
Jovišić, N., Škipina, M., Švenda, V. G., Culibrk, D. R., Antić, B., & Brkljač, B. (2026) · AI · doi:10.3390/ai7090375
$λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted ResourcePreprint
Wang, Y., Priye, P., Marathe, M., & Pahwa, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.22041
Zhu, H., Ma, Y., He, S., Li, L., Gong, S., Li, M., Xiong, X., Wang, C., Tian, H., Liu, Q., et al. (2026) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2026.3732698
Hu, K., Zhao, Z., Zhang, Y., & Gao, X. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03003-x
Bridge of $Ψ$'s: Quantum Circuit Optimization with Schrödinger BridgesPreprint
Hofstetter, L. S., Yeh, L., & Murali, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.25947
JAMB: Joint Action-Motion Diffusion for Bimanual ManipulationPreprint
Xiao, C., Meng, P., & Held, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.25322
Cross-Detector Transfer Learning with Parnassus: From ALEPH to SLDPreprint
Lo, Y.-F., Cheng, C. L., & Nachman, B. P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.25061
Low-light image enhancement based on Laplacian diffusion model
He, M., Xie, C., Wang, R., Wang, Y., Zhou, F., Bian, X., & Chen, Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117030
LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous DiffusionPreprint
Chen, N., Fu, Y., Zhao, J., Sun, Q., Yao, G., Wang, P., Wang, Z., & Zhang, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.28431
Lorentz, A., May, S., Bellet, V., Derksen, D., & Nespoulous, B. (2026) · Remote Sensing · doi:10.3390/rs18193303
TriFlow: Triplane Latent Conditional Flow Matching for Efficient 3D Skull Shape Completion
Liu, Z., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38186-6_61
Hassan, S., Salem, M., Elsayed, A., Oullier, O., & Yaqub, M. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_9
Han, L., Min, P., Xie, X., Zhang, T., Wang, X., Gao, Y., Lu, C., Liang, X., Duan, Y., Portaluri, A., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_3
A Survey on Vision Transformers: Design Pressures, Architectural Taxonomy, and Future Outlook
Lee, C. P., Ooi, E. K. H., Loh, N. K. N., Alqahtani, A., & Lim, K. M. (2026) · IEEE Access · doi:10.1109/access.2026.3735148
LUT-DiT: A LUT-Based Diffusion Transformer Accelerator for Scalable LUT Inference
Tang, E., Yin, Y., Li, W., Jin, F., Wang, Z., & Lin, J. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3732472
AdaBIMBA: Adaptive Token Compression for Long Endoscopy Video Understanding
Yung, K.-W., Mobadersany, P., Parmar, C., Chaitanya, K., Gunderson, F., Surace, L., Ghanem, L. R., Mansi, T., Cula, G. O., Standish, K., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38233-7_1
Demographic-Conditioned State Space Models for ECG-Based Age Estimation
Bracke, B., Stang, A., Schmidt, B., & Friedrich, C. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38260-3_36
Wang, L., Dou, Y., Yang, J., Song, G., & Cui, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_34
Zhu, H., Song, Y., & Nishikawa, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_11
TiltDiff: Tilted Weight-Space Diffusion for Neural Network Generation
Chuang, E.-N., Huang, H., Song, H.-J., Pao, H.-K., & Liu, T.-L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_9
SlimDiffSR: Toward Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation
Wang, C., Hu, Z., & Sun, W. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3732853
Xu, H., Liu, Y., Yuan, W., & Han, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38224-5_5
LeWAM: Latent evolving World Action ModelPreprint
Fang, X., Duan, B., Wu, H., Wang, J., & Qi, G.-J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.27455 · Cited by 1
Kim, S.-Y., Oh, S.-H., Kim, M.-G., Kim, Y.-M., Jung, G., Lee, H., Son, J., Kwon, H., & Bae, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38236-8_53
VC-VAE: Leveraging Video Codecs for Training-Efficient and High-Fidelity Video VAE
Ge, X., Chai, S., Gong, L., Yu, Z., Liu, X., & Ge, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_36
Salahudeen, R., Fonkam, M. M., Vajjhala, N. R., Junaidu, S. B., & Garba, A. (2026) · Systems · doi:10.3390/systems14101198
From Sparsity to Geometry: Spatial Modeling for 3D Reconstruction from Biplanar Bone X-rays
Long, N., Liu, S., Chen, C., Tan, T., To, M. K.-T., & Chen, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38179-8_18
Zhang, X., Zou, W., Zhou, Y., Chen, Z., Zhang, Z., & Tian, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38179-8_6
Li, S. B., Dan, M., Zhu, X., Chu, Y., Zhao, Y., & Zhao, P. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104322
Xue, Q., Liu, X., Shan, H., Zhang, P., & Wang, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38179-8_5
TabDitFlow: Flow Matching with Diffusion Transformer for Tabular Data Generation
Ou, Y., Fang, J., & Cui, E. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5693-8_9
Dil, M. S., Mahmoudabadi, M., & Rezghi, M. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21926-y
Lu, Y., Tan, J., Liang, H., Feng, H., Liu, Y., & Zhang, F. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01303-3
Beyond Index-Only RoPE: Integrating Time and Order for Generative Recommendation
Wei, X., Wu, J., Yi, D., Shirkavand, R., & Gong, M. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831831
Wennker, P. (2026) · Springer eBooks · doi:10.1007/978-3-658-44690-1_29-1
Multiobjective Evolutionary Diffusion Transformer Acceleration
Zhou, Y., Zhang, Y., & Yen, G. G. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2026.3731615
Genel dünya bilgisi ile uç seviyede video sıkıştırmaya doğru
Küçük, F. (2026) · OpenMETU (Middle East Technical University)
Jiang, C., Song, Q., Liu, W., Dapeng, T., Liu, B., & Wang, Y. (2026) · International Journal of Remote Sensing · doi:10.1080/01431161.2026.2735048
Guo, W., Su, N., Jiang, G., & Wang, K. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08885-9
Generative diffusion models for geophysical classification problems
Gong, X., Chen, Y., Breton, C., Siervo, D., Yang, L., & Savvaidis, A. (2026) · Geophysical Journal International · doi:10.1093/gji/ggag383
Wang, F., & Liu, P. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3737695
Short-To-Long Functional Connectivity Transfer via Structure-Aware Latent Diffusion
Torres, B., Liu, Y., & Acharyya, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37242-0_6
Drift-aware denoising-uniform step optimization for fast diffusion sampling
He, Y., Lu, W., Xu, J., Jiang, J., & Zheng, J. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115021
FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References and Proactive Agent PlanningPreprint
Huang, Z., Rong, Z., Qin, S., Liang, S., Hu, W., Luo, Y., Zhang, Y., & Gao, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.35728
Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action ModelsPreprint
Liu, P., Niu, J., Zheng, W., Chen, X., Li, C., Shi, Z., Xie, J., & Liu, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.35439
G$^3$-LoRA: Organizing Reward-Weighted Video Data with Gradient-Guided Grouped LoRAPreprint
Song, J., Li, W., Bai, L., Ye, B., & Xie, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.35189
Synthetic Data Augmentation for Plasmocyte Detection in Bone Marrow Images
Filho, J. L. D. S. B., Rios, T. N., & Rios, R. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39898-7_38
SMART-Edit: Spectral Mutual Attention Refinement and fusion for precise training-free image editing
Chen, J., Tu, Y., Huang, Q., Wang, X., Huang, X., & Huang, C. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115025
Kakde, Y., Jaiswal, J. K., Sahoo, B. M., Saini, D. K. J. B., Randhawa, P., & Mishra, S. N. (2026) · International Conference on Secure Information Systems and Technologies (ICSIST) · doi:10.1109/icsist70215.2026.11705972
LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World ModelsPreprint
Huang, L., Chu, L., Liang, J., & Zhao, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.34375
UniColorFlow: A Unified Framework for Multimodal-Guided Video Colorization with Consistency Flow
Chang, Z., Lin, L., Ouyang, H., Weng, S., Li, S., & Shi, B. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03058-w
DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling
Yang, H., Chen, Y., Pan, Y., Chen, Z., Yao, T., & Mei, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37135-5_19
TaoFlowForge: Progressive Native Mesh Generation via Cascaded Flow MatchingPreprint
Fang, X., Feng, Q., Sun, D., Zhang, Y., Wu, X., Gao, J., Lyu, J., Lyu, C., & Yu, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.37139
Consistent Video-to-Video Translation via Explicit Correspondences
Parmar, G., Li, Z., Zhang, R., Zhu, J.-Y., Srinivasa, N., Shechtman, E., & Nitzan, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37135-5_3
Rho: A Foundation for Efficiently Adaptable VLA ModelsPreprint
Rho Team, Bagaria, S., Chen, D., Fortier, D., Fu, J., Harrison, M., Hellebrekers, T., Joshi, N., Kolobov, A., Moore, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.38164
OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency
Wen, Y., Kang, J., Zhong, S., Zhang, Y., Feng, Y., Chen, J., & Wu, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_15
RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free GuidancePreprint
Liu, Y., Wan, B., Liu, T., Wang, A., Xiong, Y., Zhang, F., Chen, H., & Ding, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.36433
DuoFlow: JVP-Free Finite-Difference Mean Flows for One-Step Image Generation
Li, Z., Zhang, X., Tan, P., & Shum, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37225-3_12
Blind Spatial Room Impulse Response Estimation via Conditional Rectified Flow Matching
Saini, S., & Peissig, J. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3739192
HelixWorld: A Real-time Interactive Audio-Visual World ModelPreprint
Ke, L., Pan, J., Tian, Z., Wang, J., Huang, H., Wu, K. M., Fang, P., Liu, H., Qi, C., Wang, L., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.38123
Scaling Dense Prediction with Latent Decoding
Wu, X., Lao, Y., Wang, C., Yang, S., Zhang, Y., & Zhao, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37225-3_3
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
