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 3,401–3,500 of 3,684
Physics consistent conditional flow matching model as a plasma physics surrogate model
Anonymous, Viegas, P., Ventura, R., & Guerra, V. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/aeaf46
HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives
Kim, J. J., Huh, J., Choi, J., Cheng, W.-H., Jiang-Lin, J.-Y., Lin, W., & Lee, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37520-9_7
Future Video Generation Better Aligns with the Human Visual Cortex than Observed VideoPreprint
Bang, C., Chung, H., & Kim, B.-H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.38819
IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric PretrainingPreprint
Pan, H., Ren, Y., Song, K., Wang, S., Zhang, X., Hu, X., Duan, Z., Zheng, H., Ni, J., Zhao, N., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.39403
BRepFacetGen: Reverse Engineering B-Reps By Generative Face Segmentation
Hui, K.-H., Thamizharasan, V., Jayaraman, P. K., & Xu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37258-1_35
Scalable Cross-Embodiment Dexterous Grasping via Morphology-Prior Diffusion
Li, S., Zhou, Z., Ghasemalizadeh, O., Carlone, L., Sun, M., Feng, C., & Kuo, C.-H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37531-5_31
Xu, Y., Zhu, J., Hong, D., Xiao, L., Wei, Z., & Wu, Z. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3736733
SkillFM: Generating Skills for LLM Agents via Latent Flow MatchingPreprint
Zhang, Z.-M., He, J., Zhang, Y.-Z., & Pan, J. Z. (2026) · arXiv.org · doi:10.48550/arxiv.2609.39382
SAND: Stage-Aware Noise Decomposition for Training-Free Diffusion Guidance
Lee, H., Lee, J. H., Kim, H., & Koh, Y. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37138-6_15
AuthentiQ: Real-Time On-Device Deepfake Detection for the Internet of Multimedia Things
Iyengar, R. S., Mallampalli, K., & Sanghvi, H. (2026) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr70517.2026.00090
A Diffusion-Based Data Augmentation Framework for Semantic Segmentation with Limited Data
Wang, Z., Li, X., Zhu, C., & Qi, L. (2026) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr70517.2026.00068
Mamba-Guided Diffusion for Prediction-Based Industrial Video Anomaly Detection
Li, J., Pan, Y., Liu, W., Wang, Y., Zhang, C., & Xu, Z. (2026) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac70325.2026.11712289
Jin, Z., Yang, T., Li, P., Zhang, H., & Huang, X. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3739530
SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar
Xiang, J., Guo, Y., Guo, B., Yuan, Y., & Zhang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_36
Sketch Animation from Text: Methods, Control, and Mobile Deployment
Терещенко, В. М., Tytarchuk, P., Hordiichuk, V. V., & Tereshchenko, Y. (2026) · Cybernetics and Systems Analysis · doi:10.1007/s10559-026-00907-x
Unleashing Chain-of-Thought Style Reasoning for Text-to-Speech Systems
Jiang, Z., & Zhao, Z. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3831131
Walczak, M., Humes, E., Fang, C., Verhelst, M., & Mohsenin, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.00207
HLRAD: High-Dimensional Latent Representation for Unified Anomaly Detection
Zhang, T., Zang, Z., & Zou, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37083-9_24
Follow-Your-Mind: Towards Inversion-Free Brain-Driven Visual Context Synthesis and Editing
Jing, H., Yang, P., Zhang, R., Liu, Z., Liu, Y., Bai, X., Ma, Y., & Zheng, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37083-9_31
Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE SolversPreprint
Medrano-Navarro, L., Baldan, G., Liu, Q., Holzschuh, B., Hagnberger, J., Niepert, M., & Thuerey, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.03363
Yang, Y., Wang, B., Ran, W., Zhou, N., Zhou, M., Wang, J., & Sui, H. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.09.048
SamgPose: self-attention map guided 6D pose estimation via diffusion model
Ma, C., Pei, W., Gao, Y., Gao, L., Li, X., & Liu, Q. (2026) · Procedia CIRP · doi:10.1016/j.procir.2026.06.001
Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design
Jung, S., Moon, S., Jeong, J., Lee, J., & Huh, J. (2026) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3845814.3850089 · Cited by 1
TF-SiTo: Time-Frequency Guided Similarity Token Pruning for Faster Diffusion Sampling
Bai, L., & Wang, Z. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716408
MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset DistillationPreprint
Chen, Y., Wang, C., Ye, X., Zheng, Z., & Zhang, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.05252
Equivariant generative diffusion learns and generalizes the structural ensemble of amorphous oxidesPreprint
Jiang, J., Berry, I., Fry, J. N., & Cheng, H.-P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.03973
Walt, E., Kofinas, M., Mücke, N. T., Gavves, E., & Coumou, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06509
Trinity: One Differentiable Physics for Training, Refining and Scoring Generative FloorplannersPreprint
Yeh, S.-Y., Wang, T.-S., Wang, X., Lee, J.-H., Kaplan, D. Z., Xu, M.-Q., Tang, W., Wang, C.-Y., Shang-Hong, L., & Lee, C.-Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.04957
Diffusion Transformers are Provably Optimal In-context GeneratorsPreprint
Fu, G., Wakayama, T., Kawata, R., Nitanda, A., Lee, W. S., & Suzuki, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.05333
Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source ImagingPreprint
Morik, M., Palarus, J., Vidaurre, C., Müller, K.-R., & Nakajima, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06726
Balmaseda, V., Lin, C.-L., & Yang, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.05711
Controllable Human-Object Interaction Synthesis via Progressive and Invertible Condition Injection
Lin, X., Liang, T., Li, H., Sun, J., Zhang, J., & Hu, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03052-2
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion TransformersPreprint
Chen, J., Lai, Z., Wang, J., Ouyang, Z., Huang, Y., Yue, X., Lu, C., & Guo, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06801
Efficient visual generation for community player and production service
Zhang, C. (2025) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
IntentEdit: Multi-Agent Reasoning for Intent-Driven Complex Image Editing
Zhang, Y., Huang, S., & Wang, L. (2026) · doi:10.1109/cvprf71909.2026.00842
Disentangling Paradigm, Identifier, and Decoding in Generative RetrievalPreprint
Randrianarivo, H., Renaud, L., & Allal, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.08716
RealDiffusion: Physics-Informed Attention for Multi-Character Storybook Generation
Zhao, Q., Chen, J., Tsang, I. W.-H., & Dai, G. (2026) · doi:10.1109/cvprf71909.2026.00452
PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation
He, J., Su, B., & Wong, F. (2026) · doi:10.1109/cvprf71909.2026.00460
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
Lin, B., Cao, X., Guo, J., & Tan, R. T. (2026) · doi:10.1109/cvprf71909.2026.00031
UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation
Li, H., Sun, B., Yang, Y., Liang, Z., Yin, Z., Sha, X., & Wang, C. (2026) · doi:10.1109/cvprf71909.2026.00447
Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data
Xu, Y., Zhu, H., Liu, C., Wang, T., Chen, K., Xu, S., Yang, J., Yuan, N. J., & Zhang, Q. (2026) · doi:10.1109/cvprf71909.2026.00065
OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation
Xu, G., Bian, Y., Zeng, A., Chen, Z., Shi, M., Huang, S., Li, W., Duan, L., & Xu, Q. (2026) · doi:10.1109/cvprf71909.2026.00353
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
Picard, D., Dufour, N., Degeorge, L., Ghosh, A., Allegro, D., Ravaud, T., Perron, Y., Sautier, C., Baltaci, Z. S., Meng, F., et al. (2026) · 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF) · doi:10.1109/cvprf71909.2026.00248
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Xiao, Z., Zhao, Y., Li, L., Lan, Y., Yu, N., Garg, R., Taghavi, M. H., & Pan, X. (2026) · doi:10.1109/cvprf71909.2026.00381
霍宇飞, Li, A., Dai, W., Wu, S., & Tang, Y. (2026) · doi:10.1109/cvprf71909.2026.00335
One Layer is Enough: Adapting Pretrained Visual Encoders for Image Generation
Gao, Y., Chen, C., & Gu, J. (2026) · doi:10.1109/cvprf71909.2026.00451
CoherentHand: Temporally Consistent 3D Hand Trajectory Synthesis with Semantic Motion Priors
Boote, B., Kim, J., Kara, Ö., Lee, S., & Rehg, J. M. (2026) · doi:10.1109/cvprf71909.2026.00332
IM-Animation: An Implicit Motion Representation for Identity-Decoupled Character Animation
Xu, Z., Gao, X., Liu, F., Zhang, H., Fang, Z., Lai, Y.-K., Liu, X., Wan, P., & Gao, L. (2026) · doi:10.1109/cvprf71909.2026.00446
GRACE: Generation-aware latent compression for efficient video generationPreprint
Kim, J., Cho, P. H., Nam, J., Lee, D., Go, H., Lee, Y., Kim, H., & Kim, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.10524
NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-Based Image Editing
Xu, Z., Shen, X., Nan, H., & Zhang, X. (2026) · doi:10.1109/cvprf71909.2026.00423
Activation-Norm Maximization to Accelerate Training in Flow-Matching Transformers
Belhe, Y., Chang, W., Li, T., Ramamoorthi, R., & Gharbi, M. (2026) · doi:10.1109/cvprf71909.2026.00395
Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-Light Enhancement
Sun, X., Wang, L., Jin, Y., Lam, K., Su, Z., Yang, Y., Pan, J., & Wang, C. (2026) · doi:10.1109/cvprf71909.2026.00465
Decoupled Scale-Wise Autoregressive Modeling for Visual Generation
Ren, S., Yu, Y., Ruiz, N., Wang, F., & Xie, C. (2026) · doi:10.1109/cvprf71909.2026.00434
OmniPSD: Layered Psd Generation with Diffusion Transformer
Liu, C., Song, Y., Wang, H., & Shou, M. Z. (2026) · doi:10.1109/cvprf71909.2026.00405
TinySR: Shallow Diffusion Transformers for Real-World Image Super-Resolution
Dong, L., Fan, Q., Yu, Y., Zhang, Q., Chen, J., Luo, Y., & Zou, C. (2026) · doi:10.1109/cvprf71909.2026.00488
Improving Autoregressive Image Generation Through Coarse-to-Fine Token Prediction
Guo, Z., Zhang, K., & Shieh, M. (2026) · doi:10.1109/cvprf71909.2026.00123
Deep Parameter Interpolation for Scalar Conditioning
Park, C. Y., McCann, M. T., García–Cardona, C., Wohlberg, B. E., & Kamilov, U. S. (2026) · doi:10.1109/cvprf71909.2026.00376
LoViC: Efficient Long Video Generation with Context Compression
Jiang, J., Li, W., Ren, J., Qiu, Y., Pei, R., Song, F., Guo, Y., Xu, X., Wu, H., & Zuo, W. (2026) · doi:10.1109/cvprf71909.2026.00389
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Chen, J., Li, X., Bai, X., Ma, T., Zhang, P., Li, M., Chen, Z., Li, G., Liu, L., Zhao, S., et al. (2026) · doi:10.1109/cvprf71909.2026.00393
From Orbit to Ground: Generative City Photogrammetry From Extreme Off-Nadir Satellite Images
余飞, Liu, Y., Tang, L., Sun, M., Ge, Z., Bu, R., Jin, Y., Zhao, H., Sun, H., Li, Y., et al. (2026) · doi:10.1109/cvprf71909.2026.00042
Lai, J., Lu, Z., He, J., Quan, R., Zhao, W., Yang, Q., Chen, Q., Lin, Q., Li, C., Gao, T., et al. (2026) · doi:10.1109/cvprf71909.2026.00400
ColorMam: Color-Aware State Space Model for Image Color Style Transfer
Jian, L., Peng, J., Li, Y., & Siwang, Z. (2026) · doi:10.1109/cvprf71909.2026.00422
Is Your Text-to-Image Model Robust to Caption Noise?
Yu, W., Yang, Z., Lin, S., Zhao, Q., Wang, J., Gui, L., Fredrikson, M., & Jiang, L. (2026) · doi:10.1109/cvprf71909.2026.00367
MotionDreamer: Generating Continuous Intermediate Motions for Complex Motion Interpolation
Ma, Y., Zhao, S., Yao, M., Li, J., Zhang, L., Liu, X., Dou, Q., Gu, J., & Xue, T. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3739604
FlowC2S: Flowing From Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation
Margaryan, H., Bammey, Q., & Sandor, C. (2026) · doi:10.1109/cvprf71909.2026.00374
Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Spatial and Temporal Representation
Xia, J., Zhang, C., Zhang, Y., Zhou, C., Wang, Z., Liu, B., & Yin, D. (2026) · doi:10.1109/cvprf71909.2026.00826
Xia, T., Ning, Z., Zhao, Z., & Wang, M. (2026) · doi:10.1109/cvprf71909.2026.00370
Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
Lin, Y., Yao, Y., Zhou, Y., & Liu, T. (2026) · doi:10.1109/cvprf71909.2026.00383
Zhang, W., Foo, L. G., Beeler, T., Dabral, R., & Theobalt, C. (2026) · doi:10.1109/cvprf71909.2026.00388
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution
Yang, D., Vicol, P. A., Qi, X., Liao, R., & Zhang, X. (2026) · doi:10.1109/cvprf71909.2026.00485
Rethinking Training Dynamics in Scale-Wise Autoregressive Generation
Zhou, G., Ge, C., Tan, H., Liu, F., & Hong, Y. (2026) · doi:10.1109/cvprf71909.2026.00442
Shiohara, K., Yamasaki, T., & Golyanik, V. (2026) · doi:10.1109/cvprf71909.2026.00355
A-Select: Automatic Timestep Selection for Diffusion Transformer Representation Learning
Liu, C., Liang, J., Yang, W., Cui, Y., Yang, J., Wang, T., Wang, Q., Liu, D., & Han, C. (2026) · doi:10.1109/cvprf71909.2026.00667
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
Le, T.-T., Zhao, Y., Chai, M., Shen, Z., Cao, Z., Tang, D., 谢小辉, & Kong, D. (2026) · doi:10.1109/cvprf71909.2026.00418
Jano: Adaptive Diffusion Generation with Early-Stage Convergence Awareness
Chen, Y., Zeng, L., Zhou, Y., Li, H., & Zhai, J. (2026) · doi:10.1109/cvprf71909.2026.00432
Fast Generative DeOcclusion for Vision and Robotics
Chen, J., Zhang, T., Xuan, X., He, J., Yin, Y., Shi, H., Ye, S., Li, X., Yuan, R., Shu, T., et al. (2026) · doi:10.1109/cvprf71909.2026.00131
HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
Suzuki, K., Chen, K., Wang, L., Du, B., Li, R. B., Liu, P., Bi, N., & Nguyen, T. (2026) · doi:10.1109/cvprf71909.2026.00064
Yan, W., Ye, S., Yang, Z., Teng, J., Dong, Z., Wen, K., Gu, X., Liu, Y.-J., & Tang, J. (2026) · doi:10.1109/cvprf71909.2026.00429
WorldSonus: Bringing Sound to WorldsPreprint
Fang, P., Jingyi, 法. F., Wu, K. M., Wang, J., Huang, H., Wu, Y., Huang, X., Ma, Z., Chen, W., Liu, H., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.08760 · Cited by 1
USV: Unified Sparsification for Accelerating Video Diffusion Models
Wu, X., Wang, H., Zhou, Y., & Lu, Q. (2026) · doi:10.1109/cvprf71909.2026.00404
FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers
温, 欣., Li, B., Luo, J., Li, Y., & Wang, Z. (2026) · doi:10.1109/cvprf71909.2026.00396
Fashion130K: An E-Commerce Fashion Dataset for Outfit Generation with Unified Multi-Modal Condition
He, Y., Zhu, T., Liu, Y., Ma, L., Shan, X., Fu, J., Shi, Y., Huang, J., & Li, Y. (2026) · doi:10.1109/cvprf71909.2026.00459
Cai, M., Wang, Q., Ye, Z., Liu, W., Liu, Q., Ye, W., Wang, X., Wan, P., Gai, K., & Yue, X. (2026) · doi:10.1109/cvprf71909.2026.00431
Animated-ART: Multi-Layer Transparent Video Generation
Li, Z., Wang, Y., Chen, D., Dong, Y., Li, J., Yuan, Y., & Jin, X. (2026) · doi:10.1109/cvprf71909.2026.00401
Consistent Video Editing as Flow-Driven Image-to-Video Generation
Wang, G., Fan, S., Liu, H., Song, Q., Wang, H., & Xu, J. (2026) · doi:10.1109/cvprf71909.2026.00445
Wang, R., Wang, C., Yi, F., Zhao, Y., Xu, J., Dai, Y., Wang, Z., & Zhang, C. (2026) · doi:10.1109/cvprf71909.2026.00378
Safe Codebook: Token-Level Moderation for Safer Visual Autoregressive Generation
Zhang, J., Xu, Q., Wen, P., Dai, S., Liu, Y., & Huang, Q. (2026) · doi:10.1109/cvprf71909.2026.00761
FREE-Switch: Frequency-Based Dynamic LoRA Switch for Style Transfer
Zheng, S., Zhang, M., Liu, T., & Wang, H. (2026) · doi:10.1109/cvprf71909.2026.00272
Towards Generalization of Scene Text Tampering Localization Via Causal Invariance
Shao, H., Dong, B., Huang, K., Huang, X., & Wang, Q. (2026) · doi:10.1109/cvprf71909.2026.00697
UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation
Liu, Z., Wang, L., Zhou, S., Wu, Y., Sun, X., Hua, G., & Li, H. (2026) · doi:10.1109/cvprf71909.2026.00449
FA-MoE: Improving Medical Image Generation through Frequency-Aware Mixture of Experts
Sun, Y., Meng, Q., Chen, T., & Chen, H. (2026) · doi:10.1109/cvprf71909.2026.00386
Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generation
Reddy, S., Malhi, I., Ma, S., & Dutta, P. (2026) · doi:10.1109/cvprf71909.2026.00851
Nagy, R., Voß, H., Hoang-Minh, T., Tsakov, M., Nikolov, T., Zhang, Z., Ao, T., Yang, S., Huang, S., Cheng, Y., et al. (2026) · doi:10.1109/cvprf71909.2026.00211
Chen, Y., Li, M., Rao, Z., Zeng, D., Guo, S., & Guo, J. (2026) · doi:10.1109/cvprf71909.2026.00328
OminiControl2: Efficient Conditioning for Diffusion Transformers
Tan, Z., Xue, Q., Yang, X., Liu, S., & Wang, X. (2026) · doi:10.1109/cvprf71909.2026.00411
E-Grpo: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Zhang, S., Zhang, Z., Dai, C., & Duan, Y. (2026) · doi:10.1109/cvprf71909.2026.00427
GeneFlow: Modeling Heredity and Variation Via Flow Matching Transformers for Kinship Verification
Wu, Y., Hou, X., & Shen, L. (2026) · doi:10.1109/cvprf71909.2026.00357
Harmonized Multi-Layer Text-to-Image Generation with Generative Priors
Dalva, Y., Li, Y., Liu, Q., Zhao, N., Zhang, J., Lin, Z., & Yanardag, P. (2026) · doi:10.1109/cvprf71909.2026.00813
ControlPose: High-Fidelity Pose-Controlled Image Generation with Multi-Faceted Pose Disentanglement
Du, Z., Chen, X., Nie, Z., Chen, Y., Liu, C., Ji, X., & Chen, J. (2026) · doi:10.1109/cvprf71909.2026.00373
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
