The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index; 1 of the 5 sources its claims cite were checked for support.
Scalable Diffusion Models with Transformers
Open accessAbstract
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops—through increased transformer depth/width or increased number of input tokens—consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
Diffusion Transformers (DiTs) replace the standard U-Net backbone in latent diffusion models with a transformer operating on latent patches. DiT-XL/2 achieves state-of-the-art class-conditional ImageNet generation, reaching FID 2.27 at 256×256 and 3.04 at 512×512.
Key findings
- DiT block conditioning matters: adaLN-Zero outperforms cross-attention and in-context conditioning at all training stages while being the most compute-efficient; at 400K iterations its FID is nearly half that of the in-context model.
- Scaling DiT Gflops improves sample quality: across 12 models, transformer Gflops and FID-50K at 400K steps have a correlation of −0.93, with gains from increasing depth/width or number of input tokens.
- DiT-XL/2 sets state of the art: FID 2.27 on class-conditional ImageNet 256×256 with classifier-free guidance cfg=1.50, improving on LDM’s previous best 3.60; at 512×512 it reaches FID 3.04 versus ADM’s 3.85.
- Larger DiT models are more compute-efficient, and extra sampling compute cannot compensate for smaller models: DiT-L/2 with 1000 sampling steps uses 80.7 Tflops and gets FID-10K 25.9, while DiT-XL/2 with 128 steps uses 15.2 Tflops and gets FID-10K 23.7.
Methods
- Design: latent diffusion with a frozen off-the-shelf Stable Diffusion VAE (downsample factor 8); DiT patchifies latents, applies ViT-style positional embeddings, processes tokens through N transformer blocks, and linearly decodes to noise and covariance predictions. Design space includes patch sizes p=2,4,8; block variants in-context, cross-attention, adaLN, and adaLN-Zero; model sizes DiT-S/B/L/XL.
- Data and training: class-conditional ImageNet at 256×256 and 512×512; AdamW, constant learning rate 1×10⁻⁴, batch size 256, horizontal flips, EMA decay 0.9999, no learning-rate warmup or regularization; diffusion hyperparameters retained from ADM; implemented in JAX on TPU-v3 pods.
- Evaluation: FID-50K with 250 DDPM sampling steps using ADM’s TensorFlow evaluation suite; 12 DiT models swept over S/B/L/XL and p=8/4/2 at 400K steps; DiT-XL/2 trained for 7M steps at 256×256 and 3M steps at 512×512; additional comparisons of conditioning strategies and model versus sampling compute.
Limitations
- The paper does not state an explicit limitations section.
- Evident from the text: experiments are limited to class-conditional ImageNet at 256×256 and 512×512; text-to-image and other domains are left to future work.
- Evident from the text: DiTs use a frozen off-the-shelf VAE, so generation quality depends on that VAE; training hyperparameters were retained from ADM and not tuned; pixel-space DiT is mentioned as possible but not tested.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
28 Own result · 5 Own interpretation · 4 No basis given · 3 Sources not found · 2 Own method · 1 Partly supported · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As shown in Figure 2, LDMs achieve good performance while using a fraction of the Gflops of pixel space diffusion models like ADM.”
§ 3. Diffusion Transformers > 3.1. Preliminaries
What the sources say
- Partly supportedcites [48] sourceExperimental — accuracy not yet measured
Section 4.2 reports performance close to ADM on LSUN-Bedrooms while using four times fewer training resources, and Appendix D.4 describes competitive ImageNet performance with lower compute requirements. These passages support the performance-and-efficiency comparison, but our copy does not give a GFLOPs comparison with ADM; it reports training resources instead. (LLM, conf=0.85)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Larger DiT models are more compute-efficient.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Adaptive layer norm works best.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Transformer Gflops are strongly correlated with FID.”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Performance steadily improves in FID as model flops increase.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing transformer forward pass Gflops increases sample quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results demonstrate that different DiT configs obtain similar FID values when their total Gflops are similar (e.g., DiT-S/2 and DiT-B/4).”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, scaling both model size and the number of tokens yields notable improvements in visual quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all four configs, significant improvements in FID are obtained over all stages of training by making the transformer deeper and wider.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Scaling the transformer backbone yields better generative models across all model sizes and patch sizes.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 4
- Probably not a substantial claim. 6
- It may state two separate claims as one. 18
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Cross-attention adds the most Gflops to the model, roughly a 15% overhead.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“As with prior work using guidance, we observe that larger scales increase visual fidelity and decrease sample diversity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For both the 256 × 256 and 512 × 512 DiT-XL/2 models, we never observed FID saturate and continued training them as long as possible.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of the three block designs we explore, adaLN adds the least Gflops and is thus the most compute-efficient.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 2. Benchmarking class-conditional image generation on ImageNet 256×256. DiT-XL/2 achieves state-of-the-art FID.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When trained for only 2.35M steps (similar to ADM), XL/2 still outperforms all prior diffusion models with an FID of 2.55.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XL/2 again outperforms all prior diffusion models at this resolution, improving the previous best FID of 3.85 achieved by ADM to 3.04.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we did not find learning rate warmup nor regularization necessary to train DiTs to high performance.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the Gflops in the model—either by increasing transformer depth/width or increasing the number of input tokens—yields significant improvements in visual fidelity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find a strong negative correlation between model Gflops and FID-50K, suggesting that additional model compute is the critical ingredient for improved DiT models.”
- Also stated in: § 100 101 102 · boosted
“Transformer Gflops are strongly correlated with FID.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 100 101 102 · boosted
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, we also observe that DiT-XL/2 achieves higher recall values at all tested classifier-free guidance scales compared to LDM-4 and LDM-8.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing DiT model Gflops (via transformer size or number of input tokens) causes the training loss to decrease more rapidly and saturate at a lower value.”
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
“Note that scaled-up DiT models exhibit lower training losses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We did not tune learning rates, decay/warm-up schedules, Adam β1/β2 or weight decays.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“which have been shown to scale more effectively for visual recognition than traditional convolutional networks (e.g., ResNet [15]).”
What the sources say
- Not matchedcites [10] Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Even without these techniques, training was highly stable across all model configs and we did not observe any loss spikes commonly seen when training transformers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“diffusion models have been at the forefront of recent advances in image-level generative models [9,46]; yet, they all adopt a convolutional U-Net architecture as the de-facto choice of backbone.”
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [46] Ramesh, 2022, Hierarchical text-conditional image generation with clip latents
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“Note that prior work [9] measures Precision and Recall using 1000 real samples for 512 × 512 resolution; for consistency, we do the same.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 1,000- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“halving pwill quadruple T , and thus at least quadruple total transformer Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A smaller patch size p results in a longer sequence length and thus more Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper relies on this without support.
FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
“We show samples from the model in Figures 1, and we compare against state-of-the-art class-conditional generative models. We report results in Table 2.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Unlike prior works that employ text-to-image (T2I) U-Net [10, 33, 35, 40] for talking head generation, MoCha is built on a diffusion transformer (DiT) [26]. By incorporating text and speech conditions sequentially via cross-attention, it effectively captures both semantics and temporal dynamics.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [26]
In the citing paper
“Supervised learning, a foundational approach in AI, uses labeled datasets to guide models towards accurate predictions, and it has been integral to various applications, including image recognition and NLP [163], [164], [165].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [164]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Research works printed but not linked: 3
- Chen, Generative pre-training from pixels
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- Goodfellow, Generative adversarial nets
Cited by
Sorted by citations
Items 1,801–1,900 of 3,684
Soft Tail-Dropping for Adaptive Visual Tokenization
Chen, Z., Zhang, K., Tu, Z., & Xiong, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_24 · Cited by 2
Latent Gene Diffusion for Spatial Transcriptomics Completion
Cárdenas, P., Manrique, L., Vega, D., Ruiz, D., & Arbeláez, P. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00099 · Cited by 2
Accelerating Masked Image Generation by Learning Controlled Latent Dynamics
Zhu, K., Zeng, Q., Pu, Y., Cao, S., Li, X., Xin, Y., Qin, Q., Li, J., Yan, J., Qiao, Y., et al. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836027 · Cited by 2
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
Yehezkel, S., Yadin, S., Elata, N., Ostrovsky-Berman, Y., & Kawar, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_33 · Cited by 3
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
Wang, J., Tang, Y., Gong, J., Li, J., Li, S., Liu, L., Lan, J., Liu, Y., & Zhang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_6 · Cited by 2
Hu, Z., Wang, Q., Cao, T., Liao, L., Lu, L., Liu, L., Li, S., Chen, H., Xue, M., Chen, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37577-3_20 · Cited by 2
StructMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
Qian, Y., Cao, Y., Fu, H., Lv, M., & Zhu, M. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836046 · Cited by 2
Composing Driving Worlds Through Disentangled Control for Adversarial Scenario Generation
Zhan, Y., Chen, Z., Wang, Q., He, Z., Niu, M., Guo, X., Yin, W., Ren, W., Zhang, Q., & Zheng, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_25 · Cited by 2
Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation
Jin, M., Liao, M., Han, M., Li, Z., & Chang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37138-6_21 · Cited by 2
AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers
Xu, B., Wang, Y., Wang, Z., & Li, P. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i32.39936 · Cited by 2
Han, C., Yang, B., & Hu, J. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i17.38498 · Cited by 2
LibraGen: Playing a Balance Game in Subject-Driven Video Generation
Zhu, J., Lao, S., Liu, L., Li, G., Qi, T., Han, W., Li, B., Liu, F., Chen, Z., Ma, T., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_18 · Cited by 2
TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
Mao, J., Wang, K., Xiang, Y., & Chen, K. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i10.37738 · Cited by 2
OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
Gao, S., Wang, Z., Cao, Q. P., Yu, D., Wang, C., Liu, T., Gong, M., & Bian, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_6 · Cited by 2
SyncDIT: audio-visual aligned video generation with audio synchronization feature
Song, Q., Guo, Z., He, Y., Wang, Z., He, Z., Zhang, C., Jiang, C., & Li, X. (2026) · Vicinagearth. · doi:10.1007/s44336-026-00036-1 · Cited by 2
A Review of Photovoltaic Uncertainty Modeling Based on Statistical Relational AI
Yang, L., & Fu, X. (2026) · Energies · doi:10.3390/en19061509 · Cited by 2
Prabhakar, C., Wittmann, B., Amiranashvili, T., Büschl, P., de la Rosa, E., McGinnis, J., Wiestler, B., Menze, B. H., & Shit, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37520-9_8 · Cited by 2
FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal
Xu, T., Zhang, C., Zhai, G., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_30 · Cited by 2
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
Erkoç, Z., Dai, A., & Nießner, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37718-0_27 · Cited by 2
SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis
Zhao, B., Zhou, Q., Yang, C., Gao, J., & Wang, Q. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836460 · Cited by 2
Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
Perini, J., Bischof, R., Arar, M., Duran, A., Kraus, M. A., Mishra, S., & Bickel, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_12 · Cited by 2
WorldMesh: Generating Navigable Multi-room 3D Scenes via Mesh-Conditioned Image Diffusion
Schneider, M.-A., & Dai, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_7 · Cited by 2
Yang, L., Bai, Y., Wang, Y., Alsarraj, I., Gitta Kutyniok, B., Wang, Z., & Wu, K. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3677747 · Cited by 2
ColoDiff: Integrating Dynamic Consistency With Content Awareness for Colonoscopy Video Generation
Fu, J., Liang, S., Li, W., Ma, C., Huang, P. F., Wang, K., Chen, K., Lin, S., Zhou, P.-H., Li, Z., et al. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3678906 · Cited by 2
RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn Conversation
Chen, P., Wei, X., Yang, Y., Yao, N., Chen, H., & Tian, F. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3679919 · Cited by 2
ConceptWeaver: Weaving Disentangled Concepts with Flow
Chen, J., Hao, A., Chen, X., Bai, C., Chen, C., Li, Y., Wu, J., Chu, X., & Zhang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_4 · Cited by 2
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Shabanov, A., Hedman, P., Weber, E., Li, Z., Rozumnyi, D., Lan, G. L., Dhingra, N., Luo, L., Vedaldi, A., Richardt, C., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_25 · Cited by 2
FlowInOne: Unifying Multimodal Generation as Image-in, Image-Out Flow Matching
Yi, J., Zhao, R., Tang, J., Lei, W., Li, L., Su, Q., Yang, Z., Wang, L., Zhu, X., & Wang, A. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_14 · Cited by 2
Generating archaeological line drawings from limited reference images
Xue, J., Wang, X., Zhang, Q., Yang, X., & Li, C. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02526-3 · Cited by 2
From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
Mahdi, M., Savov, N., Paudel, D. P., & Gool, L. V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37383-0_8 · Cited by 2
Instrument Generation Through Distributional Flow Matching and Test-Time Search
Yang, Q., Leistikow, R. J., & Zang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462304 · Cited by 2
EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
Yu, Z., Shen, K., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37450-9_24 · Cited by 2
StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks
Huang, J., Yang, Q., Chen, F.-Y., McAuley, J., Leistikow, R. J., Cook, P. R., & Zang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461590 · Cited by 2
Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
Lin, J., Su, J., Anand, N., Jin, Z., Kim, M., & Smaragdis, P. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464833 · Cited by 2
FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning
Wang, H., Tian, B., Jiang, Y., Pan, Z., Zhao, S., Ma, B., Chen, D., & Li, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461623 · Cited by 2
Stemphonic: All-At-Once Flexible Multi-Stem Music Generation
Wu, S.-L., Zhu, G., Cáceres, J.-P., Huang, C.-Z. A., & Bryan, N. J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464473 · Cited by 2
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
Cole, A., & Grierson, M. (2026) · Creativity and Cognition · doi:10.1145/3803784.3807565 · Cited by 2
Shao, D., Wu, S., Wang, S., Wang, Y., Tang, Z., Liu, F., 姜, 琳., Chen, X., (32718), Q. W., Tai, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_12 · Cited by 2
MeshReGen: A Unified 3D Geometry Regeneration Framework
Park, G. Y., Shapovalov, R., Ranjan, R., Ye, J. C., Vedaldi, A., & Nguyen-Phuoc, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37517-9_16 · Cited by 2
Memory-Efficient Generative Models via Product Quantization
Shao, J., Zhang, H., Yu, H., & Wu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01567 · Cited by 2
VAFlow: Video-to-Audio Generation with Cross-Modality Flow Matching
Wang, X., Cheng, X., Wang, Y., Song, R., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01095 · Cited by 2
Concord: Concept-Informed Diffusion for Dataset Distillation
Gu, J., Wang, H., Jia, R., Vahidian, S., Kungurtsev, V., Jiang, W., & Chen, Y. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00510 · Cited by 2
The Learnability Gap in Medical Latent Diffusion
Dombrowski, M., Nützel, F., & Kainz, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_52 · Cited by 2
Climber-Pilot: A Non-Myopic Generative Recommendation Model Towards Better Instruction-Following
Guo, D., Wang, S., Xiao, Q., Ren, Y., Li, W., Xu, S., Yue, M., Huang, B., Wu, G., & Luo, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818340 · Cited by 2
VAR-3D: View-aware Auto-Regressive Model for Text-to-3D Generation via a 3D Tokenizer
Han, Z., Hong, Y., Sun, H., & Cao, D. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810588 · Cited by 2
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
Wang, S., Li, L., Chen, Y., Gao, R., Teng, Y., & Wang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_17 · Cited by 2
UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving
Zhao, B., Zhao, X., Li, N., Cheng, E., & Ling, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_16 · Cited by 2
Scaling Multi-reference Image Generation with Dynamic Reward Optimization
Huang, W., Fu, Y., Wang, J., Huang, M., Li, Y., Liu, G., Cai, J., He, Y., & Tian, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37520-9_27 · Cited by 2
PhyEditBench: A Real-World Multi-stage Benchmark for Physics-Aware Image Editing
Guo, S., He, S., Meng, C., Xiao, S., Xiang, X., Zhang, S., & Fan, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37083-9_30 · Cited by 2
ChronoFlow-Policy Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
Lin, B., Xu, Y., Zhan, X., Fang, H., Tian, J., Zhang, F.-C., Li, Y.-L., Lu, C., & Yang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_25 · Cited by 2
Su, Z., Hu, T., Zhang, J., Wang, R., Yi, R., Ma, L., & Tao, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_36 · Cited by 2
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Namekata, K., Kant, Y., Liu, Z., Burgert, R., Xu, Y., Lin, K. H., Steven, E., Philip, J., Ma, L., Vedaldi, A., et al. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811093 · Cited by 2
MeshFlow: Mesh Generation with Equivariant Flow Matching
Sun, Q., Nakayama, K., Yan, J. N., Huang, Q., Rush, A. M., Guibas, L. J., Wetzstein, G., Liao, J., & Yang, G. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811195 · Cited by 2
InnoText: A Unified Model for Visual Text Generation and Editing
Liu, H., He, R., Lu, J., Ma, A., Ling, R., Cao, K., Feng, J., Feng, W., Lu, S., Xu, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_7 · Cited by 2
EVBench: A Comprehensive Benchmark of Video Generative Models for E-commerce Scenarios
Chen, H., Zheng, J., Liu, K. J. R., Liu, X., Qu, L., Li, M., Liu, W., & Yan, C. C. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3830242 · Cited by 2
From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation
Yang, R., Li, X., Sheng, J., Cao, J., Lin, X., Wang, S., Yang, S., Liu, Z., & Liu, T. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780285 · Cited by 2
SIRR-LMM: Single-Image Reflection Removal via Large Multimodal Model
Guo, Y., Lao, Z., Song, X., Zhou, Y., & Yu, H. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00181 · Cited by 2
Toward a Foundation-Model Paradigm for Aerodynamic Prediction in Three-Dimensional Design
Yang, Y., Gholami, B., Guerbuez, C., Rashed, M., & Thuerey, N. (2026) · AIAA Journal · doi:10.2514/1.j066861 · Cited by 2
AnimateAnyMesh++: A Flexible Feed-Forward Framework for High-Fidelity Text-Driven Mesh Animation
Wu, Z., Yu, C., Wang, F., & Bai, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3724593 · Cited by 2
PolaFormer++: Polarity-Aware Linear Attention With Channel-Wise Spikiness
Meng, W., Luo, Y., Huo, L., Li, Y., Wang, Y., Zhang, Z., & Shen, H. T. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3723414 · Cited by 2
MSEditor: Toward Consistent Multi-shot Video Editing
Feng, K., Ma, Y., Wang, B., Wang, Y., Qin, Z., Cheng, H., Li, H., Chen, Q., & Wang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_5 · Cited by 2
LaCoOT: Layer Collapse through Optimal Transport
Quétu, V., Liao, Z., Hezbri, N., Pizzati, F., & Tartaglione, E. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01906 · Cited by 2
Complex Image-Generative Diffusion Transformer for Audio Denoising
Li, J., Wang, P., Li, J., & Zhang, Y. (2024) · Interspeech (USB) · doi:10.21437/interspeech.2024-611 · Cited by 2
A Simplified Query-Only Attention for Encoder-Based Transformer Models
Yeom, H. G., & An, K. (2024) · Applied Sciences · doi:10.3390/app14198646 · Cited by 2
DiffSurf: A Transformer-Based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose
Yoshiyasu, Y., & Sun, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73007-8_15 · Cited by 2
Extracting Thin Film Structures of Energy Materials Using Transformers
Zhang, C., Niemann, V. A., Benedek, P., Jaramillo, T. F., & Doucet, M. (2024) · ACS Physical Chemistry Au · doi:10.1021/acsphyschemau.4c00054 · Cited by 2
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
Wang, H., Wu, Y., Guo, S., & Wang, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3518762 · Cited by 2
SRC-gAudio: Sampling-Rate-Controlled Audio Generation
Li, C., Xu, M., & Yu, D. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10849319 · Cited by 2
Brain-Inspired Action Generation with Spiking Transformer Diffusion Policy Model
Wang, Q., Sun, Y., Lu, E., Zhang, Q., & Zeng, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2882-7_23 · Cited by 2
Exploratory Analysis of Modified Deep Learning Model for Potholes Data Augmentation
Adebiyi, R. F., Bello-Salau, H., Onumanyi, A. J., Adebiyi, B. H., Adekale, A. D., & Bello-Salahuddeen, R. (2025) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit63348.2025.10989435 · Cited by 2
Kaleidoscope Gallery: Exploring Ethics and Generative AI Through Art
Issak, A., Narayan, U., Srinivasan, R., Kleinman, E., & Harteveld, C. (2025) · Creativity and Cognition · doi:10.1145/3698061.3726929 · Cited by 2
Mobius: Text to Seamless Looping Video Generation via Latent Shift
Bi, X., Yuan, J., Liu, B., Zhang, Y., Cun, X., Pun, C., & Xiao, B. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730744 · Cited by 2
Towards Controllable Real Image Denoising With Camera Parameters
Oh, Y.-J., Kwon, J.-H., Lee, K., & Cho, N. I. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084351 · Cited by 2
Precise Action-to-Video Generation Through Visual Action Prompts
Wang, Y., Wen, C., Guo, H., Peng, S., Qin, M., Bao, H., Zhou, X., & Hu, R. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01181 · Cited by 2
Unleashing Diffusion and State Space Models for Medical Image Segmentation
Wu, R., Chen, Z., Zhong, L., Li, H., & Shu, H. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-01926-y · Cited by 2
Taxadiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
Monsefi, A. K., Khurana, M., Ramnath, R., Karpatne, A., Chao, W., & Zhang, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00803 · Cited by 2
ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image
Gong, T., Li, B., Zhong, Y., & Wang, F. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209941 · Cited by 2
SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusion
Xiang, Z., Li, Z., Khodabandeh, A., & Khoshelham, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02315 · Cited by 2
Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models
Wang, J., Yang, Z., Bai, Y., Li, Y., Zou, Y., Sun, B., Kundu, A., Lezama, J., Huang, L. Y., Zhu, Z., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247678 · Cited by 2
Layer-Aware Video Composition via Split-then-Merge
Kara, Ö., Chen, Y., Yan, S., Rehg, J. M., Chu, W., & Tran, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_7 · Cited by 2
Zhang, H., & Wan, X. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3771070 · Cited by 2
UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis
Wang, Y., Han, C., Li, Y., Jin, Z., Li, X., Du, S., Tao, W., Li, S., Yang, Y., Yuan, C. Y., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01704 · Cited by 2
FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
Yang, F., Zhu, Y., Li, X., Zhan, Y., Zhao, H., Zheng, S., Wang, Y., Tang, M., & Wang, J. (2025) · neural information processing systems · doi:10.52202/085713-1123 · Cited by 2
RadarGen: Automotive Radar Point Cloud Generation from Cameras
Borreda, T., Ding, F., Fidler, S., Huang, S., & Litany, O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_35 · Cited by 2
Multi-agent Auto-Bidding with Latent Graph Diffusion Models.
Huh, D., & Mohapatra, P. (2025) · ACM Conference on Research in Adaptive and Convergent Systems (RACS) · doi:10.1145/3769002.3769957 · Cited by 2
Mots’Oehli, M., Chen, F., Chan, H. W., Tlali, I., Babeli, T., Baek, K., & Chen, H. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00177 · Cited by 2
Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion
Zou, K., Feng, X., Huang, T., Huang, Z., Haihang, Z., Zou, Y., & Li, D. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00645 · Cited by 2
Wang, Y., Wu, Z., Li, C., & Wu, A. (2023) · neural information processing systems · doi:10.52202/075280-1694 · Cited by 3
PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution
Liu, Y., Dong, H., Pan, J., Dong, Q., Chen, K., Zhang, R., Fu, L., & Wang, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01050 · Cited by 2
GIGA: Generalizable Sparse Image-Driven Gaussian Humans
Zubekhin, A., Zhu, H., Gotardo, P. F. U., Beeler, T., Habermann, M., & Theobalt, C. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00086 · Cited by 2
You, R., Jia, H., & Xu, F. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3703726 · Cited by 2
Spatio-Temporal Parallelism for Diffusion Model Inference on Heterogeneous Multi-GPU Systems
Liang, H., Zhou, J., Zhou, Z., Zhang, X., & Chen, X. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00073 · Cited by 2
Improved DDIM Sampling with Moment Matching Gaussian MixturesPreprint
Gabbur, P. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.04938 · Cited by 2
DiffusionPipe: Training Large Diffusion Models with Efficient PipelinesPreprint
Tian, Y., Jia, Z., Luo, Z., Wang, Y., & Wu, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.01248 · Cited by 2
Tuning-Free Visual Customization via View Iterative Self-Attention ControlPreprint
Li, X., Gu, C., Xie, S., Bai, Y., Zhang, W., & Wang, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.06258 · Cited by 2
Self-citationLatent Diffusion Model for Multidisciplinary and Multi-Objective Airfoil Inverse DesignPreprint
Gong, Z., & Zhao, H. (2024) · doi:10.36227/techrxiv.172468827.77833794/v1 · Cited by 2
Accurate Compression of Text-to-Image Diffusion Models via Vector QuantizationPreprint
Egiazarian, V., Kuznedelev, D., Voronov, A. Y., Svirschevski, R., Goin, M., Pavlov, D., Alistarh, D., & Baranchuk, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.00492 · Cited by 2
AMG: Avatar Motion Guided Video GenerationPreprint
Yang, Z., Shan, M., Farazi, M., Zhu, W., Chen, Y., Dong, X., & Wang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.01502 · Cited by 2
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority GenerationPreprint
Um, S., Kim, B., & Ye, J. C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.06516 · Cited by 2
Vivat: Virtuous Improving Vae Training Through Artifact MitigationPreprint
Novitskiy, L., Vasilev, V., Kovaleva, M., Arkhipkin, V., & Dimitrov, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5333162 · Cited by 2
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
