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 1,101–1,200 of 3,684
DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers
Guimarães, H. R., Su, J., Kumar, R., Falk, T. H., & Jin, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463138 · Cited by 7
Feng, W., Yang, C., Qin, H., Li, Y., Li, X., An, Z., Huang, L., Diao, B., Zhuang, F., Magno, M., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3700583 · Cited by 7
OutDreamer: Video Outpainting With a Diffusion Transformer
Zhong, L., Li, F., Huang, Y., Liu, J., Pei, R., & Song, F. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3694129 · Cited by 7
Dataset Distillation Via Vision-Language Category Prototype
Zou, Y., Li, G., Su, D., Wang, Z., Yu, J., & Zhang, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00282 · Cited by 7
MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
Xue, H., Chen, Q., Wang, Z., Huang, X., Shechtman, E., Xie, J., & Chen, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_34 · Cited by 7
DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation
Lin, R., Wu, Z., Lei, J., Wang, K., Chen, W., Dai, J., & Jiang, T. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836425 · Cited by 7
OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
Shi, C., Wu, W., Shen, F., Zhu, X., Hu, K., & Wang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_30 · Cited by 7
Qin, Y., Luo, Z., Che, Y., & Cao, L. (2026) · Green Energy and Intelligent Transportation · doi:10.1016/j.geits.2026.100404 · Cited by 7
MemCam: Memory-Augmented Camera Control for Consistent Video Generation
Gao, X., Guan, J., Luo, S., Li, W., Tan, G., & Wang, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729191 · Cited by 7
ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor
Wang, Y., Jiang, T., Shao, Z., Ye, H., Sun, J., Ma, M., Wang, Q., Zhang, J., Chen, Y., & Li, H. H. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836067 · Cited by 7
Pro‐DG: Procedural Diffusion Guidance for Architectural Facade Generation
Płocharski, A., Swidzinski, J., & Musialski, P. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70487 · Cited by 7
GEM: Generative Supervision Helps Embodied Intelligence
Zhao, R., Li, B., Liu, Z., Liang, Y., Ye, J., Liu, F., Wu, D., Wang, Z., Yu, X., Rao, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_34 · Cited by 7
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
Guo, Z., Ma, L., He, Y., Fu, X., Fu, J., Huang, J. W., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_24 · Cited by 7
Learning Transferable Dynamics Priors from Action to World Modeling
Huang, Z. Z., Zhang, J., Liu, H. X., Zhang, C., Cheng, R., & Zhang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37550-6_25 · Cited by 7
SegviGen: Repurposing 3D Generative Model for Part Segmentation
Li, L., Feng, H., Huang, Z., Chen, H., Nie, W., Hou, S., Fan, K., Hu, P., Wang, S., Li, B., et al. (2026) · ACM Transactions on Graphics · doi:10.1145/3811399 · Cited by 7
YODA: Yet Another One-Step Diffusion-Based Video Compressor
Li, X., Zhang, J., Shi, J., Lu, M., & Ma, Z. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3714453 · Cited by 7
Learning to Generate Rigid Body Interactions with Video Diffusion Models
Romero, D., Bermúdez, A., Iablochnikov, V., Li, H., Pizzati, F., & Laptev, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_13 · Cited by 7
Li, Y., Chen, B., Ren, Z., Ding, Y.-X., Liu, L., Shao, T., & Zhou, K. (2024) · ACM Transactions on Graphics · doi:10.1145/3687932 · Cited by 7
Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation
Dao, Q. T., Phung, H., Dao, T., Metaxas, D., & Tran, A. N. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i3.32269 · Cited by 7
Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation
Xiang, T., Li, K., Long, C., Häne, C., Guo, P., Delp, S. L., Adeli, E., & Fei-Fei, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01531 · Cited by 7
Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion
Guo, B., Hong, Z., Li, J., Wang, S., & Zhao, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780191 · Cited by 7
JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
Kwon, M., Shin, J., Jeong, J., Park, J., & Uh, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_20 · Cited by 7
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
Dalva, Y., Qian, G., Goldenberg, M., Chen, T.-S., Aberman, K., Tulyakov, S., Yanardag, P., & Wang, K.-C. J. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811219 · Cited by 7
MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Albedo Post-Processing
Zhu, L., Ye, J., Zhang, R., Hu, Z., Yin, Y., Li, L., Chen, J., Qian, S., Wang, X. E., Liao, Q., et al. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3684391 · Cited by 7
Ma, J., Peng, Q., Guo, X., Chen, C., Lu, H., & Yang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01554 · Cited by 7
CausalDrive: Real-Time Causal World Models for Autonomous Driving
Yan, T., Zheng, H., Chen, D., Qu, M., Shen, Y., Zhou, L., Tu, M., Wang, B., Chen, G., Ye, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_8 · Cited by 7
Wang, L., Wu, C., & Wang, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3718223 · Cited by 7
Bertazzini, G., Albisani, C., Baracchi, D., Shullani, D., & Verdecchia, R. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116340 · Cited by 7
LaCon: Late-Constraint Controllable Visual Generation
Liu, C., Liu, D., Zhang, K., Lan, Y., Luo, X., & Liu, D. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3654412 · Cited by 7
StyleMamba: State Space Model for Efficient Text-Driven Image Style Transfer
Wang, Z., & Liu, Z.-S. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240554 · Cited by 7
Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
Guizilini, V., Irshad, M. Z., Chen, D., Shakhnarovich, G., & Ambruş, R. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00080 · Cited by 7
Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling
Kim, S., Oh, S. W., Wang, J.-H., Lee, J.-Y., & Shin, J. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00671 · Cited by 7
Toward Generating Realistic 3D Semantic Training Data for Autonomous Driving
Nunes, L., Marcuzzi, R., Behley, J., & Stachniss, C. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3669002 · Cited by 7
DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation
Di, D., He, F., Sun, W., Ma, Y., Li, H., Chen, W., Fan, L., Su, T., & Yang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01127 · Cited by 7
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?Preprint
Boutin, V., Fel, T., Singhal, L., Mukherji, R., Nagaraj, A., Colin, J., & Serre, T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.11722 · Cited by 7
Video Unlearning via Low-Rank Refusal VectorPreprint
Facchiano, S., Saravalle, S., Migliarini, M., Matteis, E. D., Sampieri, A., Pilzer, A., Rodolà, E., Spinelli, I., Franco, L., & Galasso, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.07891 · Cited by 7
LIA-X: Interpretable Latent Portrait AnimatorPreprint
Wang, Y., Yang, D., Chen, X., Brémond, F., Qiao, Y., & Dantcheva, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.09959 · Cited by 7
Privacy Attacks on Image AutoRegressive ModelsPreprint
Kowalczuk, A., Dubiński, J., Boenisch, F., & Dziedzic, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.02514 · Cited by 7
ViSSFlow: Unifying Video-Conditioned Sound and Speech Generation via Joint LearningPreprint
Cheng, X., Wang, Y., Wang, X., Wu, Y., Guan, K., Chen, Y., Zhang, P., Liu, X., Cao, M., & Song, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24773 · Cited by 7
Discrete Adjoint Schrödinger Bridge SamplerPreprint
(Way), W. G., Zhu, Y., Du, X., Nam, J., Chen, Y., Gómez‐Bombarelli, R., Liu, G.-H., Tao, M., & Choi, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.08243 · Cited by 7
The Diffusion Duality, Chapter II: $Ψ$-SamplersPreprint
Deschenaux, J., Gülçehre, Ç., & Sahoo, S. S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.21185 · Cited by 7
IRASim: A Fine-Grained World Model for Robot Manipulation
Zhu, F., Wu, H., Guo, S., Liu, Y., Cheang, C., & Kong, T. (2024) · arXiv · doi:10.48550/arxiv.2406.14540 · Cited by 6
Efficient Federated Learning With Quality-Aware Generated Models: An Incentive Mechanism
Zhang, H., Li, P., Dai, M., Wu, Y., & Qian, L. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3461329 · Cited by 6
Krishna, A., Wang, G., & Mueller, K. D. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/adb9b3 · Cited by 6
Multimodal feature‐guided diffusion model for low‐count PET image denoising
Lin, G., Jin, Y., Huang, Z., Chen, Z., Liu, H., Zhou, C., Zhang, X., Fan, W., Zhang, N., Liang, D., et al. (2025) · Medical Physics · doi:10.1002/mp.17764 · Cited by 6
MDiffSR: Mutual information and diffusion model in image super-resolution
Jiang, M., Fan, J., Huang, L., Jiang, Z., & Bu, Q. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130372 · Cited by 6
Lan, D., Zhang, G., & Guo, R. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3717376 · Cited by 6
DiSRT-In-Bed: Diffusion-Based Sim-To-Real Transfer Framework for In-Bed Human Mesh Recovery
Gao, J., Zheng, C., Jeni, L. A., & Erickson, Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00177 · Cited by 6
Knit-FLUX: Simulation of Knitted Fabric Images Based on Low-Rank Adaptation of Diffusion Models
Liu, X., Peng, J., Lu, Z., Wang, Y., & Liu, F. (2025) · Applied Sciences · doi:10.3390/app15168999 · Cited by 6
Zhang, Y., Zhou, Y. C., Zhang, L., Xu, Z., Feng, H., Zhou, Y., & Liu, R. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104101 · Cited by 6
Xie, Y., Xiong, W., Zhang, S., Li, Z., Johnson, B. C., & Zhu, H. (2026) · Energy · doi:10.1016/j.energy.2025.139886 · Cited by 6
Rogsplat: Robust Gaussian Splatting Via Generative Priors
Kong, H., Yang, X. X., & Wang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02387 · Cited by 6
10x Future of Filmmaking Empowered by AIGC
Wang, H., Smith, D., & Kudelska, M. (2024) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr62202.2024.00018 · Cited by 6
InDeepFake: A novel multimodal multilingual indian deepfake video dataset
Das, A. K., Bose, A., Manohar, P., Dutta, A., Naskar, R., & Chakraborty, R. S. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.07.002 · Cited by 6
Karaarslan, E., & Aydin, Ö. F. (2024) · doi:10.36227/techrxiv.170862194.43871446/v2 · Cited by 6
ViDA: Video Diffusion Transformer Acceleration with Differential Approximation and Adaptive Dataflow
Ding, L., Liu, J., Huang, S., & Dai, G. (2025) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1145/3658617.3697692 · Cited by 6
RealPortrait: Realistic Portrait Animation with Diffusion Transformers
Yang, Z., Wei, H., & Wang, Z. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i9.33012 · Cited by 6
Park, D., Park, H., Yeo, I., Kim, J., Lee, S., Lee, S., Shin, H., Pae, S.-I., Fan, D., Kung, J., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3633487 · Cited by 6
Authentic 4D Driving Simulation with a Video Generation Model
Wang, L., Zheng, W., Du, D., Zhang, Y., Ren, Y. Q., Jiang, H., Cui, Z., Yu, H., Zhou, J., & Zhang, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02683 · Cited by 6
OpenVid++: A Large-scale High-quality Dataset for Text-to-video Generation
Nan, K., Fan, T., Xie, R., Zhou, P., Zhang, Y., Li, X., Yang, J., Yang, Z., & Tai, Y. Y. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02989-8 · Cited by 6
Transferable adversarial sample purification by expanding the purification space of diffusion models
Ji, J., Gao, S., & Zhou, W. (2024) · The Visual Computer · doi:10.1007/s00371-023-03253-7 · Cited by 6
Nested Diffusion Processes for Anytime Image Generation
Elata, N., Kawar, B., Michaeli, T., & Elad, M. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00493 · Cited by 6
Shadow Removal based on Diffusion, Segmentation and Super-resolution Models
Li, C., Yang, B., Wu, Z., Gao, C., Yu, Y., & Zhou, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00611 · Cited by 6
Controllable All-Atom Protein Generation with Latent DiffusionPreprint
Lu, A. X., Yang, J., Long, Y., Lambert, T., Yan, W., Robinson, S. A., Yang, K., Gligorijević, V., Cho, K., Bonneau, R., et al. (2024) · Research Square · doi:10.1101/2024.12.02.626353 · Cited by 6
Masked latent transformer with random masking ratio to advance the diagnosis of dental fluorosis
Xu, H., Wu, Y. J., Wu, J., Xie, R., Gu, M., & Wang, R. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104496 · Cited by 6
FlexiD-Fuse: Flexible number of inputs multi-modal medical image fusion based on diffusion model
Xu, Y., Li, X., Wang, Y., Cheng, X., Li, H., & Tan, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128895 · Cited by 5
Controllable diffusion generated dataset and hybrid CNN–Mamba network for burned area segmentation
Fu, Y., Fang, W., & Fu, Z. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104057 · Cited by 6
A Diffusion-Guided Task Decomposition Framework for SAR-to-Optical Image Translation
Du, D., Gu, Y., & Liu, T. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3623105 · Cited by 6
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
Vontobel, T., Sadat, S., Salehi, F., & Weber, R. M. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763979 · Cited by 6
Object-centric Video Prediction with Mask-guided Spatiotemporal Diffusion
Han, C., Fan, J., Wu, N., Dai, J., Bao, H., & Lu, X. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1584-y · Cited by 6
RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation
Chen, Z., Li, Y., Wang, H., Chen, Z., Jiang, Z., Li, J., Wang, Q., Yang, J. J., & Tai, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01797 · Cited by 6
Bochtler, M. (2024) · BioEssays · doi:10.1002/bies.202400155 · Cited by 6
HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
Kumbong, H., Liu, X., Lin, T.-Y., Liu, M.-Y., Liu, X., Liu, Z., Fu, D. Y., Ré, C., & Romero, D. W. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00242 · Cited by 6
MedIENet: medical image enhancement network based on conditional latent diffusion model
Yuan, W., Feng, Y., Wen, T., Luo, G., Liang, J., Sun, Q., & Liang, S. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01909-5 · Cited by 6
Yamaguchi, R., & Yanai, . (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2641-0_18 · Cited by 6
Rethinking Cluster-Conditioned Diffusion Models for Label-Free Image Synthesis
Adaloglou, N., Kaiser, T., Michels, F., & Kollmann, M. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00355 · Cited by 6
Stefenon, S. F., Cristoforetti, M., & Cimatti, A. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11458-1 · Cited by 6
Li, S., Zhang, L., Wang, Z., Tian, J., Tan, C. W., Liu, Z., Yu, C. W., Xie, Q., Lu, H., Wang, H., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01836 · Cited by 6
ReactDiff: Latent Diffusion for Facial Reaction Generation
Li, J., Wang, S., Wang, X., Zhu, Y., Xiong, H., Zhuang, Z., & Wang, Q. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107596 · Cited by 6
Temporal Feature Matters: A Framework for Diffusion Model Quantization
Huang, Y., Gong, R., Liu, X., Liu, J., Li, Y., Lu, J., & Tao, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3585692 · Cited by 6
OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving
Tang, T., Ma, E., Zhou, X., Wang, L., Yan, T., Zhang, X., Zhan, K., Jia, P., Lang, X., Bian, J.-W., et al. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754772 · Cited by 6
LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization
Wu, R., Su, W., & Liao, J. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763964 · Cited by 6
VLAbot: A human Vision–Language–Action models interaction framework for robotic assembly
Wang, X., Dengxiong, X., Bai, S., Zheng, P., & Zhang, Y. (2026) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2026.103268 · Cited by 6
Zhao, Q., Wu, H., Hao, Y., Ye, Z., Li, J., Liu, X., & Zhou, K. (2025) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3676642.3736127 · Cited by 6
Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
Fang, K., Tao, Q., Huang, X., & Yang, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02156-x · Cited by 6
MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers
Ma, H., Mahdizadehaghdam, S., Wu, B., Fan, Z., Gu, Y., Zhao, W., Shapira, L., & Xie, X. S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00707 · Cited by 6
Li, B., Jiang, Y., & Tiwari, D. (2024) · ACM SIGEnergy Energy Informatics Review · doi:10.1145/3727200.3727224 · Cited by 6
CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
Ma, X., Liu, Y., Gao, T., Huang, Q., & Huang, H. F. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730638 · Cited by 6
Reducing Pilots in Channel Estimation With Predictive Foundation Models
Zhou, X., Liang, L., Ye, H., Zhang, J., Wen, C.-K., & Jin, S. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3698937 · Cited by 6
Move-in-2D: 2D-Conditioned Human Motion Generation
Huang, H., Zhou, Y., Wang, J.-H., Liu, D., Liu, F., Yang, M., & Xu, Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02120 · Cited by 6
ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
Luo, C. X., Song, S., Yan, S., Yu, Z. T., & Ge, Z. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755038 · Cited by 6
Taming Flow Matching With Unbalanced Optimal Transport Into Fast Pansharpening
Cao, Z., Zhong, Y., & Deng, L.-J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00269 · Cited by 6
DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-Rigid Shape Matching
Pierson, E., Li, L., Dai, A., & Ovsjanikov, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00544 · Cited by 6
Li, Q., Qiu, S., Koo, K. K., Han, J., & Bouyarmane, K. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00028 · Cited by 6
Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications
Qin, H.-L., Dai, J., Lu, G. S., Shao, S., Wang, S., Xu, T., Zhang, W., Zhang, P., & Letaief, K. B. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3690542 · Cited by 6
Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
Liu, J., Xin, Z., Fu, Y., Zhao, R., Lan, B., & Li, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01073 · Cited by 6
ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos
Soraki, R., Bharadhwaj, H., Farhadi, A., & Mottaghi, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_24 · Cited by 6
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Zhao, Z., Liu, Z., Cao, Y., Gong, S., Zhang, Z., Song, J., Deng, J., & Patras, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_10 · Cited by 6
Forecasting Motion in the Wild
Thakkar, N., Ginosar, S., Walker, J., Malik, J., Carreira, J., & Doersch, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_15 · Cited by 6
A universal vision transformer for fast calorimeter simulations
Favaro, L., Giammanco, A., & Krause, C. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae7179 · Cited by 6
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
