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 101–200 of 3,684
From Reusing to Forecasting: Accelerating Diffusion Models With Taylorseers
Liu, J., Chang, Z., Lyu, Y., Chen, J., & Zhang, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01471 · Cited by 97
VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video GenerationPreprint
Li, X. S., Chu, W., Wu, Y., Yuan, W., Liu, F., Zhang, Q., Li, F., Feng, H., Ding, E., & Wang, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.00398 · Cited by 91
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape PredictionPreprint
Wang, P., Tan, H., Bi, S., Xu, Y., Luan, F., Sunkavalli, K., Wang, W., Xu, Z., & Zhang, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.12024 · Cited by 91
Residential floor plans: Multi-conditional automatic generation using diffusion models
Zeng, P., Gao, W., Yin, J., Xu, P., & Lu, S. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105374 · Cited by 89
Denoising Diffusion Autoencoders are Unified Self-supervised Learners
Xiang, W., Hongyu, Y., Huang, D., & Wang, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01448 · Cited by 88
Hi3dgen: High-Fidelity 3D Geometry Generation From Images Via Normal Bridging
Ye, C., Wu, Y., Lu, Z., Chang, J., Guo, X., Zhou, J., Zhao, H., & Han, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02323 · Cited by 88
Foundation models and intelligent decision-making: Progress, challenges, and perspectives
Huang, J., Xu, Y., Wang, Q., Wang, Q., Liang, X., Wang, F., Zhang, Z., Wei, W., Zhang, B., Huang, L., et al. (2025) · The Innovation · doi:10.1016/j.xinn.2025.100948 · Cited by 87
DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous DrivingPreprint
Jia, X., You, J., Zhang, Z., & Yan, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.07656 · Cited by 87
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
Chen, Z., Tang, J., Dong, Y., Cao, Z., Hong, F., Lan, Y., Wang, T., Xie, H., Wu, T., Saito, S., 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/cvpr52734.2025.02475 · Cited by 86
Diffusion Model is Secretly a Training-Free Open Vocabulary Semantic Segmenter
Wang, J., Li, X., Zhang, J., Xu, Q., Zhou, Q., Yu, Q., Sheng, L., & Xu, D. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3551648 · Cited by 88
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
Cui, J., Li, H., Zhan, Y., Shang, H. L., Cheng, K., Ma, Y., Mu, S., Zhou, H., Wang, J., & Zhu, S. (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/cvpr52734.2025.01964 · Cited by 85
Chen, K., Han, T., Ling, F., Gong, J., Bai, L., Wang, X., Luo, J., Fei, B., Zhang, W., Chen, X., et al. (2025) · Communications Earth & Environment · doi:10.1038/s43247-025-02502-y · Cited by 85
Long Context Tuning for Video Generation
Guo, Y., Yang, C., Yang, Z., Ma, Z., Lin, Z., Yang, Z., Lin, D., & Lu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01605 · Cited by 83
OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving
Wang, L., Zheng, W., Ren, Y., Jiang, H., Cui, Z., Yu, H., & Lu, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3687468 · Cited by 88
Efficient training of large language models on distributed infrastructures: a survey
Duan, J., Zhang, S., Wang, Z., Jiang, L., Qu, W., Hu, Q., Wang, G., Weng, Q., Yan, H., Zhang, X., et al. (2026) · Vicinagearth. · doi:10.1007/s44336-026-00038-z · Cited by 84
Knowledge Diffusion for Distillation
Huang, T., Zhang, Y., Zheng, M., You, S., Wang, F., Qian, C., & Xu, C. (2023) · neural information processing systems · doi:10.52202/075280-2849 · Cited by 82
Language Modeling Materializes a World Model of Protein BiologyPreprint
Candido, S., Hayes, T., Derry, A., Rao, R., Lin, Z., Verkuil, R., Wu, B. Z., Lee, J. S., Bruguera, E. S., Keval, J. A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.03.729735 · Cited by 85
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
Huang, T., Zheng, W., Wang, T., Liu, Y., Wang, Z., Wu, J., Jiang, J., Li, H., Lau, R. W. H., Zuo, W., et al. (2025) · ACM Transactions on Graphics · doi:10.1145/3763330 · Cited by 81
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
Stein, G., Cresswell, J. C., Hosseinzadeh, R., Sui, Y., Ross, B. L., Villecroze, V., Liu, Z., Caterini, A. L., Taylor, E., & Loaiza-Ganem, G. (2023) · neural information processing systems · doi:10.52202/075280-0165 · Cited by 81
Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives
Liu, Y., Yue, J., Xia, S., Ghamisi, P., Xie, W., & Fang, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3464685 · Cited by 81
ST-LLM: Large Language Models Are Effective Temporal Learners
Liu, R., Li, C., Tang, H., Ge, Y., Shan, Y., & Li, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_1 · Cited by 82
Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model
Zheng, Z., Ermon, S., Kim, D., Zhang, L., & Zhong, Y. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3475824 · Cited by 80
UniScene: Unified Occupancy-centric Driving Scene Generation
Li, B., Guo, J., Liu, H., Zou, Y., Ding, Y., Chen, X., Zhu, H., Tan, F., Zhang, C., Wang, T., 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/cvpr52734.2025.01118 · Cited by 79
Lumina-Image 2.0: a Unified and Efficient Image Generative Framework
Qin, Q., Zhuo, L., Xin, Y., Du, R., Li, Z., Fu, B., Lu, Y., Li, X., Liu, D., Zhu, X., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01863 · Cited by 79
Latent Diffusion for Language Generation
Lovelace, J., Kishore, V., Wan, C., Shekhtman, E., & Weinberger, K. (2023) · neural information processing systems · doi:10.52202/075280-2492 · Cited by 82
GenTron: Diffusion Transformers for Image and Video Generation
Chen, S., Xu, M., Ren, J., Cong, Y., He, S., Xie, Y., Sinha, A., Luo, P., Xiang, T., & Pérez-Rúa, J.-M. (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/cvpr52733.2024.00616 · Cited by 84
3D and 4D World Modeling: A SurveyPreprint
Kong, L., Yang, W., Mei, J., Liu, Y., Liang, A., Zhu, D., Lu, D., Yin, W., Hu, X., Jia, M., et al. (2025) · arXiv (Cornell University) · doi:10.13140/rg.2.2.12518.28487 · Cited by 78
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Ye, C., Qiu, L., Gu, X., Zuo, Q., Wu, Y., Dong, Z., Bo, L., Xiu, Y., & Han, X. (2024) · ACM Transactions on Graphics · doi:10.1145/3687971 · Cited by 77
Hung, C.-Y., Majumder, N., Kong, Z., Mehrish, A., Bagherzadeh, A. A., Li, C., Valle, R., Catanzaro, B., & Poria, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.21037 · Cited by 84
Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
Wu, S., Zhang, W., Xu, L., Jin, S., Wu, Z., Tao, Q., Liu, W., Li, W., & Loy, C. C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01648 · Cited by 76
OmniGen: Unified Image Generation
Xiao, S., Wang, Y., Zhou, J., Yuan, H., Xing, X., Yan, R., Li, C., Wang, S., Huang, T., & Liu, Z. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.01241 · Cited by 75
MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., & Xu, Q. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02612 · Cited by 79
Refining Generative Process with Discriminator Guidance in Score-based Diffusion ModelsPreprint
Kim, D., Kim, Y., Kwon, S. J., Kang, W., & Moon, I. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.17091 · Cited by 74
DreamO: A Unified Framework for Image Customization
Mou, C., Wu, Y., Wu, W., Guo, Z., Zhang, P., Cheng, Y., Yiming, L., Ding, F., Zhang, S., Li, X., et al. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763956 · Cited by 73
Towards Large-Scale 3D Representation Learning with Multi-Dataset Point Prompt Training
Wu, X., Tian, Z., Wen, X., Peng, B., Liu, X., Yu, K., & Zhao, H. (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/cvpr52733.2024.01849 · Cited by 72
Latent Diffusion Model without Variational AutoencoderPreprint
Shi, M., Wang, H., Zheng, W., Yuan, Z., Wu, X., Wang, X., Wan, P., Zhou, J., & Lu, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.15301 · Cited by 71
When Does Sora Show: The Beginning of TAO to Imaginative Intelligence and Scenarios Engineering
Wang, F., Miao, Q., Li, L., Ni, Q., Li, X., Li, J., Fan, L., Tian, Y., & Han, Q. (2024) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2024.124383 · Cited by 70
Meng, Z., Xie, Y., Peng, X., Han, Z., & Jiang, H. (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/cvpr52734.2025.02594 · Cited by 70
VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
Liu, R., Wu, H., Zheng, Z., Wei, C., He, Y., Pi, R., & Chen, Q. (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/cvpr52734.2025.00750 · Cited by 71
Dong, S., Wang, S., Liu, S., Cai, L., Fan, Q., Kannala, J., & Yang, Y. (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/cvpr52734.2025.01560 · Cited by 69
Epona: Autoregressive Diffusion World Model for Autonomous Driving
Zhang, K., Tang, Z., Hu, X., Pan, X., Guo, X., Liu, Y., Huang, J., Yuan, L., Zhang, Q., Long, X., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02527 · Cited by 70
Hunyuan-GameCraft-2: Instruction-following Interactive Game World ModelPreprint
Tang, J., Liu, J., Li, J., Wu, L., Yang, H., Zhao, P., Gong, S., Yuan, X., Shao, S., Zhang, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.23429 · Cited by 72
CaloDREAM – Detector response emulation via attentive flow matching
Favaro, L., Ore, A., Schweitzer, S. P., & Plehn, T. (2025) · SciPost Physics · doi:10.21468/scipostphys.18.3.088 · Cited by 68
VACE: All-in-One Video Creation and Editing
Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., & Liu, Y. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01597 · Cited by 68
MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
Zhu, R., Tu, Z., Liu, J., Bovik, A. C., & Fan, Y. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3501855 · Cited by 67
360-degree Human Video Generation with 4D Diffusion Transformer
Shao, R., Pang, Y., Zheng, Z., Sun, J., & Liu, Y. (2024) · ACM Transactions on Graphics · doi:10.1145/3687980 · Cited by 67
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
Chen, L., Meng, Y., Tang, C., Ma, X., Jiang, J., Wang, X., Wang, Z., & Zhu, 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/cvpr52734.2025.02636 · Cited by 67
ImageFolder: Autoregressive Image Generation with Folded TokensPreprint
Li, X., Qiu, K., Chen, H., Kuen, J., Gu, J., Raj, B., & Lin, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.01756 · Cited by 67
Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective
Li, O., Cai, J., Hao, Y., Jiang, X. H., Hu, Y., & Feng, F. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709392 · Cited by 66
AETHER: Geometric-Aware Unified World Modeling
Zhu, H., Wang, Y., Zhou, J., Chang, W., Zhou, Y., Li, Z., Chen, J., Shen, C., Pang, J., & He, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00799 · Cited by 66
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Kodaira, A., Xu, C., Hazama, T., Yoshimoto, T., Ohno, K., Mitsuhori, S., Sugano, S., Cho, H., Liu, Z., Tomizuka, M., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01150 · Cited by 66
Chen, Y., Wang, Y., & Zhang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02496 · Cited by 68
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
Hou, Z., Zhang, T., Xiong, Y., Duan, H., Pu, H., Tong, R., Zhao, C., Zhu, X., Qiao, Y., Dai, J., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00721 · Cited by 66
CameraCtrl II: Dynamic Scene Exploration via Camera-Controlled Video Diffusion Models
He, H., Yang, C., Lin, S., Xu, Y., Wei, M., Gui, L., Zhao, Q., Wetzstein, G., Jiang, L., & Li, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01246 · Cited by 66
A Unified Framework for U-Net Design and Analysis
Williams, C., Falck, F., Deligiannidis, G., Holmes, C. C., Arnaud Doucet, B., & Syed, S. (2023) · neural information processing systems · doi:10.52202/075280-1206 · Cited by 66
Zheng, K. P., Sun, Z., Song, Y. L., Zhang, C., Zhang, C., Chang, F., Yang, D., & Fu, X. (2025) · Energies · doi:10.3390/en18030503 · Cited by 70
The role of large language models in agriculture: harvesting the future with LLM intelligence
Shaikh, T. A., Rasool, T., Veningston, K., & Yaseen, S. M. (2024) · Progress in Artificial Intelligence · doi:10.1007/s13748-024-00359-4 · Cited by 67
Diffusion models for robotic manipulation: a survey
Wolf, R., Shi, Y., Liu, S., & Rayyes, R. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1606247 · Cited by 67
The Ingredients for Robotic Diffusion Transformers
Dasari, S., Mees, O., Zhao, S., Srirama, M. K., & Levine, S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127493 · Cited by 67
Golden Noise for Diffusion Models: A Learning Framework
Zhou, Z., Shao, S., Bai, L., Zhang, S., Xu, Z., Han, B., & Xie, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01643 · Cited by 65
VDT: General-purpose Video Diffusion Transformers via Mask ModelingPreprint
Lu, H., Yang, G., Fei, N., Huo, Y., Lu, Z., Luo, P., & Ding, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.13311 · Cited by 65
Relay Diffusion: Unifying diffusion process across resolutions for image synthesisPreprint
Teng, J., Zheng, W., Ding, M., Hong, W., Wangni, J., Yang, Z., & Tang, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.03350 · Cited by 65
Hyper-ConnectionsPreprint
Zhu, D., Huang, H., Huang, Z., Zeng, Y., Mao, Y., Wu, B., Min, Q., & Zhou, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.19606 · Cited by 65
Efficient Diffusion Models: A Comprehensive Survey From Principles to Practices
Ma, Z., Zhang, Y., Jia, G., Zhao, L., Ma, Y., Ma, M., Liu, G., Zhang, K., Ding, N., Li, J., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3569700 · Cited by 72
Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation
Huang, H. K., Sun, L., Du, B., & Lyu, W. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3416328 · Cited by 69
Stable Flow: Vital Layers for Training-Free Image Editing
Avrahami, O., Patashnik, O., Fried, O., Nemchinov, E., Aberman, K., Lischinski, D., & Cohen‐Or, D. (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/cvpr52734.2025.00738 · Cited by 64
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Chen, J., Xue, S., Zhao, Y., Yu, J., Paul, S., Chen, J., Cai, H., Han, S., & Xie, E. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01502 · Cited by 64
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
Ren, S., Yu, Q., Ju, H., Shen, X., Yuille, A., & Chen, L.-C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01464 · Cited by 64
CompoDiff: Versatile Composed Image Retrieval With Latent DiffusionPreprint
Gu, G., Chun, S., Kim, W., Jun, H., Kang, Y., & Yun, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.11916 · Cited by 64
Transferable deep generative modeling of intrinsically disordered protein conformations
Janson, G., & Feig, M. (2024) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1012144 · Cited by 62
Kandinsky: An Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
Razzhigaev, A., Shakhmatov, A., Maltseva, A., Arkhipkin, V., Pavlov, I., Ryabov, I., Kuts, A. L., Panchenko, A., Кузнецов, А. В., & Dimitrov, D. (2023) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2023.emnlp-demo.25 · Cited by 62
Adaptive Caching for Faster Video Generation With Diffusion Transformers
Kahatapitiya, K., Liu, H., He, S., Liu, D., Jia, M., Zhang, C., Ryoo, M. S., & Xie, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01414 · Cited by 62
LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
Lyu, J., Liu, K., Zhang, X., Liao, H., Feng, Y., Zhu, W., Shen, T., Chen, J., Zhang, J., Dong, Y., et al. (2026) · Robotics: Science and Systems · doi:10.15607/rss.2026.xxii.210 · Cited by 65
Diffusion Models and Representation Learning: A Survey
Fuest, M., Ma, P., Gui, M., Schusterbauer, J., Hu, V. T., & Ommer, B. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3658965 · Cited by 60
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed SamplingPreprint
Sadat, S., Buhmann, J., Bradley, D., Hilliges, O., & Weber, R. M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.17347 · Cited by 60
ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
Song, W., Zhou, Z., Zhao, H., Chen, J., Ding, P., Yan, H., Huang, Y., Tang, F., Wang, D., & Li, H. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i22.38921 · Cited by 60
Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale DatasetPreprint
Agrawal, V., Akinyemi, A., Alvero, K., Behrooz, M., Buffalini, J., Carlucci, F. M., Chen, J., Chen, J., Chen, Z., Cheng, S., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.22554 · Cited by 59
Diffusion Models Without Attention
Yan, J. N., Gu, J., & Rush, A. M. (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/cvpr52733.2024.00787 · Cited by 62
Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
Cao, C., Zhou, J., Li, S., Liang, J., Yu, C., Wang, F., Xue, X., & Fu, Y. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763842 · Cited by 57
Yu, B. X. B., Chang, J., Wang, H., Liu, L., Wang, S., Wang, Z., Lin, J., Xie, L., Li, H., Lin, Z., et al. (2024) · ACM Computing Surveys · doi:10.1145/3657632 · Cited by 58
A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning
Ji, Y., Li, J., Xiang, Y., Ye, H., Wu, K., Kai, Y., Xu, J., Mo, L., & Zhang, M. (2026) · Computational Linguistics · doi:10.1162/coli.a.629 · Cited by 58
Toward Real-World Blind Face Restoration With Generative Diffusion Prior
Chen, X., Tan, J., Wang, T., Zhang, K., Luo, W., & Cao, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3383659 · Cited by 59
Lee, S.-H., Choi, H.-Y., Kim, S.-B., & Lee, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3584944 · Cited by 57
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Wang, M., Wang, Q., Jiang, F., Fan, Y., Zhang, Y., Qi, Y., Zhao, K., & Xu, M. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755217 · Cited by 57
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
Liu, S., Ren, Z., Gupta, S., & Wang, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73007-8_21 · Cited by 56
ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance
Wang, C., Lu, G., Yang, J., Huang, R., Han, J., Hou, L., Zhang, W., & Xu, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02007 · Cited by 56
Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
Chen, R., Zhang, J., Liang, Y., Luo, G., Li, W., Liu, J., Li, X., Long, X., Feng, J., & Tan, P. (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/cvpr52734.2025.01515 · Cited by 58
Wang, H., Liu, Z. Q., Sun, K., Wang, X., Shen, D. G., & Cui, Z. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3585372 · Cited by 55
Rethinking Token-Wise Feature Caching: Accelerating Diffusion Transformers With Dual Feature Caching
Zou, C., Zheng, S., Zhang, E., Guo, R., Xu, H., Shi, Z., He, C., Hu, X., & Zhang, L. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3698363 · Cited by 55
Any2anytryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks
Guo, H., Zeng, B., Song, Y., Zhang, W., Liu, J., & Zhang, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01774 · Cited by 55
MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
Huang, Z., Guo, Y., An, X., Yang, Y., Li, Y., Zou, Z., Ding, L., Liu, X., Cao, Y., & Sheng, L. (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/cvpr52734.2025.02202 · Cited by 54
Diffusion Model-Based Video Editing: A Survey
Sun, W., Tu, R.-C., Liao, J., & Tao, D. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03040-6 · Cited by 54
From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications
Jiang, F., Pan, C., Wang, K., Michiardi, P., Dobre, O. A., & Debbah, M. (2026) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2026.3660010 · Cited by 53
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation
Mo, S., Xie, E., Chu, R., Hong, L., Nießner, M., & Li, Z. (2023) · neural information processing systems · doi:10.52202/075280-2973 · Cited by 53
MOVA: Towards Scalable and Synchronized Video-Audio GenerationPreprint
OpenMOSS Team, Yu, D., Chen, M., Chen, Q., Luo, Q., Wu, Q., Cheng, Q., Li, R., Liang, T., Zhang, W., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.08794 · Cited by 53
Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
Li, H., Shen, C., Torr, P. H. S., Volker Tresp, C., & Gu, J. (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/cvpr52733.2024.01141 · Cited by 56
ConsistentID: Portrait Generation With Multimodal Fine-Grained Identity Preserving
Huang, J., Dong, X. M., Song, W., Zheng, C., Tang, Z., Zhou, J., Cheng, Y., Chen, L., Li, H., Yan, Y., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3652557 · Cited by 52
Long-Context State-Space Video World Models
Po, R., Nitzan, Y., Zhang, R., Chen, B., Dao, T., Shechtman, E., Wetzstein, G., & Huang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00817 · Cited by 52
ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning
Zhang, D. J., Paiss, R., Zada, S., Karnad, N., Jacobs, D. E., Pritch, Y., Mosseri, I., Shou, M. Z., Wadhwa, N., & Ruiz, N. (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/cvpr52734.2025.00197 · Cited by 51
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Li, L., Huang, Z., Feng, H., Zhuang, G., Chen, R., Guo, C., & Sheng, L. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00126 · Cited by 51
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
