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 1,201–1,300 of 3,684
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Mei, Y., Guo, L., Ming-ming, Y., Zhao, G., He, X., & Liu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_21 · Cited by 6
MemLearner: Learning to Query Context Memory for Video World Models
Yu, J., Gao, Bai, J., Qin, Y., Huang, K., Liu, Q., Wang, X., Wan, P., Gai, K., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37595-7_6 · Cited by 6
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Yang, J., Di, D., Zhang, X., Fan, L., Cui, J., Li, H., & Ma, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_16 · Cited by 6
YaART: Yet Another ART Rendering Technology
Kastryulin, S., Konev, A., Shishenya, A., Lyapustin, E., Александрович, Х. А., Tselousov, A., Vinokurov, N., Kuznedelev, D., Markovich, A., Livshits, G. B., et al. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709404 · Cited by 6
Diffusion Model Patching via Mixture-of-Prompts
Ham, S., Woo, S., Kim, J., Go, H., Park, B., & Kim, C. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i16.33871 · Cited by 6
AvatarArtist: Open-Domain 4D Avatarization
Liu, H., Wang, X., Wan, Z., Ma, Y., Chen, J., Fan, Y., Shen, Y., Song, Y., & 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/cvpr52734.2025.01005 · Cited by 6
Latent Diffusion Models With Masked Autoencoders
Lee, J., Shin, J., Choi, H. W., & Lee, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01618 · Cited by 6
DC-Gen: Post-training Diffusion Acceleration with Deeply Compressed Latent Space
He, W. L., Gu, Y., Chen, J., Wu, J., Ge, W., Zou, D., Lin, Y., Zhang, Z., Xi, H., Li, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37196-6_14 · Cited by 6
DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering
Zheng, R., Zhang, Q., Long, C., & Zheng, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00963 · Cited by 6
RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals
Heo, J., Fozilov, E., Song, H., & Kim, T.-H. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.1182 · Cited by 6
What Makes for Text to 360-Degree Panorama Generation with Stable Diffusion?
Ni, J., Zhang, C.-B., Zhang, Q., & Zhang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01537 · Cited by 6
Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention
Ai, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_6 · Cited by 6
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
Fu, M., Wang, G.-H., Cui, T., Chen, Q.-G., Xu, Z., Luo, W., & Zhang, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37550-6_27 · Cited by 6
StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data
Mu, Y., Ling, H. Y., Shi, Y., Ojeda, I. B., Xi, P., Shu, C., Zinno, F., & Peng, X. B. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763817 · Cited by 6
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Liu, F., Li, H., Chi, J., Wang, H., Yang, M., Wang, F., & Duan, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02694 · Cited by 6
The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation
Yin, A., Tan, X., Shen, K., Leng, Y., Zhou, X., Li, J., & Tang, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01448 · Cited by 6
Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details
Medi, T., Wang, H., Rampini, A., & Keuper, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37032-7_7 · Cited by 6
GarmentX: Autoregressive parametric representations for 3D garment generation
Guo, J., Chen, J., Chen, W., Sun, Z., Li, L., Zhao, B., Zhu, L., Wang, X., & Liu, Q. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114937 · Cited by 6
Fillerbuster: Unified Generative Scene Completion Model for Casual Captures
Weber, E., Muller, N. E., Kant, Y., Agrawal, V., Zollhöfer, M., Kanazawa, A., & Richardt, C. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00057 · Cited by 6
Scaling Diffusion Mamba with Bidirectional SSMs for Efficient 3D Shape Generation
Mo, S. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i18.34144 · Cited by 6
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
Vallaeys, T., Verbeek, J. J., & Cord, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37556-8_19 · Cited by 6
GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model
Li, R., Zhang, X., Tong, C., Xu, Z., & Zhang, J. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1588-7 · Cited by 6
Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers
Srivastava, D., Zhang, X., He, W., Wen, C., & Tu, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01664 · Cited by 6
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
Kim, D., Zhang, J., Jin, W., Cho, S., Dai, Q., Park, J., & Luo, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_32 · Cited by 6
Model as a Game: On Numerical and Spatial Consistency for Generative Games
Chen, J., Zhao, Y., Huang, Y., Cui, L., Dong, L. M., Lv, T., Chen, Q., & Wei, F. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00205 · Cited by 6
Locality-Aware Generalizable Implicit Neural Representation
Lee, D., Kim, C., Cho, M., & Han, W.-S. (2023) · neural information processing systems · doi:10.52202/075280-2097 · Cited by 8
Latent-Reframe: Enabling Camera Control for Video Diffusion Models Without Training
Zhou, Z., An, J., & Luo, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01187 · Cited by 6
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single ImagePreprint
Li, J., Liu, S., Liu, Z., Wang, Y., Zheng, K., Xu, J., Li, J., & Zhu, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.02826 · Cited by 6
DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 frameworkPreprint
Zhang, F., Ji, N., Gao, F., Zhao, B., Wu, J., Jiang, Y., Du, H., Ye, Z., Zhu, J., Zhong, W., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.00370 · Cited by 6
LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid LibraryPreprint
Yu, T., Cai, Y., Sun, Z., Feng, S., Zhang, L., Lyu, K., Bai, X., Liu, A., Zhang, X., Zou, J., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.06150 · Cited by 6
FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the EdgePreprint
Shen, X. J., Ma, W., Zhou, Y., Tang, E., Xie, Y., Li, Z., Gong, Y., Wang, Q., Ding, H., Wang, Y., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.14709 · Cited by 6
X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion LatentsPreprint
Song, G., Xu, H., Zhao, X., Xie, Y. X., Gu, T., Li, Z., Zhang, C., & Luo, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.09383 · Cited by 6
Speech Editing -- a SummaryPreprint
Kässmann, T., Liu, Y., & Liu, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.17172 · Cited by 6
LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion TransformerPreprint
Fei, S., Tian, Y., Wang, L., & Zhu, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.22414 · Cited by 6
UniTok-Audio: A Unified Audio Generation Framework via Generative Modeling on Discrete Codec TokensPreprint
Liu, C., Yan, H., Xue, S., Liang, X., Liu, Y., Xue, Z., Song, G., & Zhou, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.26372 · Cited by 6
Laminating Representation Autoencoders for Efficient DiffusionPreprint
Calvo-González, R., & Fleuret, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.04873 · Cited by 6
Latent Generative Solvers for Generalizable Long-Term Physics SimulationPreprint
Chen, Z., & Deng, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.11229 · Cited by 6
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy AnalysisPreprint
Gao, J., Zheng, T., Zou, J., Yang, F., Liu, S., Fan, L., Zhang, Z., Zhang, H., Chen, J., Jiang, P.-T., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.08155 · Cited by 6
Qantara: Bridge-Flow Training for Multi-Paradigm JEPA InferencePreprint
Rakhimov, R., Bredis, G., Maksyuta, Y., & Gavrilov, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.04978 · Cited by 7
Chen, N., Xu, T., Sun, M., Yao, C., & Yang, D. (2025) · Intelligent Computing · doi:10.34133/icomputing.0143 · Cited by 5
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
NVIDIA, :, Bjorck, J., Castañeda, F., Cherniadev, N., Da, X., Ding, R., Fan, L. "., Fang, Y., Fox, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.14734 · Cited by 10
How Far is Video Generation from World Model: A Physical Law Perspective
Kang, B., Yue, Y., Lu, R., Lin, Z., Zhao, Y., Wang, K., Huang, G., & Feng, J. (2024) · arXiv · doi:10.48550/arxiv.2411.02385 · Cited by 7
“Following Sora (Brooks et al., 2024), we directly use the DiT architecture (Peebles & Xie, 2023) as the denoising model.”
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
Chen, J., Long, F., An, J., Qiu, Z., Yao, T., Luo, J., & Mei, T. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i2.32205 · Cited by 12
Wang, B., Wang, C., Chen, J., Liu, D., Sun, C., Zhang, J., Zhang, K., & Li, H. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01198-9 · Cited by 5
Gabrielidis, H., Gatti, F., & Vialle, S. (2025) · Computer Physics Communications · doi:10.1016/j.cpc.2025.109930 · Cited by 5
CausalGeD: Blending Causality and Diffusion for Spatial Gene Expression Generation
Sadia, R. T., Ahamed, M. A., & Cheng, Q. S. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736875 · Cited by 5
DiffChar: A fast conditional diffusion model for air-writing Chinese character generation
Zhao, W., Wu, M., & Wang, W. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112307 · Cited by 5
Song, H., Xu, L., Wang, Y., Wu, X., Wang, M., & Wang, Z. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10557837 · Cited by 5
Xu, Y., Zhai, B., Zhang, C., Li, M., Li, Y., & Du, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102869 · Cited by 5
Scaling AI filmmaking with collaborative networking
Wang, H., Smith, D., & Demir, U. (2025) · IET Communications · doi:10.1049/cmu2.12877 · Cited by 5
Scoring structure regularized gradient boosting network for blind image quality assessment
Wang, L., Wu, Q., Meng, F., Wang, Z., Wu, C., Wei, H., & Ngan, K. N. (2025) · Displays · doi:10.1016/j.displa.2024.102955 · Cited by 5
Yi, L., Liu, S., Zhou, L., Ning, Z., Song, J., Chen, Q., Zhang, K., & Ding, J. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3527809 · Cited by 5
Chikwendu, I. A., Zhang, X., Monday, H. N., Nneji, G. U., Ukwuoma, C. C., Chikwendu, O. C., Gu, Y. H., & Al–antari, M. A. (2025) · Electronics · doi:10.3390/electronics14061158 · Cited by 5
Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion
Gao, G., Liu, W., & Zhang, X. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3561516 · Cited by 5
Wang, C., Liu, G., & Zhu, L. X. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113763 · Cited by 5
Near-Field Channel Estimation for XL-MIMO via IDiT-Based Variance Exploding SDE Generator
Fang, Y., Xu, S., Fang, P., Zhang, J., Huang, Y., & Yang, L. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3604846 · Cited by 5
Generation of Clinical Skin Images with Pathology with Scarce Data
Borghesi, A., & Calegari, R. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-63592-2_5 · Cited by 5
Munia, N., & Imran, A.-A.-Z. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980892 · Cited by 5
Liu, R., Chen, Q., Liu, Y., Shi, Z., Li, Z., Jiang, W., & Li, D. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3592738 · Cited by 5
AirScape: An Aerial Generative World Model with Motion Controllability
Zhao, B., Tang, R., Jia, M., Wang, Z., Man, F., Zhang, X., Shang, Y., Zhang, W., Wu, W., Gao, C., et al. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758180 · Cited by 5
Towards Interactive Deepfake Analysis
Qin, L., Jiang, N., Zhang, Y., Qiu, Y., Zeng, D., Hu, J., & Deng, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888337 · Cited by 5
Cross‐Modal Denoising and Integration of Spatial Multi‐Omics Data with CANDIES
Liu, Y., Zou, W., Li, Y., Wang, J., Cai, M., & Cai, H. (2026) · Advanced Science · doi:10.1002/advs.202523754 · Cited by 6
Generation of Infrastructure Crack Images for Self-Supervision Training Based on Diffusion Model
Qin, S., Fang, Y., Li, Y., & Li, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3597284 · Cited by 5
Wang, H., Yeo, Y., Paiva, A. R., Goodman, J. P., Utke, J., & Monache, M. L. D. (2025) · Accident Analysis & Prevention · doi:10.1016/j.aap.2025.108226 · Cited by 5
Hwang, J., Lee, J., & Lee, 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/cvpr52733.2024.00836 · Cited by 6
ELGAR: Expressive Cello Performance Motion Generation for Audio Rendition
Qiu, Z., Jin, Y., Wang, Y., Shi, Y., Tan, C., Wang, C. Q., Li, X., Yu, F., Yu, T., & Dai, Q. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730756 · Cited by 5
AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
Guan, J., Wang, K., Xu, Z., Yang, Q., Sun, Y., He, S., Liang, B., Cao, Y., Li, Y., Feng, 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/cvpr52734.2025.00998 · Cited by 6
Zhang, M., Liu, C., Zhang, Y., & Wei, H. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3605587 · Cited by 5
Deep Learning for 3D Fashion Design: A Survey From a Sewing Pattern-Driven Perspective
Luo, J., Qu, H., Zhao, Y., Zhang, J., & Yang, Y. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3637565 · Cited by 5
Chen, Z. S., Lu, B., & Wu, W. (2025) · IEEE Signal Processing Magazine · doi:10.1109/msp.2025.3595320 · Cited by 5
QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing
Shen, T., Huang, Z., Li, X., Lin, Z., Liu, J., Wang, Y., Feng, J., Yang, M., & Liew, J. H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01770 · Cited by 5
Denoising Token Prediction in Masked Autoregressive Models
Yao, T., Li, Y., Pan, Y., Qiu, Z., & Mei, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01675 · Cited by 5
Anchored Diffusion for Video Face Reenactment
Kligvasser, I., Cohen, R., Leifman, G., Rivlin, E., & Elad, M. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00402 · Cited by 5
Diffusion‐Based Subsurface CO2 ${\text{CO}}_{2}$ Multiphysics Monitoring and Forecasting
Huang, X., Wang, F., & Alkhalifah, T. A. (2025) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2025jh000603 · Cited by 5
Generating functional and multistate proteins with a multimodal diffusion transformerPreprint
Jing, B., Sappington, A., Bafna, M., Shah, R., Tang, A., Krishna, R., Klivans, A. R., Diaz, D. J., & Berger, B. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.03.672144 · Cited by 5
Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
Delatolas, T., Kalogeiton, V. S., & Papadopoulos, D. P. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00248 · Cited by 5
Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Liu, K., Mei, J., Zhang, H., Zhang, Y., Dong, D., & He, L. (2025) · International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE) · doi:10.1145/3746278.3759378 · Cited by 5
A comprehensive survey of computer vision methods for spatial transcriptomics
Zhu, J., Deng, R., Guo, J., Yao, T., Lu, S., Qu, C., Xiong, J., Zhu, Y., Lu, Z., Yang, Y., et al. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag255 · Cited by 5
Intelligent Psyllid Monitoring Based on DiTs-YOLOv10-SOD
Zhang, L., Liang, Q., John, V., Chen, H., Li, S., Li, W., & Chen, Y. (2025) · IEEE Transactions on AgriFood Electronics · doi:10.1109/tafe.2025.3551072 · Cited by 5
Mueller, P., Wiese, J., Craciun, I., & Mikelsons, L. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00071-2_16 · Cited by 5
HGDiffuser: Efficient Task-Oriented Grasp Generation via Human-Guided Grasp Diffusion Models
Huang, D., Dong, W., Tang, C., & Zhang, H. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247551 · Cited by 5
Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs
Zhu, Z., Li, H., Ren, W., Wu, M., Ye, L., Huang, R., & Jia, T. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10993224 · Cited by 5
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis
Tanke, J., Shibuya, T., Uchida, K., Saito, K., & Mitsufuji, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00270 · Cited by 5
Source Separation by Flow Matching
Scheibler, R., Hershey, J. R., Arnaud Doucet, B., & Li, H. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230963 · Cited by 5
Zhang, D., Peng, J., Jiao, Y., Gu, J., Jingyi Yu, A., & Chen, J. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245965 · Cited by 5
GraphBRep : Explicit Graph Diffusion of B–Rep Topology for Efficient CAD Generation
Lai, W., Xu, T. J., Niu, B., & Wang, H. (2025) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwaf136 · Cited by 5
From Image to Video: An Empirical Study of Diffusion Representations
Vélez, P., Polanía, L. F., Yang, Y., Zhang, C., Kabra, R., Arnab, A., & Sajjadi, M. S. M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01574 · Cited by 5
FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
Chen, K., Min, C., Zhang, L., Hampali, S., Keskin, C., & Sridhar, 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/cvpr52734.2025.01626 · Cited by 5
MotionShot: Adaptive Motion Transfer Across Arbitrary Objects for Text-to-Video Generation
Liu, Y., Sun, Y., Xing, Z., Gao, J., Chen, K., & Pei, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01103 · Cited by 5
Latent Diffusion and Spatiotemporal Transformers Generate Large Ensemble Climate Simulations
Meuer, J., Witte, M., Finn, T. S., Timmreck, C., Ludwig, T. G., & Kadow, C. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3621121 · Cited by 5
SummDiff: Generative Modeling of Video Summarization with Diffusion
Kim, K., Hahm, J., Kim, S., Sul, J., Kim, B., & Lee, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01401 · Cited by 5
Chen, Z., Chen, G., Wang, Y., Chen, Z., & Zhang, W.-Q. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2447 · Cited by 5
ECHO: Ego-Centric Modeling of Human-Object Interactions
Petrov, I. A., Guzov, V., Marin, R., Aksan, E., Chen, X., Cremers, D., Beeler, T., & Pons‐Moll, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_7 · Cited by 5
Conditioning Matters: Training Diffusion Policies is Faster Than You Think
Dong, Z., Liu, Y., Li, Y., Zhao, H., & Hao, J. (2025) · neural information processing systems · doi:10.52202/085713-3995 · Cited by 5
SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulation
Jin, Y., Funk, N., Prasad, V., Li, Z., Franzius, M., Peters, J., & Chalvatzaki, G. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696956 · Cited by 5
Wukong Framework for Not Safe For Work Detection in Text-to-Image Systems
Liu, M., Zhang, S., & Long, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780226 · Cited by 5
Vision Bridge Transformer at Scale
Tan, Z., Wang, Z., Yang, X., Liu, S., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37029-7_30 · Cited by 5
What Happens Next? Anticipating Future Motion by Generating Point Trajectories
Boduljak, G., Karazija, L., Laina, I., Rupprecht, C., & Vedaldi, A. (2025) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.2509.21592 · Cited by 5
Wu, Y., Song, J., Tan, Z., He, Z., & Liu, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37602-2_5 · Cited by 5
EgoCogNav: Cognition-Aware Human Egocentric Navigation
Qiu, Z., Liu, Z., Niu, W., Bhattacharjee, T., & Kalantari, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_29 · Cited by 5
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
