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 1,601–1,700 of 3,684
Next-Frame Decoding for Ultra-low-Bitrate Image Compression with Video Diffusion Priors
Chen, Y., Zhou, C., Li, J., Ling, X., He, B., Dai, J., Song, L., & Lu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_15 · Cited by 3
MessyKitchens: Contact-Rich Object-Level 3D Scene Reconstruction
Ansari, J. A., Ding, R., Pizzati, F., & Laptev, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_29 · Cited by 3
ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images
Wu, Y., Cheng, H., He, Z., & Liu, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_19 · Cited by 3
SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences
Kim, S.-Y., Kim, D., Cho, W., Song, H., Kang, S., & Woo, W. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3679893 · Cited by 3
TORA: Topological Representation Alignment for 3D Shape Assembly
Lee, N., Chen, Z., Pollefeys, M., & Hong, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37350-2_4 · Cited by 3
PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
Xu, R., Zhou, D., Shen, X., Ma, F., & Yang, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835046 · Cited by 3
MoRight: Motion Control Done Right
Liu, S., Ren, X., Shen, T., Ling, H., Gupta, S., Wang, S., Fidler, S., & Gao, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_6 · Cited by 3
Erasing Your Voice Before it’s Heard: Training-Free Speaker Unlearning for Zero-Shot Text-to-Speech
Lee, M., Shin, E., & Lee, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462017 · Cited by 3
Penguin: General Vital Sign Reconstruction from PPG with Flow Matching State Space Model
Suzuki, S., Koyama, S., Hirano, S., & Nagashima, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463201 · Cited by 3
Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces
Mahapatra, A., Mai, L., Bourgin, D., Zhang, Y., & Liu, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01638 · Cited by 3
Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation
Ulmer, M., Boerdijk, W., Triebel, R., & Durner, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02258 · Cited by 3
NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation
Liu, Y.-T., Li, J., Liu, Y.-T., Yu, X., Guo, Y.-C., Cao, Y.-P., Liang, D., Shamir, A., & Zhang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02599 · Cited by 3
Diffusion transformers with hybrid conditioning for structural optimization
Lutheran, A., Das, S. B., & Tabarraei, A. (2026) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-026-04429-0 · Cited by 3
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
Jiao, G., Zhang, C., Xian, J. J. C., Zhang, Z., & Liao, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37335-9_1 · Cited by 3
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-teacher On-Policy Distillation
Wu, F., Guo, H., Huang, S., Song, J., Huang, Y., Liu, M., Wang, Z., Yu, Y., Liu, J., & Huang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37196-6_18 · Cited by 3
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Zhang, L., Mo, S., Cai, Z., Lin, J., Lin, Z., Gu, J., SINGH, K., Li, Y., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37083-9_18 · Cited by 3
DiT-JSCC: Rethinking Deep JSCC With Diffusion Transformers and Semantic Representations
Tan, K., Dai, J., Wang, S., Lu, G. S., Shao, S., Niu, K., Zhang, W., & Zhang, P. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3705826 · Cited by 3
Pondering the Way: Spatial-Perceiving World Action Model for Embodied Navigation
Chen, H., Liu, D., Zhang, Z., Wang, H., Lu, T., Yan, L., Sun, H., Li, F., Xie, H., Wang, B., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37595-7_25 · Cited by 3
A First Exploration of Neuromorphic OT-CFM for Multi-speaker VSR
Chen, L., Fang, J., Liu, H., Xu, C., Chen, J., Li, X., Cai, W., & Chen, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_8 · Cited by 3
Chen, C., Sun, P., & Yuan, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_30 · Cited by 3
SCORE: Scaling Audio Generation Using Standardized COmposite REwards
Jung, J., Kim, J., Shin, I., & Chung, J. S. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3721787 · Cited by 3
ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories
Li, Y., Wang, S., Guo, M., Huang, J., Ding, T., Hu, M., Wang, K., Shen, S., & Tan, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_17 · Cited by 3
Training-Free Refinement of Flow Matching with Divergence-Based Sampling
Cha, Y., Yoo, J., Kim, S., Park, Y., Kwon, J., & Hong, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_19 · Cited by 3
Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA
Wu, Z., Li, B., Dai, J., Zhang, Y., Ma, Y., Wang, Q., Jia, X., & Xu, H. (2026) · doi:10.1109/cvprf71909.2026.00406 · Cited by 3
Diff-Feat: Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification
Lan, T., Zheng, Y., & Yin, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728464 · Cited by 3
Latent Diffusion for Guided Document Table Generation
Hamdani, S. J. H., Saifullah, S., Agne, S., Dengel, A. R., & Ahmed, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70549-6_22 · Cited by 3
Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer
Li, B., Wang, X., Song, R., & Huang, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887687 · Cited by 5
Xu, L., Song, H., Lan, T., Wang, Z., & Wang, M. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3745028 · Cited by 3
Zheng, P., Wang, J., Chang, Y., Yu, Y., Ma, R., & Wu, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01615 · Cited by 3
1LoRa: Summation Compression for Very Low-Rank Adaptation
Quercia, A., Cao, Z., Bangun, A., Paul, R. D., Morrison, A., Assent, I., & Scharr, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00223 · Cited by 3
Hyper Diffusion Avatars: Dynamic Human Avatar Generation Using Network Weight Space Diffusion
Cao, D., Sun, G., Habermann, M., & Bernard, F. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00176 · Cited by 3
Zhang, Y., Cao, C., Yu, C., & Zhu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01352 · Cited by 3
Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
Adnan, M., Kurella, N., Arunkumar, A., & Nair, P. J. (2025) · neural information processing systems · doi:10.52202/085713-5631 · Cited by 3
StereoFoley: Object-Aware Stereo Audio Generation from Video
Karchkhadze, T., Chen, K.-L., Heydari, M., Henzel, R., Toso, A., Souden, M., & Atkins, J. D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464717 · Cited by 3
Learning Counterfactually Decoupled Attention for Open-World Model Attribution
Zheng, Y., Gong, B., Kong, F., Duan, Y., Yu, B., Zheng, W., Chen, L., Lu, J., & Zhou, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00019 · Cited by 3
ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editing
Dai, J., Zhang, Y., Chen, S., Yang, J. J., & Luo, L. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3638406 · Cited by 3
Stable Signer: Hierarchical Sign Language Generative Model
Fang, S., Feng, Y., Zhong, H., Zhang, Y., & Metaxas, D. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.659 · Cited by 3
MELA-TTS: Joint Transformer-Diffusion Model with Representation Alignment for Speech Synthesis
An, K., Zhang, Z., Gao, C., Li, Y., Peng, Z., Wang, H., Du, Z., Zhao, H., Gao, Z., & Li, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461891 · Cited by 3
Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
Zhang, G., Shi, C., Jiang, Z., Xiang, X., Qian, J., Shi, S., & Jiang, L. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763949 · Cited by 3
Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
Mao, S., Guo, W., Zhang, C., Long, J., Xie, K., & Cai, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_21 · Cited by 3
Li, Y., Mao, Q., Chen, L., Fang, Z., Tian, L., Xiao, X., Jin, L., & Wu, H. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668668 · Cited by 3
DreamAudio: Customized Text-to-Audio Generation With Diffusion Models
Yuan, Y., Liu, X., Liu, H. D., Kang, X., Chen, Z., Wang, Y., Plumbley, M. D., & Wang, W. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3678172 · Cited by 3
REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers
Jiang, Y., Ning, Z., Wang, S., Wang, C., Bi, M., Zhu, P., Fu, Z., & Xie, L. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434632 · Cited by 3
Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V
Wu, M., Song, B., Lin, R., Zhu, C., Feng, X., Wu, J., Chu, X., & Huang, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460490 · Cited by 3
Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation
Ma, A., Feng, J., Cao, K., Wang, J., Wang, Y., Zhang, Q., & Zhang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01494 · Cited by 3
SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors
Jin, Z., & Feng, A. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00153 · Cited by 3
CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art
Jin, Z., & Chua, T. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810794 · Cited by 3
OmniX: Any-View and Any-Time 4D Reconstruction via Feed-Forward Trajectory Fields
Jiang, Y., Wang, T., Wang, Z., Cao, C., Wu, J., Luo, W., Hu, W., Gao, J., & Guo, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37235-2_19 · Cited by 3
FrameCrafter: Novel View Synthesis as Video Completion
Wu, Q., Vuong, K., Jeon, M., Narasimhan, S. G., & Ramanan, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_5 · Cited by 3
Chiu, P.-Y., Wu, D.-J., Chu, P.-H., Hsu, C. T., Chiu, H.-C., Wang, C.-Y., & Chen, J.-C. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557020 · Cited by 3
PBR‐Inspired Controllable Diffusion for Image Generation
Xue, B., Guarnera, G. C., Zhao, S., & Montazeri, Z. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70329 · Cited by 3
ITVTON: Virtual Try-On Diffusion Transformer Based on Integrated Image and Text
Ni, H., & Xu, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5679-3_32 · Cited by 3
Straighter Flow Matching via a Diffusion-Based Coupling Prior
Xing, S., Cao, J., Huang, H., Shi, H., & Zhang, X.-Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5682-3_4 · Cited by 3
Monte Carlo Marginalization: A Differentiable Method to Learn High-Dimensional Distributions
Zhao, C., Dong, G., & Basu, A. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3682991 · Cited by 3
MRGen: Segmentation Data Engine for Underrepresented MRI Modalities
Wu, H., Zhao, Z., Zhang, Y., Wang, Y., & Xie, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01851 · Cited by 3
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
Thomas, X., & Ghadiyaram, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00211 · Cited by 3
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete DiffusionPreprint
Susladkar, O., Gupta, J. S., Sehgal, C., Mittal, S., & Singhal, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.07659 · Cited by 4
He, S., Liang, H., Zhang, Y., & Yuan, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.02905 · Cited by 4
Mistryukova, L., Manuylov, V. D., Avchaciov, K., & Fedichev, P. O. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.06.16.659955 · Cited by 3
Li, J., Ju, S., Su, Y.-S., Li, H., & Shen, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.18831 · Cited by 3
Flow Autoencoders are Effective Protein TokenizersPreprint
Dilip, R., Zhang, E., Varshney, A., & Valen, D. V. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.01.679645 · Cited by 3
Paris: A Decentralized Trained Open-Weight Diffusion ModelPreprint
Jiang, Z., Seraj, R., Villagra, M., & Roy, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.03434 · Cited by 3
MediQ-GAN: Quantum-Inspired GAN for High Resolution Medical Image GenerationPreprint
Jiao, Q., Tang, Y., Zhuang, J., Cong, J., & Shi, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.21015 · Cited by 3
WaveletDiff: Multilevel Wavelet Diffusion For Time Series GenerationPreprint
Wang, Y.-H., & Milenković, O. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.11839 · Cited by 3
Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive TilingPreprint
Kwon, Y. D., Mehrotra, A., Chadwick, M., Ramos, A. G., & Bhattacharya, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.06295 · Cited by 3
Latent-Augmented Discrete Diffusion ModelsPreprint
Shariatian, D., Durmus, A., Simsekli, U., & Peluchetti, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.18114 · Cited by 3
UniFlow: Unifying Speech Front-End Tasks via Continuous Generative ModelingPreprint
Wang, Z., Liu, Z., Zhu, Y., Li, X., Kang, B., Yao, J., Xia, X., Huang, C., & Xie, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.07558 · Cited by 3
LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion TransformerPreprint
Chen, Y., Ma, Z., Wang, J., Kang, K., Yao, S., & Zhang, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.00477 · Cited by 3
Your Latent Mask is Wrong: Pixel-Equivalent Latent Compositing for Diffusion ModelsPreprint
Bradbury, R., & Zhong, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.05198 · Cited by 3
Guided Transfer Learning for Discrete Diffusion ModelsPreprint
Kleutgens, J., Battiloro, C., Kong, L., Grewe, B. F., Dominici, F., & Tec, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.10877 · Cited by 3
Computational Narrative Understanding for Expressive Text-to-SpeechPreprint
Michel, G., Epure, E. V., & Cerisara, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.04072 · Cited by 3
DiTraj: training-free trajectory control for video diffusion transformerPreprint
Lei, C., Zhang, J., Ma, Y., Wang, X., Chen, L., Tang, L., Yan, Y., Su, F., & Zhao, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.21839 · Cited by 3
Wei, F., Dong, R., Lai, Y., Yang, Y., Luo, Z., Zhang, J., Yang, M., Yuan, S., Zhao, J., Luo, B., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.23239 · Cited by 3
WiFo-MUD: Wireless Foundation Model for Heterogeneous Multi-User DemodulatorPreprint
Yang, Z., Gao, S., Cai, X., Cheng, X., & Yang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.00612 · Cited by 3
CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language ModelsPreprint
Huang, J., Wang, C., Li, L., Xu, G., Huang, D., Chen, H. M., Dai, Q., & Xu, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.21798 · Cited by 3
Stop-Think-AutoRegress: Language Modeling with Latent Diffusion PlanningPreprint
Lovelace, J., Belardi, C. K., Zalouk, S., Polavaram, A., Kundurthy, S., & Weinberger, K. Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.20528 · Cited by 3
LESA: Learnable Stage-Aware Predictors for Diffusion Model AccelerationPreprint
Cai, P., Liu, J., Xu, H., Wang, X., Zou, C., & Zhang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.20497 · Cited by 3
NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight SpacesPreprint
Kim, J., Mehta, S., Hsu, H.-L., Ryu, H., Liu, Y., & Pajić, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.00180 · Cited by 3
Scalable Simulation-Based Model Inference with Test-Time Complexity ControlPreprint
Gloeckler, M., Manzano-Patron, J. P., Sotiropoulos, S. N., Schröder, C., & Macke, J. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.15292 · Cited by 3
A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural RetargetingPreprint
Li, J., Song, X., Wang, S., Huang, H., & Zhao, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.13427 · Cited by 3
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video DiffusionPreprint
Cai, P., Zhang, E., Liu, J., Lin, H., Zhang, R., Mo, W., Ma, Y., Zheng, S., Huang, J., Liu, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.18346 · Cited by 4
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM SteeringPreprint
Shi, Y., Zhang, R., Li, C., Yang, Z., Zhang, K., Jingyi Yu, A., & Ren, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.30076 · Cited by 3
Continuous Language Diffusion as a Decoder-Interface ProblemPreprint
Du, Z., & Ma, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.08810 · Cited by 3
Reward as An Agent for Embodied World ModelsPreprint
Li, P., Lin, Z., Wu, Q., Lv, Y., Wang, F., & You, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.19990 · Cited by 3
Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint MatchingPreprint
Thilges, S., Celik, O., Blessing, D., Gospodinov, E., & Neumann, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.22630 · Cited by 3
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPEPreprint
Hirschorn, O., Olender, A., Alshan, E., Ideses, I., Fritz, L., & Benaim, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.32033 · Cited by 3
WaiT for the Signal: Simple Frequency-Aware Flow-MatchingPreprint
Pavasovic, K. L., Vallaeys, T., Mallat, S., Biroli, G., Zettlemoyer, L., Karrer, B., & Verbeek, J. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.28760 · Cited by 3
dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive ModelPreprint
Wang, H., Li, B., Lian, S., Gu, X., Peng, J., Zheng, D., Guo, Y., Zhang, C., Wang, S., & Yu, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.02673 · Cited by 3
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
NVIDIA, :, Alhaija, H. A., Alvarez, J., Bala, M., Cai, T., Cao, T., Cha, L., Chen, J., Chen, M., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.14492 · Cited by 121
Diffusion-Based Method with TTS Guidance for Foreign Accent Conversion
Bai, Q., Wang, S., Liu, Z., Zhang, M., Rao, W., Wang, Y., & Li, H. (2024) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp63861.2024.10800623 · Cited by 2
A Semantic-Driven Data Generative Traffic Modeling Method for Digital Twin Networks
Yuan, H., Yan, X., & Li, C. (2024) · International Conference on Engineering and Emerging Technologies (ICEET) · doi:10.1109/iceet65156.2024.10913930 · Cited by 2
Zhang, J., Sun, H., Fan, H., Xiong, Y.-J., & Zhang, J. (2025) · Journal of Imaging · doi:10.3390/jimaging11050138 · Cited by 2
Addressing Character Consistency Challenges in AI Filmmaking
Kalinski, M., Podstawski, M., Ostrowski, K., Kudelska, M., Bartkowiak, P., Łyczko, P., Piasecki, M., Visscher, T., & Wang, H. (2025) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc64010.2025.10993630 · Cited by 2
Hierarchical Diffusion Model for Zero-Shot Singing Voice Synthesis With MIDI Priors
Byun, D.-M., Kim, S.-B., & Lee, S. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3577324 · Cited by 2
DiffSCTG: Diffusion-based Safety-Critical Trajectory Generation for Autonomous Vehicles
Zhao, Z., & Zhan, Y. (2025) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce65916.2025.11065683 · Cited by 2
TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance
Liu, M., She, D., Pang, J., Huang, Q., Ying, J., He, W., Hou, Y., & Fu, 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/cvpr52734.2025.00259 · Cited by 2
RainCast: A Hybrid Precipitation Nowcasting Algorithm Using the Himawari-8/9 Satellite Measurements
Andreev, A. I., Олегович, К. М., Malkovsky, S. I., & Filei, A. A. (2025) · Informatics and Automation · doi:10.15622/ia.24.4.4 · Cited by 2
Enhancing Modulation Classification via Diffusion Transformers for Drone Video Signal Processing
Lee, I., Alteneiji, K. M., & Alghfeli, M. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3599110 · Cited by 2
DRL-Based Adaptive Multidomain Feature Fusion for Continuous Authentication on Smartphones
Li, Y., Yang, Y., Deng, S., & Huang, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3608703 · Cited by 2
Yang, X., Zhao, T., Wang, H., Ma, W., Zeng, S., Zhu, Z., Ning, X., Yang, H., & Wang, Y. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133383 · Cited by 2
Metadata
- Authors
- Peebles, W., & Xie, S.
- Affiliations
- University of California, Berkeley (US)
- New York University (US)
- ORCID
- Xie, Saining
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 4172-4182
- OpenAlex
- W4390872297
- Semantic Scholar
- 736973165f98105fec3729b7db414ae4d80fcbeb
- Cited by
- 2,284
- References
- 59
- Citations by year
- 2026: 1007 · 2025: 925 · 2024: 315 · 2023: 37
- FWCI
- 244.26
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- diffusion models, latent diffusion models, diffusion transformer, scalability, image generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
