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 2,901–3,000 of 3,684
Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
Lee, H., Lee, H., & Kim, J.-Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_13
RTINet: A learned in-loop filter in VVC using interaction of ResNet and Transformer
Jung, C., Fu, P., Han, J., & Liu, L. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117605
A unified hybrid Quantum-Embedded Timestep Mapping method for diffusion models
An, K., Kong, D., Zhang, K., Yu, M., Fu, Y., Xu, J., & Wang, D. (2026) · Displays · doi:10.1016/j.displa.2026.103551
CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENerationPreprint
Meric, A., Foo, L. G., Kiray, M., Busam, B., Dabral, R., & Theobalt, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.22996
Zhou, L., Hang, K., Zhao, W., Yang, Y.-F., Shen, Q., Wang, Y., Gao, J., Li, S., & Yang, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3696320
Wang, Z., Wu, G., Zhang, Y., & Liu, J. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3697221
Point2Seq: Quantized Serialization Encoding for Object Point Cloud Pretraining
Yu, X., Liu, Z., Zhou, J., & Lu, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02884-2
Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
Peng, W., Hariharan, B., & Averbuch‐Elor, H. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811129
Tang, C., Lin, X., Huang, Z., Sun, W., Jia, H., & Liu, Y. (2026) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2026.3697149
DevilSight: Augmenting Monocular Human Avatar Reconstruction Through a Virtual Perspective
Chen, Y., Shao, R., Pang, Y., Zhang, H., Wu, X., Wu, R., & Liu, Y. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00142
Statistical Aware Transformer for Tool Wear Monitoring
An, L., Si, Y., Wang, X., Liu, Y., & Wang, P. (2026) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3249/1/012001
Time-Evidence Dual Gating for Blue-and-White Porcelain Style Transfer
徐, 子. (2026) · Modeling and Simulation · doi:10.12677/mos.2026.155084
A survey: advances in multi-modal visual understanding and generation
Xi, D., Zhou, Z., Wang, Y., Wang, J., & Zhang, C. (2026) · Vicinagearth. · doi:10.1007/s44336-025-00032-x · Cited by 1
LEIA: Learned Environment for Interactive Architected MaterialsPreprint
Yang, H., Cao, Y., & Buehler, M. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.28368
SignMoD: Sign Language Video Generation via Mixture of Diffusion
Qi, F., Duan, Y., Zhang, H., & Xu, C. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3698334
Transcriptomics-Conditioned Virtual Tissue Synthesis via Diffusion TransformersPreprint
Vlachas, P. R., Nonchev, K., Koelzer, V. H., & Rätsch, G. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.26.727902
CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous DrivingPreprint
Qian, Z., Yang, Z., Tan, L., Yan, Z., Hong, W., Liu, H., & Jueluo, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.29935
Frequency-Aware timestep optimization for efficient sampling in diffusion models
Zheng, Y., Li, X., & Zhan, Y. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00886-1
Physical plausibility reasoning via HCM-GRPO: Empowering compact model for superior performance
Hu, Z., Sun, Z., Wei, Y., & Yu, L. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114108
SFM-Adapter: Style-Aware Feature Manipulation Adapter for Speech Style Editing
Chen, Y., Liu, H. D., Chen, Q., Singh, A., Zhao, J., Wang, W., Jackson, P. J. B., & Plumbley, M. D. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3698957
NATE and T-NATE: Efficient transformers for IoT task offloading in edge–fog–cloud computing
Garon, A., Yassa, S., & Alouache, L. (2026) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2026.101392
Wang, C., Wang, Z., & Dong, H. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3694336
Zhang, H., Chen, G., Tang, Z., Yang, B., & Xu, Y. (2026) · Journal of Geophysical Research Solid Earth · doi:10.1029/2025jb033046
GLIDE: Graph-Guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
Zhou, G., Liu, Y., Gan, Y., Cai, Y., He, P., Lin, R., Liu, Q., & Liu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37664-0_36
MaPPA: Multimodal Controllable Person Image Generation With Pose and Appearance Guidance
Ye, M., Dong, Y., Wang, T., Zhou, D., Tan, Q., & Du, B. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3697647
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
Xue, D., Zhu, Z., & Hou, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_26
DriveGen: Shared Video-Condition Encoding for Autonomous Multi-View Video Generation
Kang, Y., Li, H., Zhao, S., Wang, S., Qin, X., Han, J., & Tao, J. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3699816
Yang, D., Anik, S. M., Lee, B. K., & Ryoo, J. (2026) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc71020.2026.00024
BlockGen: Flexible Blockwise Sequence Modeling with Hybrid SamplersPreprint
Deschenaux, J., & Gülçehre, Ç. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.02241
Lan, S., Dou, H., Huang, J., Zakeri, A., Lin, F., Zhou, Z., Duan, J., & Frangi, A. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_8
The PRISM benchmark: PhotoRealistic Image Synthesis and Manipulation to detect generated images
Bartolucci, F., Salti, S., & Lisanti, G. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104826
Efficient Speech Super-Resolution Based on Conditional Flow Matching
Bao, H., Yang, Y., Zhou, L., Jing, K., & Ding, Z. (2026) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp69961.2026.11540575
Parallel Complex Diffusion for Scalable Time Series Generation
Cai, R., Wan, Y., Zhang, K., Jin, M., Ge, Z., Wen, Q., & Liu, Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817791
FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning
Lupaşcu, M., Jindal, N., Mironică, I., & Wang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38407-2_4
Dai, C., Zhang, S., Li, Y., Zhang, Z., Zhu, Z., & Duan, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_17
Al-Abaji, M. A., Salih, M. M., & Hussein, M. K. (2026) · PROtek Jurnal Ilmiah Teknik Elektro · doi:10.33387/protk.v13i2.11858
DeltaAug: A Directional Semantic Data Augmentation Framework Guided by Differential Reasoning
Chen, W., Li, H., Shen, G., Cao, R., & Song, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1462-4_7
Towards controllable video synthesis of routine and rare OR events
Schneider, D., Seenivasan, L., Rapuri, S., Anil, V., Maksutova, A., Shen, Y., Mangulabnan, J. E., Ding, H., Porras, J. L., Ishii, M., et al. (2026) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-026-03692-2
Narmadha, R. P., Jeevasankar, V., Mishal, M., & M, A. (2026) · International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn68523.2026.11543542
Multi-Scale Flow Matching for Tibetan Speech Enhancement with Context-Aware Phonetic Embeddings
Gan, Z., Sun, Z., & Wang, T. (2026) · International Conference on Multi-scale Artificial Intelligence (MAI) · doi:10.1109/mai69289.2026.11543749
PLuG: Pairwise Logit Gating for Expressive Attention Modulation in Vision Transformers
Lee, D., Yoon, S., Kim, S. K., & Paik, J. (2026) · IEEE Access · doi:10.1109/access.2026.3701015
Yang, S., Bhat, S., Han, D. W., Salour, A., Stroup, T., Barakat, R., Pridham, P., Liu, Y., & Jessie, X. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3701124
Efficient Inference for Flow Matching via Unified Path CFG
Ukita, K., & Okita, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1465-5_14
DiBS: Diffusion-Informed Branch SelectionPreprint
Liu, B., Xie, Y., Gao, Y., Luo, X., Ye, P., Chen, T., & Han, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.06518
CondFoodGen: A Conditional Two-Stream Network for Controllable Food Image Generation
Zhao, M., Xiong, H., Min, W., Hou, S., Zhang, M., & Jiang, S. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3699097
Drifting Models for Surrogate Flow ModelingPreprint
Jung, C. R., Dörr, M., Jüngling, N., Niessner, J., Müller, A. T., & Stache, N. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.07481
Zhu, L., He, P., Ming, L., Zhou, J.-Z., Sun, T., & Jiang, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3701354
Void-X: A generative void-filling model for predicting atomic packing in proteins
Yang, J., Yuan, J., & Chou, J. J. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2607035123
AniFeats: Animate 3D Feature Meshes for Character Video Generation
Lu, B., Gu, Z., Dou, Z., Yuan, H., Li, P., Si, C., Cao, Y., Jiang, Y., Liu, Y., Wang, W., et al. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3701833
UAV-Based Highway Pedestrian Detection via Large-Scale Image Generation Model and Transfer Learning
Chen, L., Zhou, C., Hou, X., Tong, Q., An, R., & Jia, L. (2026) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs70157.2026.11545198
TM ‐Edit: Text Guided Diffusion‐Transformer Based Motion Editing With Temporal Soft Masks Learning
Zheng, Y., Qiu, X., Xiang, N., Zhou, Y., & Wang, Z. (2026) · Computer Animation and Virtual Worlds · doi:10.1002/cav.70138
FashionAtlas: Enhancing Semantics and Control in Multimodal Fashion Image Editing
Gu, E., Wang, J., & Shi, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9694-2_7
Ma, Z., Wei, J., Cai, Z., Yang, C., Hua, E., Xie, S., Li, J., & Zhou, B. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3700904
Self-citationRD-VTA: Rule-Data Guided Video-to-Audio Generation for Fine-Grained Footstep Sound
Qi, Q., Cheng, H., Huang, H., Ye, L., & Li, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3703315
SAS: Semantic-Aware Sampling for Generative Dataset Distillation
Li, M., Li, G., Ye, L., Mao, J., Ogawa, T., Plataniotis, K. N., & Haseyama, M. (2026) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2026.3703204
Enescu, V., Zeghina, A. O., Meignin, M., Viltard, N., & Mallet, C. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630427
SA-Edit: Accelerating Editing Models via Test-time Spatial Acceleration
Song, Y., Hu, T., Yi, R., Lei, X., & Sheng, B. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810596
Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing
Zhan, Z., Li, H., Wang, C., Ma, Y., Huang, M., Bai, R., Chen, J., Lyu, S., & Chen, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37657-2_22
Yang, L., Lin, H., Wu, Y., Sun, Z., & Gu, Q. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810825
Huang, J. (2026) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta70174.2026.11549003
InterFold: Learning Interpretable Diffusion Manifolds Beyond Binary Samples
Lewi, A. V., Tan, R., & He, S. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810585
Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
Fei, J., Dai, Y., Xia, Z., Cao, X., Zhou, J., Piva, A., & Tondi, B. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3703439
NetDiT: A Diffusion-Transformer Framework for Synthetic Network Packet Generation
Farhangi, D., Nukavarapu, S. K., & Nadeem, T. (2026) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc65185.2026.11555339
MMDiff: Extending Diffusion Transformers for Multi-modal Generation
Akarken, Y., Kupyn, O., & Rupprecht, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37020-4_15
Privacy-Compliant Human Data Synthesis in Images for GDPR
Patwari, K., Schneider, D., Sun, X., Chuah, C., Lyu, L., & Sharma, V. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557001
Xu, J., Xue, W., Yu, X., Pan, J., Lianga, X., & Wang, M. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.10.025
Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting
Tsoumplekas, G., Bounareli, S., & Argyriou, V. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557018
Shades of Generalization: Diversity Aware Open Set Deepfake Detection
Tukkani, S. R., & Bharati, A. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557037
Echoes of the Brain: Reconstructing Music From EEG via Latent Space Alignment and Guided Diffusion
Shen, L., Li, R., Liu, X. R., Zhang, H., Zhu, C., Qian, K., Tian, F., Hu, B., Schuller, B. W., & Yamamoto, Y. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3704863
Diffusion-MF: Approximate Structured Diffusion for Sequence LabellingPreprint
Floquet, N., Roux, J. L., & Tomeh, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.18856
FG-DiTAD: A Feature Guided Diffusion Transformer for Anomaly Detection
Du, M., Zhao, J., Zhang, L., Qin, Z., Xie, L., & Hu, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116462
The Market in the Model: Latent Diffusion as Neural EconomyPreprint
Salvaggio, E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.19151
Elucidating the Design Space of Generative Models for Single-Cell Perturbation PredictionPreprint
Bhattacharya, S., Gensbigler, C., Karim, S., & Lees, J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.15.732063
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion ModelsPreprint
Wu, H., Po, L.-M., Liu, M. Y., Li, K., Yang, H., & Liu, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.20310
LooseControlVideo: Directorial Video Control Using Spatial Blocking
Bhat, S. F., Mitra, N. J., & Sunkavalli, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_5
Yang, C., Tan, W., Chen, H., Li, G., Lei, S., Yu, J., Wang, S. Q., & Li, H. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3705684
A scalable framework for synthesizing conditional porous media images using diffusion and GAN models
Dheyauldeen, A., Wang, Y. D., Tang, K., Armstrong, R. T., & Mostaghimi, P. (2026) · Advances in Water Resources · doi:10.1016/j.advwatres.2026.105328
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention DistillationPreprint
Liu, G., Wang, Y., Li, C., Chen, W., Lin, J., Yao, Y., Ke, D., Ding, W., & Zhao, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.20005
基于生成式人工智能的单曝光压缩成像重建算法：研究现状与展望（特邀）
Ge, 王. W., Zongliang, W., & Xin, 袁. Y. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop260754
Text Dictates, Music Decorates: Energy-Based Attention for Editable Dance Motion Generation
Yoo, S. J., Peng, S., Gu, F., Aloimonos, S., & Fermuller, C. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_14
ParaChromo: Scalable and Seam-Coherent Inference for 3D Genome Diffusion
Su, X., Zhu, M., Shang, W., & Ou, Z. (2026) · Electronics · doi:10.3390/electronics15132750
Video Object Segmentation-Aware Audio Generation
Viertola, I., Iashin, V., & Rahtu, E. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02911-2
Video frame interpolation for coronary angiography using latent flow matching
Kwon, H., Park, S., Kim, D.-H., Ko, S.-K., Kim, S.-H., Moon, I. T., Jeon, K., Kang, S., Yoon, C., Youn, T., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02923-9
Research on Multi-Model Fusion Image Generation Algorithm Based on Class Guidance and PEFT
Zhou, W. (2026) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect68671.2026.11565081
One-Step Flow Matching for Generative Modeling of Path-Dependent Physical FieldsPreprint
Zhou, Y., & Jelovica, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.22752
Diffusion-Head VLA Model for Adaptive UAV Vision-Language Navigation
Lin, T., Fei, Q., & Geng, Q. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11560596
FreqCache: Frequency-Aware Adaptive Branch Routing for Training-Free Diffusion Acceleration
Zheng, Y., Li, X., & Zhan, Y. (2026) · Applied Sciences · doi:10.3390/app16136328
Jiang, M., Ruan, X., Zheng, L., Zhang, X., Zheng, Y., Yu, C., Ruan, D., & Liu, H. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104187
Wang, Y., Tang, J., Zheng, B., Davydov, M., Zhang, P., & Wong, K. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3706480
Dauvilliers, C., & Monteleoni, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.24263
Confidence-Guided Fusion for Self-Supervised Monocular Depth Estimation in Endoscopy
Li, S., Wang, H., Hu, Z., Chu, T., Li, Y., & Zhao, L. (2026) · Sensors · doi:10.3390/s26134033
Lu, Y., Xun, D., Xu, C., Zhu, X., Zhang, Z. D., Chen, P., Yang, X., Yan, Z., Rao, J., Huili, H., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.23.734130
Concept Removal for Frontier Image Generative ModelsPreprint
Kumar, A., Joly, P., Dziedzic, A., & Boenisch, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.25548
EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
Li, H., Wang, J., Cai, S., Sheng, H., Deng, B., Ye, J. P., & Luo, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37196-6_15
Neural Texture Compression using HypernetworksPreprint
Belcour, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.26913
Yue, G., & Wang, J. (2026) · Chemical Engineering Science · doi:10.1016/j.ces.2026.124524
Latent Attention on Masked Patches for Flow Reconstruction
Eze, B., Magri, L., & Nóvoa, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29915-4_15
A Graph Neural Network-Based Approach for Initial Solutions Generation of Hypersonic Fields
Stumpo, L., Alia, C., Ferrero, A., Masseni, F., & Pastrone, D. G. (2026) · AIAA International Space Planes and Hypersonic Systems and Technologies Conference · doi:10.2514/6.2026-5007
Multi-Scale Transformer Diffusion Model for Realistic Wireless Network Traffic Synthesis
Si, Z., Zhang, Y., Yao, L., Guo, D., Teng, Y., Hua, X., Yu, R., & Zhu, L. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571339
Li, Y., Tian, F., Guan, S., Ge, Y., Li, W., Yan, Y., Ma, C., & Yang, X. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3706293
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
