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 3,001–3,100 of 3,684
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Wang, R., Liu, J., Huang, H., Huang, H., Wang, J., Zhang, C., Li, X., & Wu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_16
EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
Zhang, D., Liu, H., Dai, B., Chen, K., Wang, C., Li, C., LYu, J., & Wang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_2
Self-Normailzed Cross-Domain Adaption for Personalized Diffusion Model Training
Ting, H., Wang, Z., Liu, Y., & Nallanathan, A. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571560
Latent Visual Diffusion Reasoning with Monte Carlo Tree Search
Teng, X., Xi, N., & Yuan, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_1
Xu, J., Song, S., Zhao, S., Liang, X., Gu, H., & Wang, S. K. (2026) · Applied Sciences · doi:10.3390/app16136447
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
Zhou, S., Li, Z., & Chai, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37174-4_28
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Guo, Q., Luo, H., Yue, D., Jin, W., Fu, X., Wang, F., & Xu, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_14
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
Chen, J., Zhang, H., Li, M., Li, M., Zheng, Z., Liu, X., Luo, G., & Chen, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37095-2_36
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Liu, D., Xu, J., Wu, L. Y., Zhao, X., Zhu, X., Jin, Z., & Dutta, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_4
Your Data Manifold Is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Zhang, S., Li, Y., Yan, Y., Zhang, J., Zhao, W., Wang, B., & Zhang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37314-4_8
DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution
Tang, Y., Yan, C., Liu, W., Hu, Q., & Zhang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_36
Chen, C., Wang, C., Li, Y., Wan, Z., Geng, M., Xiao, J., Xing, Z., Hu, Y., Wu, Y., Qu, Z., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.28421
Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
Fu, J., Huang, Z. Z., Li, H., Wang, N., & Liu, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_22
Computational Narrative Understanding for Expressive Text-to-Speech
Michel, G., Epure, E. V., & Cerisara, C. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.308
Histogram-Constrained Image Generation
Liu, H., Guo, Y., Cao, Y., Wan, S., & Wen, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_20
Anchoring on Reality: Breaking the Pseudo-target Ceiling in Makeup Transfer
Wei, B., Lin, X., Dong, Y. H., Li, Z., Li, Z., Wang, Z., Yang, J., Liu, X., Gu, H., Li, X., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_14
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
Tong, J., Wang, Z., Ren, Y., Yin, P., Wu, H., Zhang, W., & Shen, X. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.498
Accelerated Likelihood Maximization for Diffusion-Based Versatile Content Generation
Lee, H., Hwang, I. K., & Kim, Y. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37029-7_19
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
Ma, J., Du, Y., Sun, Y., Xing, Z., Li, C., Tang, Z., Li, B., Jiang, P.-T., Yuan, L., Zhou, D., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37261-1_34
D-RGATDiff: Unified Spatiotemporal Diffusion for IoT Network Time Series Anomaly Detection
Zou, C., Ruan, Y., Yang, L. T., Deng, X., Liu, S., Wang, S. Y., & Hou, R. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3709053
Wang, J., Hua, Z., Chen, Q., Liu, X., Zhang, W., Qian, D., Li, P., Han, J., Ding, W., Ye, X., et al. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3709536
Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
Lee, Y., & Lee, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_22
MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation
Brandes, J., Crocoll, P., & Burgard, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_6
Arachne: Orchestrating Cascades for Efficient Text-to-Video Model TrainingPreprint
Yu, P., Fan, Y., Qiu, Y. L., Li, T., Chen, B., Chen, Y., & Weng, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.01701
Yuan, C., Li, P., Sun, Y., & Liu, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.01817
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
He, X., Xie, J., Zheng, M., & Chen, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37429-5_37
Wang, Z., Wang, M.-Z., He, Y., Ma, X., Wang, Z., Zhang, H., Cheng, Y., & Pun, M.-O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37261-1_15
ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies
Long, P., Wang, W., Zhao, Q., Guo, X., Pan, X., Zhang, Q., Zhou, J., Hu, T., Yang, W., Xu, L., et al. (2026) · ACM Transactions on Graphics · doi:10.1145/3811392
Anti-prompt: Image Protection Against Text-Guided Image-to-Video Generation
Song, Y., Lee, C., Park, J., & Son, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_2
CrossDiffAE: Cross-Modal Masked Diffusion Autoencoding for Zero-Shot Skeleton Action Recognition
Tan, D., Tian, W., Gong, X., & Xiong, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3710105
Qwerty: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
Choo, K., Kim, Y., Han, H., Park, G., Kim, C., Jung, S., & Hwang, S. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37450-9_23
Hu, F., Guo, Y., & Tian, H. (2026) · Applied Sciences · doi:10.3390/app16136760
Zhang, K., Yang, Y., Wang, L., Li, R., Ding, J., Li, C., Shang, H., & Xu, Y. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3710341
Text Generation Image Model Based on Large Language Model and Masked Diffusion Transformer
Liu, M., Zhang, Y., Zhou, J., & Zhang, J. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582658
Elshamy, S., & Korany, N. O. (2026) · International Conference on Machine Intelligence and Smart Innovation (ICMISI) · doi:10.1109/icmisi69868.2026.11584135
AnyStyle: A Single LoRA Is Sufficient for Image-Guided Style Transfer
Lai, Y., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_2
Liu, Y., Lan, W., Li, J., Yuan, B., & Yang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_34
Shang, C., Zhang, X., Wang, Z., & Wang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37461-5_22
Yu, Q., Zhao, H., Xu, Y., Wang, M., Zhao, Y., Fu, H., Ye, X., Villavicencio, A., Lip, G. Y. H., Zheng, Y., et al. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3710844
Haojie, P. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.03256
PedestrianDiffusion: Spectral Noise-Conditioned Dense Pedestrian Inertial Motion Estimation
Lu, I.-H., & Han, D. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3749094
Spectral Diffusion for Protein DynamicsPreprint
Phipps, H., Cagiada, M., Villalba, S. D., & Deane, C. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.04134
SEAT: Selective Entropy-Aware Token Merging for Efficient Diffusion Transformer Acceleration
Kwak, H., & Shin, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2480-7_1
Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space
Tran, T. V. T., Nguyen, N.-S., Tran, L., Pham, L.-K., Neekhara, P., Hussain, S., & Nguyen, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37261-1_11
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
Komatsu, R., Kawakita, K., Okamoto, T., & Shinozaki, T. (2026) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2026.3711530
GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts
Dong, X., Li, Q., Liang, H., Zhang, X., & Yu, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22261-9_6
FM-Font: Flow Matching With Disentangled Dual-Branch Encoding for Few-Shot Chinese Font Generation
Wang, X., Liu, T., Cao, Q., & Peng, S. (2026) · IEEE Access · doi:10.1109/access.2026.3711314
Li, M., Chao, F., Lin, C.-W., Shang, C., & Shen, Q. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3711608
Latent Space Probing for Adult Content Detection in Video Generative Models
Khatri, A., & Prabhu, C. (2026) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w70714.2026.00039
耿焕同, Shi, Z., Min, J., Wu, F., & Zhao, H. (2026) · Remote Sensing · doi:10.3390/rs18142287
Ju, Y., Tan, X., Song, Z., Zhu, Z., & Mao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22267-1_29
ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions
Liu, H., Yu, Q., Fujiwara, K., Uchiyama, H., & Kiyokawa, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_28
SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation
Xie, S., Cai, M., Yang, X., Liu, Y., & Ding, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37044-0_30
Self-citationCausality-Guided Diffusion and Fusion of incomplete multi-modal data for robust survival prognosis
Huang, Y., Zheng, X., & Dong, S. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104207
MMTryOff: multi-category virtual try-off with mask-free inference via diffusion transformer
Su, M., & Li, L. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02480-x
PanDiM: A Diffusion Mamba Network for High-Fidelity Pansharpening
Xu, H., Zhang, W., Lin, L., Wu, J., 谢伯祥, Zhang, W., Li, H., & Qu, J. (2026) · Remote Sensing · doi:10.3390/rs18142299
Fine-Grained Enhancement Convolutional Diffusion Transformer for Unsupervised Anomaly Detection
Ma, Z., Fang, X., Huang, Y., Wen, J., Zhou, G., & Xu, Y. D. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3709502
General-Purpose Audio-Visual Sounding Object Localization Based on Semi-Automatic Annotation
Sakurai, S., Bando, Y., Imoto, K., & Onishi, M. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3712286
CGDM: Cross-Modality Gradient-Guided Diffusion Model for graph generation
Zhao, J., Chen, Y., Yu, X., & LI, G. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116630
Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
Feng, Y., Wang, J., Xu, C., Hou, W., Wang, H., Qian, Y., Liu, Y., Sun, B., Liu, Y., & Wang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_31
TimeAware MoE: Adaptive Structure-to-Details Routing for Diffusion Transformers
Plumanut, R., & Bootkrajang, J. (2026) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse68839.2026.11597018
Multi-Agent Reinforcement Learning for Diffusion-Based Token Communications in Robotic Networks
Liu, Z., Yang, Z., Zhang, Z., Qi, Q., Zhang, Z., & Shikh‐Bahaei, M. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3712126
Accelerating Block Low-Rank Foundation Model Inference on Memory-Constrained GPUs
Abillama, P., Lee, C. S. G., Dong, J., Blaauw, D. T., Sylvester, D., & Kim, H.-S. (2026) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1145/3806645.3807580
Advancing 3D scene generation through GCWA with dynamic upsampling using two-stage diffusion model
Ye, S., Di, X., & Li, X. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02476-7
DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse
Chen, Y., Zhong, R., Zong, Z., Li, H., Jin, Y., & Zhai, J. (2026) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1145/3806645.3807581
Pivot-FSOF: A Full-Stack Optimization Framework for real-time DiT-based TTS on edge devices
Gong, C., Guo, H., Zhang, W., & Wang, M. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103915
PlaSphere: An Immersive Hybrid Ecology of Plastiglomerates
Ahn, S. H., Millett, R. M., & Park, S. O. (2026) · Creativity and Cognition · doi:10.1145/3803784.3809291
EmoDiffuser: emotional diffuser for speech-driven 3D facial animation
Zhao, X., Dai, J. P., Zhou, F., Wang, H., Hao, A., Pan, J., & Gao, Y. (2026) · The Visual Computer · doi:10.1007/s00371-026-04623-7
DynEval: Holistic Evaluations of T2I Generative Models in the Wild
Marjit, S., Baiju, D., Shikarkhane, A., Sakthieswaran, A., Paul, S., & Chakraborty, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_23
Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis
Lim, H., Lee, M., Chang, W., & Choi, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37419-6_15
Adversarial defense via mamba diffusion
Shi, X., & Wang, Y. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115663
Vision-Conditioned Structured Trajectory Planning via Flow Matching and Route-First Decoding
Cai, Z., & He, X. (2026) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms69701.2026.11602327
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
Taioli, F., Coelho, D., Melekhov, I., Alcover‐Couso, R., Saiz, J. M. G., Arguedas, V. F., & Bekasov, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_29
A Shortcut to Statistically Steady-State Turbulence with Flow MatchingPreprint
Galletti, G., Gutenbrunner, G., Hornsby, W., Zanisi, L., Carey, N., Pamela, S. J. P., Brandstetter, J., & Paischer, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.13022
Combining transformer and Mamba diffusion structures for super-resolution of brain MRI
Zhang, Q., Hang, Y., Chen, H., Min, B., & Qiu, J. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111034
Improve Speaker Embedding Through Diffusion Generative Training
Tu, Y., Mak, M., Chien, J., & Zuo, L. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3714207
AdaStart: Uncertainty-Aware Adaptive Warm Starting for Diffusion-Based Robotic Control
Chen, Q., Ren, X., Xing, J., Liu, C., Lin, W., & Ye, C. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3713714
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
Cai, Y., Niu, X., Lu, H., Gai, K., Wu, K., & Lin, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_8
Jun, G. H., Pang, W., Richter, E., Saeedi, M., Amarnath, A., Ferrao, P., & Chen, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.12839
Shen, Q., Wang, Y., Zhou, Y., Xia, G., Zang, K., & Luo, X. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.126887
Motion4Motion: Motion Transfer Across Subjects at Inference
Chen, L.-H., Yin, Z., Wang, D., Zeng, X., & Yu, G. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811062
FabricTryOn: Taming Image Editing Models for Garment Re-Texturing
Ma, J., He, Q., He, G., Huang, C., Liu, C., Jin, X., Yang, Y., & Wang, H. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811105
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
Fiebelman, G., Baron, Y., Averbuch‐Elor, H., Cohen‐Or, D., & Patashnik, O. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811142
EchoDiff: Echo State Reservoirs for Parameter‑Efficient Diffusion Image Generation
Rifa, K. R., Thakkar, I. G., Cheung, S.-C. S., & Hastings, J. T. (2026) · International Conference on Neuromorphic Systems (ICONS) · doi:10.1145/3822454.3822492
Deep Motion Warping via Phase-Conditioned Diffusion Autoencoder
Zheng, B., Wu, L., Jiang, X., Chai, Y., Zeng, Z., Wang, H., & Jin, X. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811144
ViT-FiLM Conditional SSB Codebook Optimization for Cell-Free mmWave Massive MIMO Systems
Han, Y., Tan, J., Zhang, X., & Wang, J. (2026) · IEEE Communications Letters · doi:10.1109/lcomm.2026.3713946
MultiAnimate: A Unified Framework for Controllable Multi-Character AnimationPreprint
Zhang, Z., Wang, G., Hu, L., Zhou, W., Zhang, P., Wei, T., Zhang, W., Zhang, B., & Yu, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.13415
DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation
Shim, E., Lee, H., & Ju, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37350-2_17
Controllable Texture Tiling via Diffusion Transformers with Transformed Rotary Embeddings
Huang, J., Zhang, Z., Tang, R., Fu, H., & Liao, J. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811172
MagicPrompt: Ultra-lightweight Prompt Tuning for Video Generation
Zhang, Y., Tan, D., Kong, X., Ma, Y., Jin, Y., & Rao, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36839-3_28
Min, K., Sun, Z., Cai, Z., Dai, C., Zheng, X., Zhu, C., & You, Y. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.113568
Sun, L., Li, J., Ma, J., Zhang, Y., Sun, H., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3520-9_48
SceneMoDiff: Trajectory-Decoupled Motion Style Transfer via Multimodal Environmental Modulation
Zhang, Y., Pan, Y., Zhang, H., Zeng, M., & Lin, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3429-5_45
Diffusion-Time Adaptive Region-Aware Cross-Modal Fusion for Food Image Generation
Fan, W., Liu, B., Zhang, R. X., Shang, X., & Zhang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3429-5_1
DynamicVAR: Multimodal-Routing-Based Adaptive Visual Autoregressive Image Generation
Hu, G., Liao, Y., & Huang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3378-6_16
Practical Consequences of FID–CLIP Disagreement in Low-Data Diffusion Model Fine-Tuning
Zhou, W., Zhang, C., & Song, L. (2026) · IEEE Access · doi:10.1109/access.2026.3715034
Seeding Success: Unlocking the Golden Seed for Any Prompt in Text-to-Image Diffusion Models
Qian, Y., Cai, Q., Pan, Y., Li, Y., Yao, T., Ngo, C., & Mei, T. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3715331
Audio-to-Video Synthesis for Realistic Facial Animation
Yang, Z., Yang, R., Han, M., & Chen, P. (2026) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai70103.2026.11605536
PAGS-relight: Position-aware Gaussian Splatting scene relighting with multi-view diffusion models
Ye, J., Zhuang, J., Bai, J., Mu, L., Tan, W., Xu, J., Abu-Bakar, S. A. R., & Hu, H. R. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114438
SGN: A Similarity-based Generative Network for Data Generation under Distribution ShiftPreprint
ZHU, J., Chen, X., Wu, Y., Luo, Z., & Ooi, B. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.18072
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
