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 3,201–3,300 of 3,684
Diffusion Model‐Enhanced In Vivo Fluorescence Imaging for Spatiotemporal Vascular Visualization
Wu, H., Liu, Z., Cai, R., Song, F., & Zhang, G. (2026) · Laser & Photonics Review · doi:10.1002/lpor.71758
Boudaghi, A., Nemati, A., & Zare, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.15727
KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generation
Luo, J., Zhong, Y., Shen, H., Xiao, Y., & Yang, Z. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3837690
LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
Liu, J., Qin, H., Tu, X., Liu, J., Hu, J., Yan, Z., Xie, Y., Shen, K., Ren, J., Lin, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_26
Kong, H., Liu, L., Bai, H., Li, X., & Du, Y. (2026) · Agriculture · doi:10.3390/agriculture16161777
Ling, Y., Zhao, D. Y., Deng, K., He, Z., Yin, K., & Ma, H. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3725299
Flexible Motion Stylization via Multi-Modality Latent Diffusion Model
Song, W., Jin, X., Li, S., Hao, A., & Hou, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3722736
SSGLD: Spatial-Semantic Guided Latent Diffusion for Person Image Synthesis
Xu, Y., Zhang, Z., & Chen, G. (2026) · IEEE Access · doi:10.1109/access.2026.3726280
AI-Based Personalized Movie Scene Reimagining System for Text-Guided Video Synthesis
Sumanth, T. V., Gupta, K., Singh, C., & Jangid, H. (2026) · International Conference on Circuit, Power and Computing Technologies · doi:10.1109/iccpct70290.2026.11654995
HAIFIT: Structure-Consistent Fashion Image Translation With Multiscale Feature Modeling
Jiang, J., Wu, M., Li, X., Yu, W., & Wu, D. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3720247
A Hierarchical Adaptive Posit-CIM Architecture for Edge Transformer Inference
Liu, X., Liu, C., Wang, J., & Shen, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-4805-6_24
Pham, V. H. S., Vo, T. B. H., Le‐Hoai, L., & Nguyen, N. H. (2026) · Cluster Computing · doi:10.1007/s10586-026-06428-8
LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals
Yan, H., Chen, R., Zhan, J., Wang, B., Xiao, Y., Ding, S., Zhang, L., Yao, T., & Zhang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_12
Guo, X., Shu, T., Xiao, T., Liu, J., & Li, K. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3727099
Kritopoulos, G., Neofotistos, G., Barmparis, G. D., & Tsironis, G. P. (2026) · AI in Medicine · doi:10.3390/aimed1030023
Understanding the Layer-Wise Role of Text-Stream Modulation in Diffusion Transformers
Kodama, H., Yoshida, M., Togo, R., Ogawa, T., & Haseyama, M. (2026) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan71481.2026.11652855
InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition AdapterPreprint
Tong, Y., Liu, M., Zhao, C., Zhang, S., Zhu, D., Zhang, P., He, W., Liu, J., Chen, Y., Jiang, H., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.20910
FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
Vuong, K., Ramanan, D., & Narasimhan, S. G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_4
SMS-Diff: Physics-aware spectral-spatial diffusion for unified geospatial multi-modal reconstruction
Zhang, W., Chen, Z., Zhang, M., Sun, C., Wang, R., Shuang, J., & Zhao, J. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.08.014
Photorealistic Novel View Synthesis of Human Faces using Next-Scale TransformersPreprint
Stella, F., Jiang, F., Jiang, Z., Barzelay, Z., Garbin, E., Jourabloo, A., & Ge, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.23410
PHASE: encoding global protein ensembles with local Hamiltonians and all-atom backmappingPreprint
Angioletti, D., Nobile, M., Carli, M., & Limongelli, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.23490
Kohli, C., Chug, A., & Singh, A. P. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01257-9
TaxoGrasp: Taxonomy-Guided Human Grasp Synthesis with Sparse Contact Constraint
Liu, H., Wang, Y., Leng, Z., Zhou, K., Wang, Y., Li, F. W. B., & Liang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36846-1_13
When Data Augmentation Falls Short: Wi-Fi Fingerprint-Based Indoor Localization Revisited
Malikov, N., Ristin, M., & Seytnazarov, S. (2026) · Sensors · doi:10.3390/s26175392
GlyphTSR: Text-Rich Scene Image Super-Resolution Beyond Glyph Priors
Jiang, N., Qiu, Y., Zhang, J., Zhai, X., Zou, D., Ren, J., Xiong, Y., & Cao, X. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3725881
Representation learning in diffusion and flow-based model: an application aspect
Xu, Y., Huang, S., Gu, Z., Zhu, R., Gao, Y., & Zhang, H. (2026) · Vicinagearth. · doi:10.1007/s44336-026-00042-3
Li, J., Zhou, M., Chen, J., & Jiang, J. (2026) · International Conference on Geoinformatics · doi:10.1109/geoinformatics72247.2026.11665096
Vision-centric generative AI models: A software-hardware perspectivePreprint
Tselepi, E., Sestito, C., Agwa, S. O., & Prodromakis, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.27199
DoTCoM: high-performance mobile vision transformers with co-bias
Kwon, Y., Kim, W., 오수민, & Kim, H. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21890-7
Real‐Time LWIR Imaging and Ranging via 4D Light‐Field Metasurface‐Transformer Integrated Framework
Wan, D., Zhan, J., Yu, J., Chen, R., Guo, S., Hu, J., Jin, Y., Shen, X., Choudhury, P. K., & Ma, Y. (2026) · Laser & Photonics Review · doi:10.1002/lpor.71816
Ding, K., Jiao, C., Hu, Y., Wen, Z., Zhou, K., Gao, H., Wu, P., Sun, T., Mu, Y., & Liu, C. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3728795
RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation
Xiao, Z., Shen, Z., Qiu, Z., Yao, T., Liu, X., & Mei, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_37
Single-Image Turntable-Style Product Rotation Video Generation via Video Diffusion Models
Chen, P., & Sun, S. (2025) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid68789.2025.00077
M 3 amba: Multi-Modality Mamba for Image Fusion
Jing, R., Gao, Q., Duan, Y., & Gao, X. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3727130
Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation
Xie, X., Liu, J., Zhou, S., Fan, H., Han, Z., Tang, Y., & Qu, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37242-0_12
Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention
Liu, B., Ran, W., Zhang, J., Yuan, H., & Ma, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_1
GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation
Wang, X., Ibrahim, M., Mansoor, A., & Mian, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37432-5_37
Li, Q., Xiang, X., Hu, M., & Liang, Y. (2026) · Mathematics · doi:10.3390/math14173131
Kantheti, B., & de Araújo, C. A. P. (2026) · AI · doi:10.3390/ai7090340
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views
Stracquadanio, G., Raj, K., Grabinski, J., & Roth, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_17
TCD: Time-Conditioned Diffusion Decoding for Binary Short Block Codes
Zheng, J., Ni, J., Li, Z., Sun, Y., Tan, X., Huang, Y., & Zhang, C. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3712754
Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex DomainsPreprint
Wang, Z., Xu, M., & Mukerji, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.00297
DiffTCL: Diffusion-based augmentation for time series contrastive learning
Yu, Z., Wang, Z., Yuan, J., Pei, H., Fan, Y., & Li, M. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114833
Physics-Preserving Attention-Guided Artifact Removal for Spaceborne Optical Images
Cai, S., Hou, Z., Zhou, H., Pan, Z., & Wang, D. (2026) · Journal of Imaging · doi:10.3390/jimaging12090414
OutageDiT: A Foundation Model for Power Outage Forecasting and Scenario GenerationPreprint
Zhu, Y., Qiu, F., & Xie, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.01896
Liu, T. (2026) · International Conference on Artificial Intelligence, Virtual Reality and Interaction Design · doi:10.1145/3820915.3820966
Reconstructing synthetic hearts from ECG using flow matchingPreprint
Zheng, J., Kalaie, S., Ma, Q., Meng, Q., Rjoob, K. W. Y., Gifani, P., Hu, L., Babazade, N., Corianò, M., Zhong, W., et al. (2026) · medRxiv · doi:10.64898/2026.09.01.26360987
End–Edge–Cloud Collaborative Fast–Slow Semantic Planning for Agricultural Field Robots
Gao, B., Gong, L., Sun, Y., Lin, G., Chen, J., Xu, Y., Li, Y., & Liu, C. (2026) · Agronomy · doi:10.3390/agronomy16171725
Score-based diffusion models in Bayesian inverse problems
Schneider, F. (2026) · reposiTUm (TU Wien) · doi:10.34726/hss.2026.122044
EC-Flow: Entropy-Enhanced Contrastive Learning for Fixed-Point Constrained Time-Series Flow Matching
Xue, X., Fu, X., Gao, Y., Fu, Y., Li, L., Chen, T., Wang, R., Zhou, H., & Li, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37676-3_17
Tang, J., Li, W., Shi, Y., Deng, Y., & Zhao, J. (2026) · Sensors · doi:10.3390/s26175657
PicTune: A Framework for Optimal Selection on Text-to-Image Diffusion Models Fine-Tuning
Lewandowski, B., Birke, R., & Chen, L. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37657-2_25
Importance-Aware Low-Rank Distillation of Diffusion Transformers
Zavadski, D., Heid, S., Kalšan, D., Roth, S., & Rother, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37314-4_35
Yang, R., Lai, T., & Huang, H. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3731576
Swap the Right Identity: Spatio-Temporal Diffusion Preference Optimization for Character Swapping
Shen, H. F., Cheng, J., Li, D., Li, X., Feng, Y., & Li, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37095-2_35
Accelerating Diffusion Models via Equal-Risk Caching
Zhang, C., & Zou, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37044-0_11
Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness
Wei, H., Wang, Y., Huang, H., Sun, Z., & Zhang, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37029-7_15
Tang, R., Yang, S., Zhao, M., Wang, H., Wang, G., Zhu, L., Ren, H., Cong, M., & Meng, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.05579
The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video GenerationPreprint
Li, P., Xu, Q., Jiang, Y., Yu, Z., & Huang, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.07216
UniReflect: Self-reflection Tuning for Unified Multimodal Understanding and Generation
Wei, C., Huang, Z., Tan, H., Liang, D., Gao, L., Yan, P., & Wei, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37577-3_19
DriftParking: Trajectory Modeling via Drifting Field for End-to-End Automated ParkingPreprint
Wang, Z., Li, D., Wang, W., Lu, Y., Xie, J., Gu, J., & Zhang, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.06923
On-demand inverse design of metamaterials via denoising diffusion probabilistic models
Tran, T. V., Nanthakumar, S. S., Jin, Y., Chen, H., Rabczuk, T., & Zhuang, X. (2026) · Machine learning for computational science and engineering · doi:10.1007/s44379-026-00089-5
Unifying CNNs and ViTs for Learning-Efficient and Scalable Variational AutoEncoder
Lu, Z., Chai, S., Liu, C., Gong, L., Li, P., Ge, T., & Xie, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_37
Concept-Level Risk and Calibration for Governance in Diffusion Foundation Models
Xu, K., Zhang, Y., Wang, T., Qi, S., Carminati, B., Ferrari, E., & Fang, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835863
Zhao, H., Xu, M., Jin, Z., Hao, Y., Cui, S. R., & Han, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.07498
JSON: Jigsaw Self-play Optimization for Normalizing Flows
Yang, F., Zheng, T., Chen, J., & Li, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_29
Region-Aware Test-Time Scaling for Compositional Image Generation
Shen, M., Ye, P., Ma, X., Fang, G., Bouganis, C.-S., Zhao, Y., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_33
SignRefine: Adapting Foundational Video Models for Sign Language Generation
Pelykh, A., Fish, E., Sincan, Ö. M., & Bowden, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_10
On the Diffusibility of High-Dimensional Latents
Feng, C., Xu, Z., Chen, B., Xiong, Y., Wang, X., Wang, J.-H., Zhang, R., Lin, Z., Owens, A., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_9
PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction
Yang, Y., Wei, Y., Bai, B. B., Zhou, W., & Zhang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37432-5_31
Geometry-Preserving Image Generation for 6D Object Pose Estimation
Zhang, J., Song, R., Zhang, Z., Li, J., Cao, K., Peng, L., Ferstl, D., & Hu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_9
When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-training
Ikezogwo, W. O., Seyfioğlu, M. S., Krishna, R., & Bouyarmane, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_35
Iterative Perceptual Alignment for VLMs via Deterministic Reconstruction Feedback
Chen, X., Guo, H., Cai, N., & Luo, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_4
Class-Conditional Diffusion with MinAdaGN for Multi-Game Scene Generation
Liu, W. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682404
Li, M., Wang, Z., Qi, F., & Xu, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_28
Adaptive Noise Covariance Scheduling Under Riemannian Metrics for Diffusion Models
Deng, B., Hu, D., Tan, B., & Wu, J. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37020-4_16
PhysEdit: Physically Consistent Image Editing via Causal Enforcement
Wan, S., Chen, J., Li, Y., Pan, Y., Yao, T., & Mei, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_24
SKETCH ANIMATION FROM TEXT: METHODS, CONTROL AND MOBILE DEPLOYMENT
Терещенко, В. М., Tytarchuk, P., Hordiichuk, V. V., & Tereshchenko, Y. (2026) · Kibernetyka ta Systemnyi Analiz · doi:10.34229/kca2522-9664.26.5.3
Predictive Structure Improves Video Diffusion Dynamics
Luo, M., Chen, Y., Dimakis, A. G., Grauman, K. L., Chu, W.-S., & Tran, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_29
CtrlCoMo: Controllable Co-speech Motion Generation with Gesture–Action Disentanglement
Wang, X., Zhou, M., Zheng, Y., Xu, Y., Zhang, Y., Gao, M., Zhuang, N., & Mu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_15
Multi-scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
Zhou, N., Tu, Z., Yu, L., Cheng, K., Hu, J., Wang, N., & Chen, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37020-4_5
TDSR-VLA: Transition-Aware Denoising Sequence Representations for Vision-Language-Action
Kim, D., Song, K., Lee, S., Ju, H., Cha, E. S., & Kim, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_27
When Higher Order Hurts: Pre-asymptotic Order Collapse in Generative ODE Sampling
Salajegheh, F., & Mudur, S. P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_9
Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards
Choi, S.-Y., & Lee, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_12
Model-Aware Schedules Improve Generation via Fiberwise Optimal TransportPreprint
Jia, L., Zhang, B., Liu, Y., & Rulands, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.11842
SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction
Wang, P., Guo, P., Chai, K., Zhou, J., Xu, D., & Jiang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_21
Klar, R., & John, E. (2026) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas67364.2026.11680894
RUTaL: Residual Upcycling with Task Ladder for Efficient Multi-task Learning
Yao, H., Luo, W., Chen, Q., Liao, J., & You, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_1
MVI2V: Human Centric Image to Video Generation with Multiview Consistent Appearance
Liu, P., Xu, M., Jiang, W., Ge, T., & Zeng, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_22
Reconstructing 3D Human-Object Interaction via a Unified Triplane Space
Chen, Y., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_4
Logit Refiner: Improving Visual Autoregressive Models via Intra-scale Dependency Modeling
Li, M., Baumann, S. A., Krause, F., & Ommer, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37029-7_28
LayerVerse: Finding the Sweet Spot for KV-Injection in Training-Free Image Editing
Zhirnov, M., Kuzhamuratov, A., Кузнецов, А. В., Oseledets, I., & Sobolev, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_6
TBMP-Diff: Accelerator-Aware Timestep-Block Mixed-Precision Scheduling for Diffusion Inference
Huang, W., Zhu, Z., Jia, T., & Zhu, M. (2026) · International Symposium on Semiconductor and Electronic Technology (ISSET) · doi:10.1109/isset70600.2026.11682576
D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation
Zeng, P., Feng, D., Liu, Z., Peng, Z., Zeng, B., & Liu, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_10
Underwater image enhancement based on detail-aware compensation and semantic diffusion guidance
Liu, X., Gao, F., Han, C., Zhang, Q., Yang, Z., & Wu, G. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104968
Oswaal, S., Varshney, A., Sumithra, R., Sarode, S., & Shetty, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7450826
Revisiting Deepfake Detection: BCNet for Robust Generalization Beyond Semantic Dependence
Yang, J., Yao, S., Tao, R., Tan, C., & Zhao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37556-8_12
Unpaired Geometry-Guided Sim2Real Translation for Autonomous Driving
Chen, X., Wang, S., Gao, C., Gu, J., & Lan, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_23
CORE-V: Chain-of-Thought Reasoning for Image Editing with Visual Interaction
Yan, T., Zhao, P., Zheng, G., Xu, M., Zhang, Z., Dai, W., Zou, J., Xiong, H., Zhang, X., & Tian, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36839-3_29
Accelerating Diffusion Transformer with Dynamic Alignment
Chen, Q., Zhang, H., Wu, X., Dong, D., & He, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38401-0_15
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
