The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index; 1 of the 5 sources its claims cite were checked for support.
Scalable Diffusion Models with Transformers
Open accessAbstract
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops—through increased transformer depth/width or increased number of input tokens—consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
Diffusion Transformers (DiTs) replace the standard U-Net backbone in latent diffusion models with a transformer operating on latent patches. DiT-XL/2 achieves state-of-the-art class-conditional ImageNet generation, reaching FID 2.27 at 256×256 and 3.04 at 512×512.
Key findings
- DiT block conditioning matters: adaLN-Zero outperforms cross-attention and in-context conditioning at all training stages while being the most compute-efficient; at 400K iterations its FID is nearly half that of the in-context model.
- Scaling DiT Gflops improves sample quality: across 12 models, transformer Gflops and FID-50K at 400K steps have a correlation of −0.93, with gains from increasing depth/width or number of input tokens.
- DiT-XL/2 sets state of the art: FID 2.27 on class-conditional ImageNet 256×256 with classifier-free guidance cfg=1.50, improving on LDM’s previous best 3.60; at 512×512 it reaches FID 3.04 versus ADM’s 3.85.
- Larger DiT models are more compute-efficient, and extra sampling compute cannot compensate for smaller models: DiT-L/2 with 1000 sampling steps uses 80.7 Tflops and gets FID-10K 25.9, while DiT-XL/2 with 128 steps uses 15.2 Tflops and gets FID-10K 23.7.
Methods
- Design: latent diffusion with a frozen off-the-shelf Stable Diffusion VAE (downsample factor 8); DiT patchifies latents, applies ViT-style positional embeddings, processes tokens through N transformer blocks, and linearly decodes to noise and covariance predictions. Design space includes patch sizes p=2,4,8; block variants in-context, cross-attention, adaLN, and adaLN-Zero; model sizes DiT-S/B/L/XL.
- Data and training: class-conditional ImageNet at 256×256 and 512×512; AdamW, constant learning rate 1×10⁻⁴, batch size 256, horizontal flips, EMA decay 0.9999, no learning-rate warmup or regularization; diffusion hyperparameters retained from ADM; implemented in JAX on TPU-v3 pods.
- Evaluation: FID-50K with 250 DDPM sampling steps using ADM’s TensorFlow evaluation suite; 12 DiT models swept over S/B/L/XL and p=8/4/2 at 400K steps; DiT-XL/2 trained for 7M steps at 256×256 and 3M steps at 512×512; additional comparisons of conditioning strategies and model versus sampling compute.
Limitations
- The paper does not state an explicit limitations section.
- Evident from the text: experiments are limited to class-conditional ImageNet at 256×256 and 512×512; text-to-image and other domains are left to future work.
- Evident from the text: DiTs use a frozen off-the-shelf VAE, so generation quality depends on that VAE; training hyperparameters were retained from ADM and not tuned; pixel-space DiT is mentioned as possible but not tested.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
28 Own result · 5 Own interpretation · 4 No basis given · 3 Sources not found · 2 Own method · 1 Partly supported · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As shown in Figure 2, LDMs achieve good performance while using a fraction of the Gflops of pixel space diffusion models like ADM.”
§ 3. Diffusion Transformers > 3.1. Preliminaries
What the sources say
- Partly supportedcites [48] sourceExperimental — accuracy not yet measured
Section 4.2 reports performance close to ADM on LSUN-Bedrooms while using four times fewer training resources, and Appendix D.4 describes competitive ImageNet performance with lower compute requirements. These passages support the performance-and-efficiency comparison, but our copy does not give a GFLOPs comparison with ADM; it reports training resources instead. (LLM, conf=0.85)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Larger DiT models are more compute-efficient.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Adaptive layer norm works best.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Transformer Gflops are strongly correlated with FID.”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Performance steadily improves in FID as model flops increase.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing transformer forward pass Gflops increases sample quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results demonstrate that different DiT configs obtain similar FID values when their total Gflops are similar (e.g., DiT-S/2 and DiT-B/4).”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, scaling both model size and the number of tokens yields notable improvements in visual quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all four configs, significant improvements in FID are obtained over all stages of training by making the transformer deeper and wider.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Scaling the transformer backbone yields better generative models across all model sizes and patch sizes.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 4
- Probably not a substantial claim. 6
- It may state two separate claims as one. 18
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Cross-attention adds the most Gflops to the model, roughly a 15% overhead.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“As with prior work using guidance, we observe that larger scales increase visual fidelity and decrease sample diversity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For both the 256 × 256 and 512 × 512 DiT-XL/2 models, we never observed FID saturate and continued training them as long as possible.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of the three block designs we explore, adaLN adds the least Gflops and is thus the most compute-efficient.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 2. Benchmarking class-conditional image generation on ImageNet 256×256. DiT-XL/2 achieves state-of-the-art FID.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When trained for only 2.35M steps (similar to ADM), XL/2 still outperforms all prior diffusion models with an FID of 2.55.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XL/2 again outperforms all prior diffusion models at this resolution, improving the previous best FID of 3.85 achieved by ADM to 3.04.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we did not find learning rate warmup nor regularization necessary to train DiTs to high performance.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the Gflops in the model—either by increasing transformer depth/width or increasing the number of input tokens—yields significant improvements in visual fidelity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find a strong negative correlation between model Gflops and FID-50K, suggesting that additional model compute is the critical ingredient for improved DiT models.”
- Also stated in: § 100 101 102 · boosted
“Transformer Gflops are strongly correlated with FID.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 100 101 102 · boosted
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, we also observe that DiT-XL/2 achieves higher recall values at all tested classifier-free guidance scales compared to LDM-4 and LDM-8.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing DiT model Gflops (via transformer size or number of input tokens) causes the training loss to decrease more rapidly and saturate at a lower value.”
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
“Note that scaled-up DiT models exhibit lower training losses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We did not tune learning rates, decay/warm-up schedules, Adam β1/β2 or weight decays.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“which have been shown to scale more effectively for visual recognition than traditional convolutional networks (e.g., ResNet [15]).”
What the sources say
- Not matchedcites [10] Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Even without these techniques, training was highly stable across all model configs and we did not observe any loss spikes commonly seen when training transformers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“diffusion models have been at the forefront of recent advances in image-level generative models [9,46]; yet, they all adopt a convolutional U-Net architecture as the de-facto choice of backbone.”
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [46] Ramesh, 2022, Hierarchical text-conditional image generation with clip latents
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“Note that prior work [9] measures Precision and Recall using 1000 real samples for 512 × 512 resolution; for consistency, we do the same.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 1,000- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“halving pwill quadruple T , and thus at least quadruple total transformer Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A smaller patch size p results in a longer sequence length and thus more Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper relies on this without support.
FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
“We show samples from the model in Figures 1, and we compare against state-of-the-art class-conditional generative models. We report results in Table 2.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Unlike prior works that employ text-to-image (T2I) U-Net [10, 33, 35, 40] for talking head generation, MoCha is built on a diffusion transformer (DiT) [26]. By incorporating text and speech conditions sequentially via cross-attention, it effectively captures both semantics and temporal dynamics.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [26]
In the citing paper
“Supervised learning, a foundational approach in AI, uses labeled datasets to guide models towards accurate predictions, and it has been integral to various applications, including image recognition and NLP [163], [164], [165].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [164]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Research works printed but not linked: 3
- Chen, Generative pre-training from pixels
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- Goodfellow, Generative adversarial nets
Cited by
Sorted by citations
Items 2,101–2,200 of 3,684
Zhou, J., Li, H., Jiang, K., Sun, Y., & Jia, T. (2026) · Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference · doi:10.1109/isscc49663.2026.11409066 · Cited by 1
VAR-Turbo: Unlocking the Potential of Visual Autoregressive Models Through Dual Redundancy
Xiang, X., & Tu, F. (2026) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca68181.2026.11408607 · Cited by 1
Cross-Resolution Distribution Matching for Diffusion Distillation
Chen, F., Pan, H., Xu, H., Duan, X., Wang, Z., & Wang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37138-6_20 · Cited by 1
Chen, Z., Chan, N. T., Hou, Y., Tie, C., Liu, Z., Chen, H., Chen, J., Shi, J., Gao, Y., Huo, J., et al. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11695867 · Cited by 1
Unveiling the Modular Design of Text-to-Video Quality Assessment
郑炳坤, Zhang, W., Zhai, G., & Yang, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3673333 · Cited by 1
Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback
Hirakawa, Y., Wada, T., Shimizu, R., Furusawa, T., Saito, Y., Araki, R., Chen, T., Mo, F., & Aoki, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_37 · Cited by 1
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
Wang, A., Ao, Y., Wu, S., & Tang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37242-0_15 · Cited by 1
A DiT-based multi-scenario optical temporal prediction model for pipeline corrosion
Cai, J., Wang, R. C., Hou, Z., Xu, X., & Pan, Y. (2026) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2026.108726 · Cited by 1
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
Lin, H., Pan, X., Wang, Z., Zhang, Y., Wang, C., Cho, J., & Bansal, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_21 · Cited by 1
Correlation-Weighted Multi-reward Optimization for Compositional Generation
Wi, J., Kim, H.-S., & Kim, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37429-5_7 · Cited by 1
Seismic random noise attenuation with diffusion transformer
Cheng, Z., Guo, Z., Li, F., & Gao, T. (2026) · Journal of Geophysics and Engineering · doi:10.1093/jge/gxag042 · Cited by 1
Toward Intelligent IoT Services: A Generative AI-Assisted Semantic-Aware Framework
Niu, X., Yuan, W., Tan, L., Wu, J., & Wang, X. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3677174 · Cited by 1
VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers
Seyfarth, M., Dar, S. U. H., Frisch, Y., Wild, P., Frey, N., André, F., & Engelhardt, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38189-7_57 · Cited by 1
DAttnVis: Attention-guided visual diagnostics for stable diffusion inference in image generation
Liang, X., Chen, Y., & Lv, C. (2026) · Information Visualization · doi:10.1177/14738716261434840 · Cited by 1
Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data
Zhang, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729135 · Cited by 1
OmniColor: A Unified Framework for Multi-modal Lineart Colorization
Zhang, X., Du, H., Wei, X., & Li, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36987-1_21 · Cited by 1
Mastering Deep Learning: From Neurons to Large Language Models
Firouzi, F., Farahani, B., & Ray, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-06286-4_3 · Cited by 1
EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
Park, D., Li, Y., Tulyakov, S., & Kag, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37314-4_17 · Cited by 1
A generative model of lung CT conditioned on radiomics features
Li, P., Yuan, Y., Wang, X. E., Din, H., Lin, C. T., KIM, G. H., McNitt-Gray, M. F., Stayman, J. W., & Gang, G. J. (2026) · SPIE Medical Imaging: Physics of Medical Imaging · doi:10.1117/12.3088074 · Cited by 1
AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction
Maksutova, A., Seenivasan, L., Ding, H., Xu, J., Yu, C., Jing, C., Shen, Y., & Unberath, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38233-7_2 · Cited by 1
Research and Analysis of Diffusion Model Sampling Acceleration Technology
Hei, Y. (2026) · ITM Web of Conferences · doi:10.1051/itmconf/20268403033 · Cited by 1
Local Brain Tumour Inpainting Using Diffusion Transformers
Koch, A., Aydin, O. U., Hilbert, A., & Frey, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16370-7_12 · Cited by 1
Liu, M., Ye, Y., Li, H., Guo, Y., Liang, P., Li, X., Yin, C., Yu, X., Dong, X., Yao, Y., et al. (2026) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-026-01979-8 · Cited by 1
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
Chen, Z., Potamias, R. A., Chen, S., Deng, J., Schmid, C., & Zafeiriou, S. P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37232-1_25 · Cited by 1
UniCross3D: Unified Cross‐View and Cross‐Domain Diffusion for Consistent Single‐Image 3D Generation
Jun, U.-C., Meinhold, H., & Kang, J. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70378 · Cited by 1
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
Lyu, H., Li, Z., Hong, Y., Weng, Y., Shi, J., Zhang, H., & Liang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_14 · Cited by 1
Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching
Vosoughi, A., Zang, Y., Yang, Q., Paek, N. J., Leistikow, R. J., & Xu, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463324 · Cited by 1
Gen-SER: When the Generative Model Meets Speech Emotion Recognition
Wang, T., Zhao, J., Chen, R., Lei, T., Wang, W., & Yu, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463095 · Cited by 1
Taming Audio VAEs via Target-KL Regularization
Seetharaman, P., & Kumar, R. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460662 · Cited by 1
SSG-DIT: A Spatial Signal Guided Framework for Controllable Video Generation
Hu, P., Gu, Y., Luo, L., & Ren, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461432 · Cited by 1
Enhancing Quantization for Visual Autoregressive Generation Via Uncertainty Identification
Liu, J., Xiong, G., Ren, S., Gao, R., Yu, L., & Fu, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462147 · Cited by 1
Fung, K. C., Cheung, T.-H., Lai, S., Xue, K., & Lam, K. (2026) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2026.112786 · Cited by 1
NABLA: Neighborhood Adaptive Block-Level Attention for Efficient Video Generation
Mikhailov, D., Letunovskiy, A., Kovaleva, M., Arkhipkin, V., Korviakov, V., Polovnikov, V., Vasilev, V., Sidorova, E., & Dimitrov, D. (2026) · IEEE Access · doi:10.1109/access.2026.3686867 · Cited by 1
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
Xiao, Y., Zhao, Y., Ma, Z., Wang, S., Yu, K., Liao, J., & Chen, X. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3687016 · Cited by 1
Arora, A., Zaeem, J. M., Garg, V., Aggarwal, K., & Gao, X. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01247-7 · Cited by 1
Dlfr-Gen: Diffusion-Based Video Generation With Dynamic Latent Frame Rate
Yuan, Z., Xie, R., Shang, Y., Zhang, H., Wang, S. S., Yan, S., Dai, G., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01523 · Cited by 1
ConsistentCity: Semantic Flow-Guided Occupancy DiT for Temporally Consistent Driving Scene Synthesis
Zhu, B., Wang, X., & Li, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02448 · Cited by 1
DICE: Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
Luo, J., Luo, L., Xu, J., Song, J., Lu, R., Tang, C., & Wang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01436 · Cited by 1
Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
Dedhia, B., Bourgin, D., Singh, K. K., Li, Y., Yan, K., Xu, Z., Jha, N. K., & Liu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01427 · Cited by 1
Fontanimate: High Quality Few-Shot Font Generation Via Animating Font Transfer Process
Fu, B., Wang, Z., Yan, K., Zhao, S., Qin, Q., Wen, J., He, J., & Gao, P. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01486 · Cited by 1
Tree Skeletonization From 3D Point Clouds by Denoising Diffusion
Marks, E., Nunes, L., Magistri, F., Sodano, M., Marcuzzi, R., Zimmermann, L., Behley, J., & Stachniss, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02563 · Cited by 1
DeFSS: Image-to-Mask Denoising Learning for Few-Shot Segmentation
Qin, Z., Xu, J., & Ge, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02064 · Cited by 1
Gudovskiy, D., Zheng, W., Okuno, T., Nakata, Y., & Keutzer, K. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00591 · Cited by 1
Yang, C., Xi, S., Ding, H. Q., Shen, Y., & Liu, Y. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00623 · Cited by 1
Kim, B., Lee, K., Jeong, I., Cheon, J., Lee, Y., & Lee, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00386 · Cited by 1
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
Xiao, J., Liang, D., Zhou, X., Ye, Y., Su, T., Yi, G., Xia, B., Lyu, Q., Shi, S., Huang, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37044-0_24 · Cited by 1
BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity
Koo, J., Lin, W.-T., Park, C., Park, C., & Sung, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00178 · Cited by 1
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-view Captures
Ntavelis, E., Wu, S., Shahbazi, M., Maninchedda, F., Kostiaev, D., Sevastopolsky, A., Megaro, V., Phillips, T., Blumentals, A., Ravikumar, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_3 · Cited by 1
From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation
Qu, Z., Li, X., Kang, H., Gu, H., Meng, Q., Niu, T., Yang, X., & Pan, R. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810595 · Cited by 1
Chen, M., Zirou, L. I. N., Song, X., Luo, Y., Duan, X., Li, S., & Xie, C. (2026) · Sensors · doi:10.3390/s26102972 · Cited by 1
StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing
Chen, L., Zhou, T., He, X., Tang, B., Wu, Z., Huang, Y., Wu, Y., Sun, Z., Yang, W., & Meng, H. M. L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3688404 · Cited by 1
Generative Preprocessing for Image Compression with Pre-Trained Diffusion Models
Guo, M., Zhao, S., Li, J., & Zhang, L. X. (2026) · DCC · doi:10.1109/dcc66757.2026.00015 · Cited by 1
Sampling-Free Diffusion Transformers for Low-Complexity MIMO Channel Estimation
Chen, Z., Shin, H., & Nallanathan, A. (2026) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2026.3693087 · Cited by 1
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
Wu, Z., Xu, L., Jiang, P., Liu, S., Guo, C., & Bai, X. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811135 · Cited by 1
Guo, Y., Zhuang, S., Huang, Z., Fu, C., Li, C., Lyu, J., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37602-2_36 · Cited by 1
RSEdit: Text-Guided Image Editing for Remote Sensing
Chen, Z., Zhang, Z., & Zhang, F. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3695484 · Cited by 1
Zhou, Y., Zhang, Z., Pan, J., Lin, Z., & Tu, Z. (2026) · The Visual Computer · doi:10.1007/s00371-026-04522-x · Cited by 1
Mao, Y., He, G., Wang, G., Yin, R., Zhang, H., & Chen, Z. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3696382 · Cited by 1
Matteschk, P., Aragón, M., Gomez, J., Ribel, H., Knopp, M. T., Blum, N. B., & Nouri, B. (2026) · Photonics · doi:10.3390/photonics13060515 · Cited by 1
Zhong, J., Zhang, M., Liu, L., Liu, T., Jiang, J., Piao, Y., Xu, R., Tian, F., Sun, W., Bi, H., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104138 · Cited by 1
Zhu, Y., Jiang, G., Liang, Z., & Wang, Y. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3697013 · Cited by 1
Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing
Nakayama, K., Shen, I., Liu, R., Wang, Y., Wetzstein, G., & Igarashi, T. (2026) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-c-000804249 · Cited by 1
RayDer: Scalable Self-supervised Novel View Synthesis from Real-World Video
Prestel, U., Baumann, S. A., Stracke, N., & Ommer, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37044-0_31 · Cited by 1
Diffusion Models in Robotics: A Survey
Liu, X., Ma, K., Gao, C., & Shou, M. Z. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02893-1 · Cited by 1
Multi-Temporal Latent Diffusion Transformers for Cloud Removal in Remote Sensing Images
Ahmed, F., Jen, C., & Basu, A. (2025) · International Conference on Smart Multimedia (ICSM) · doi:10.1109/icsm64417.2025.11541561 · Cited by 1
CultureScore: Evaluating Cultural Faithfulness in Video Generation Models
Rani, A., Dai, W., Nayak, S., Maes, P., Kalayeh, M. M., & Liang, P. P. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.2166 · Cited by 1
MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration
Wei, Y., Diao, L., Chen, B., Cheng, S., Qian, Z., Yu, W., Xiao, N., Lin, W., & Du, J. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810881 · Cited by 1
Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation
Yang, X., Li, Y., Qian, G. G., Skorokhodov, I., Ivanov, V., Vinella, A., Zhang, X., Wang, Y., Tulyakov, S., & Kag, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37383-0_28 · Cited by 1
Zheng, Y., Liu, D., Li, R., Wang, R., Fan, J., Guo, K., & Liang, J. (2026) · Remote Sensing · doi:10.3390/rs18121994 · Cited by 1
TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
Gao, X., Zhu, C., Fang, Y. D., Hu, Q., & Zhang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37010-5_20 · Cited by 1
Learning Natural Pedestrian Policies via Human Demonstration for Human-Vehicle Interaction
Zhang, C., Long, T., Yu, F., Xu, L., Liu, Y., Ye, Q., Wang, L., & Li, L. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3701235 · Cited by 1
Jin, Z., Li, N., Yang, T., Zhang, H., & Huang, X. (2026) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc65185.2026.11555426 · Cited by 1
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
Duan, K., Xu, Z., Liu, W., Ruan, X., Chen, X., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37435-6_19 · Cited by 1
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Kocabaş, M., Gao, G., Schölkopf, B., & Geiger, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_35 · Cited by 1
Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space
Cao, Y., Gu, J., Kungurtsev, V., Hu, Y., Hamari, J., Liu, Z., & Zardadi, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_7 · Cited by 1
Guo, C., Fan, H., Dong, S., Yin, M., Qi, G., Ma, Y., Jing, C., Liu, H., Song, N., & Kang, Y. (2026) · Applied Sciences · doi:10.3390/app16126250 · Cited by 1
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
Chen, Y., Xu, X., Wang, S., Zhang, X., Guo, Q., Ge, T., & Wang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37086-0_18 · Cited by 1
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
Deng, H., Yan, K., Mao, C., Wang, X., Liu, Y., Gao, C., & Sang, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37531-5_3 · Cited by 1
Kui, X., Zhang, M., Liu, B., Li, Q., Zou, B., & Chen, L. (2026) · Meta-Radiology · doi:10.1016/j.metrad.2026.100234 · Cited by 1
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
Li, Z., Dong, C., Du, Z., Zhou, H., Qiu, C., Qin, H., Yang, M., Wei, D., & Liu, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_23 · Cited by 1
GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
He, Y., Wang, J., Wang, X., Fong, M., Zhang, S., Xue, Y., Zheng, H.-T., & Ma, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_24 · Cited by 1
HorizonRelight: Relighting Long-Horizon Videos Consistently via Diffusion Transformers
Yang, J., Jaiswal, M. S., Wang, Z., Zeng, S., Zhao, Y., Pereira, R., & Min, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36969-7_17 · Cited by 1
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
Gao, H., Zhao, F., Hui, Q., Shi, F., Zhao, S., Li, Y., Tan, C., Lu, T., You, Y., Wang, K., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37467-7_18 · Cited by 1
Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
Wang, B., Chen, S., Zhao, J., Liu, X., Lei, Z., & Zhu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_5 · Cited by 1
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
Cao, D., & Nguyen-Ha, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_29 · Cited by 1
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
Zhang, X., Zhuang, J., Zhai, H., Yan, Z., Chen, J., Zhang, G., & Fan, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_2 · Cited by 1
Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
Rawal, R., Shirkavand, R., Paul, S., Wen, Y., Huang, H., Chen, Y., Goldstein, T., & Somepalli, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37335-9_7 · Cited by 1
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
Li, H., Fu, W., Cong, X., Li, Z., Huang, B., Jiang, H., He, X., Liang, Y., Fu, R., Lu, T., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_9 · Cited by 1
Song, H., Choi, S., & Do, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_7 · Cited by 1
Towards Real-World Wearable Motion Reconstruction
Camiletto, A. B., Dabral, R., Alvarado, E., Beeler, T., Habermann, M., & Theobalt, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_17 · Cited by 1
DualBrep: A Dual-Field Continuous Representation for B-rep Modelling
Liu, Y., Jayaraman, P. K., Reddy, C., Xu, X., & Shayani, H. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811057 · Cited by 1
Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration
Goldberg, K., Richardson, E., & Vinker, Y. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811121 · Cited by 1
Learning Sewing Patterns via Latent Flow Matching of Implicit Fields
Cao, C., Li, R., Dumery, C., & Li, H. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811055 · Cited by 1
Garment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing
Nakayama, K., Shen, I., Liu, R., Wang, Y., Wetzstein, G., & Igarashi, T. (2026) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3799902.3811102 · Cited by 1
Chen, Z., Wei, P., Dai, G., Wang, J., & Wang, M.-Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_2 · Cited by 1
Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation
Karageorgiou, D., Papadopoulos, S., Kompatsiaris, I. Y., & Gavves, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_19 · Cited by 1
TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution
Gao, S., Zhou, Z., Liu, Y., Shen, T., Wu, Z., & Timofte, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37035-8_3 · Cited by 1
Liao, Y., Lei, T., Wang, X., Wang, D., Liu, D., Gong, M., & Nandi, A. K. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3717664 · Cited by 1
DDPM-Driven Background Suppression for Efficient and Accurate Hyperspectral Anomaly Change Detection
Hu, X., Liu, H., Hong, D., Duan, Q., & Zhang, D. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3718648 · Cited by 1
Oraki, S., Ding, F., & Liang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31920-3_17 · Cited by 1
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
