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 3,101–3,200 of 3,684
From Convolution to Attention and Beyond: A Systematic Review of Modern Vision Architectures
Chakrabarty, A., Aziz, A., Tahsin, A., Nawreen, N. I., Alam, M. G. R., & Maidin, S. S. (2026) · IEEE Access · doi:10.1109/access.2026.3715655
Huang, M., Li, H., Zhang, Y., Chen, J., Wang, G., Li, X., Bhatti, U. A., & Bai, Z. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115713
Scanner‐agnostic artificial intelligence approach for fast bone scintigraphy
Menezes, V. D. O., Queiroz, C. C., Oliveira, A. A. S., Filho, A. J. D. S., MORAIS, A. F. D., Vigário, A., Flamini, M. E., Mourato, F. A., Ren, T. I., & Machado, M. A. D. (2026) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.70709
From Dark Matter to Galaxies: Halo-Free Mock Generation via Conditional Point-Cloud DiffusionPreprint
Moriwaki, K., Osato, K., & Yoshida, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.19808
Li, Q., Xiang, X., Liang, Y., & Hu, M. (2026) · Sensors · doi:10.3390/s26154694
Wang, X., Gao, R., Zhang, Q., Lv, D., Zhao, R., Xd, T., Yi, H. L., Li, Y., Zhong, J., Liu, C., et al. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3713567
Benchmarking and Improving Perceptual Straightening for Robust AI-Generated Video Detection
Papougiannakis, X., & Tous, R. (2026) · Electronics · doi:10.3390/electronics15153245
RWSG: Region-Weighted Semantic Guidance for Pose-Free Sparse Multi-View Reconstruction
Tan, R., Li, W., Li, S. Y., Tong, H., Zhang, C., Zhang, F. W., Dong, J., & Cai, Q. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3716507
A survey of deep learning in image processing: developments, applications and challenges
Xiong, Z., Tang, X., & Verbeek, F. J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11618-2
SynBoost: A Synergistic Framework for Fast Sampling of Diffusion Models
Hu, Y., Luo, H., Fu, X., Huang, J., Wang, F., & Zhao, F. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3716761
Chen, Z., & Zhang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.20598
GraphVid: Interactive Graph-Controllable Video Generation
Shah, V., Susladkar, O., Prakash, T., Nguyen, K. A., Yu, T., Juvekar, A. S., Wahed, M., & Lourentzou, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_14
Robbins, L. B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.21434
Mobile anime character generation using artificial intelligence and interactive creative pathways
Gao, J. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01801-3
Diffusion Models in Medical Image Inpainting: Challenges, Solution Taxonomy, and Future DirectionsPreprint
Mangussi, A. D., Santos, J. C., Pereira, R. C., Lorena, A. C., Figueiredo, M. A. T., & Abreu, P. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.21904
TECMO: Efficient Te mporal C ross-Interaction Mo dule for Long Synchronized Audio-Video Generation
Ergasti, A., Tarollo, G., Botti, F., Fontanini, T., Ferrari, C., Bertozzi, M., & Prati, A. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3717470
Elhanashi, A., Essahraui, S., Zheng, Q., & Saponara, S. (2026) · Applied Sciences · doi:10.3390/app16157430
Joint Optimization of Inference and Consensus for Blockchain-Enhanced Edge AIGC Services
Ye, L., Xiong, Z., Luo, Y., Luo, J., Cao, B., & Gao, L. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3717308
MicroZoom: Structure-Preserving Detail Synthesis at Extreme ScalePreprint
Huynh, H., Ma, J., Curless, B., Kemelmacher-Shlizerman, I., & Seitz, S. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.24729
Yurong, G., Yufei, H., Yonghao, L., Dongliang, C., Ke, Z., & Zhanyu, M. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836300
InDepthVOI: Geometry-Aware Video Object Insertion via Joint Generation
Han, K., Kang, K., & Cho, S. (2026) · Journal of the Korea Computer Graphics Society · doi:10.15701/kcgs.2026.32.3.109
Decoupled Semantic Flow Matching with Dynamic Reconstruction for Generalized Zero-Shot Learning
Song, C., Song, M., Liu, Y., & Qian, P. (2026) · Electronics · doi:10.3390/electronics15153359
UniCam: Taming Unified Diffusion Models in Noise Space for Camera-controllable Video Rendering
Zhao, H., Wu, Z., & Jiang, Y. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02968-z
Schrödinger’s Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics
Phan, T., Wiese, J., & Ommer, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_33
LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
Karimov, M., Spasojevic, T., Braun, M., Wiederer, J., Belagiannis, V., & Pollefeys, M. (2026) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv66570.2026.11623870
Li, X. L., Huang, X., Tao, S., Liang, C., Wang, R., Wang, J., Zhang, J., & Xia, B. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133813
Shen, L., Jin, Z., Li, X., Tao, W., Li, S., Yang, Y., Han, C., Li, S., Cai, Z., & Liu, L. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783931
Yang, B., Shen, R., Chen, Y., Ni, R., & Wang, W. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3719318
StormMind: Disentangled Layerwise Modeling for Convective Weather Systems
Chen, J., Qiu, M., Chen, L., Fang, Y., Zhong, S., Chen, B., & Wu, K. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783926
Du, C., Deng, Y., Ren, J., & Zhang, Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780174
Wang, X., Huang, Y., Su, Y., Luan, P., Zhang, T., Wei, F., & Yu, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_34
Unique Step Refinement for Transformer-Based Generative Models
Grimal, P., Borgne, H. L., & Ferret, O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31666-0_29
What Matters in Virtual Try-Off? Dual-UNet Diffusion Models for Garment Reconstruction
Truong, L.-P., Madadi, M., & Escalera, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31663-9_22
fm-AD: Feature Density Modeling for Unsupervised Anomaly Detection with Continuous Normalizing Flows
Bøss, J., & Wilm, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31404-8_21
Saleem, A. B., Ahmed, A. A., Behera, A., Amin, H., Liao, I. Y., Khattab, M., Pan, J. W., & Makmur, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31927-2_28
Nguyen, H. N., Van, B., Hoang, H., Dao, H., & Tran, C. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-2590-3_14
Efficient Caching for Conditional Flow Matching in Vietnamese Zero-Shot TTS
Trần, H. N., Nguyen, T. L., Tran, T. H., Le, N. M., & Do, V. H. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-2584-2_27
All-in-One Conditioning for Text-to-Image Synthesis
Jayasekara, H., Huynh, C., Ren, Y., Acquaye, C., & Shrivastava, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31583-0_2
ClimDiT: A Generative Latent Diffusion Transformer Framework for Multivariate Climate Downscaling
Esquivel-González, M., González, A., Díaz, J. P., Pérez, J. C., González-Abad, J., & Márquez-Cubas, S. (2026) · Earth Systems and Environment · doi:10.1007/s41748-026-01326-w
LFG: Local Controllable 3D Generation Using Latent Flexible Grid Representation
Zhang, K., Han, T., & Quan, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31335-5_16
Enhancing Wind Turbine Nacelle Fire Detection via Stable Diffusion
Liang, P., Zhang, B., Ma, J., & Li, H. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-9705-5_18
Zhang, S., Sitong, G., Kong, X., Liu, P., Guo, Y., Zhang, L., & Rao, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_25
Li, Y., Li, C., Jin, Y., Wang, H., Sheng, M., & Ren, J. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10750-0
Zhao, X., Yan, L., Li, J., Wu, Y., & Tu, F. (2026) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca66397.2026.00188
HumanDiff: Leveraging body-part expert-assisted diffusion transformers for human image generation
Huang, Y., Wang, Z., Li, H., Zheng, J., Luo, Y., Chen, T., & Wu, S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116762
Controllable Image Synthesis for Endoscopy: Leveraging Text and Spatial Guidance in Diffusion Models
Xu, L., Vats, A., Pedersen, M., & Raja, K. B. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00008
Not All EEG Moments Are Equal: Position-Adaptive Time Scheduling for EEG GenerationPreprint
Liu, B.-H., Li, Z., Duan, C., Li, Q., & Wu, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.00048
A Diffusion-Driven Local Planner for Robotic Manipulators in Constrained Environments
Lian, Z., Sun, C., Yang, H., & Chi, W. (2026) · International Conference on Control and Automation · doi:10.1109/icca69928.2026.11618042
tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital TwinsPreprint
Seo, M., Ghafoor, H., Seol, M., Cho, S., & Yoon, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.01839
Han, J., Wang, Z., Liu, W., Song, B., Wang, C., & Liu, X. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116784
Fu, X., Zhang, Y., Xie, M., Gao, Z., & Lin, F. (2026) · International Conference on Control and Automation · doi:10.1109/icca69928.2026.11618163
Nguyen, T., Stamm, M. C., Crisman, J., Hostetler, J., Cassano, L., Davinroy, M., & Bautista, P. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00103
Lin, D., & Jiao, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.00903
Handsurge: Localized Neural Surgery for Diffusion-Generated Hand Deformity Restoration
Lao, Z., Ma, D., & Yu, H. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00116
GSID: Guided single-image generation with diffusion models
Bian, R., Yang, S., Li, H., & Yang, H. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104921
Tan, S., Xu, Y., Lin, Q., Ge, M., Wu, Y., & Jin, J. (2026) · Integrative Zoology · doi:10.1111/1749-4877.70157
Orthogonal Projection Steering for Bias Mitigation and ICAO Compliance in Diffusion Transformers
Mudgalgundurao, R., Khurana, A., Schuch, P., Ramachandra, R., & Raja, K. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00105
Predictive Enhancement Calibration for Latent Breast MRI Virtual Contrast EnhancementPreprint
Lei, Q., & Wu, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.03612
ASPI-DiT: An Amortized Diffusion-Transformer Framework for Ill-Posed Mechanistic Parameter Inversion
Chen, Y., He, Y., Cao, D., Cui, J., Li, Y., & Li, S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818909
Relaxed Bipartite Matching with Structural Inertia for Efficient Diffusion
Zhou, Q., Gong, X., Wu, W., Jia, Y., Gao, J., & Wang, Q. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817743
Pinterest Canvas: Large-Scale Image Generation at Pinterest
Wang, Y., Tzeng, E., Shiau, R., Yang, J., Kislyuk, D., & Rosenberg, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818463
Causal-DFM: Diffusion-Based Causal-Invariant Dynamic Factor Model for Stock Return Prediction
Yin, Z., He, Y., Qin, X., Ren, J., Fu, S., & Wang, X. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818050
Cao, H., Sun, H., Liang, J., Li, M., & Ren, Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818937
Diffusion-based Spatio-temporal Interpolation with Dynamic Sensor Sets
Islam, M. S., Tadepalli, P. V., & Fern, A. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817811
Xie, W., Zeng, Q., Meng, Z., Tian, J., He, S., Yang, D., Du, J., Wang, Y., Li, D., Wang, H., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817651
Low-Rank Spectral Flow Matching for Human Trajectory Prediction
Mao, C., Hu, J. W., & Min, G. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818207
Skillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling
Wang, W., Chen, W., Yuan, Q., Shen, L., Peng, B., Chen, J., Wu, B., & Sun, L. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818855
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
Chang, C.-H., Ho, K.-S., Tsai, C.-Y., Chen, K.-L., Huang, Y.-S., & Ding, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818078
Lan, H., & Wang, F. (2026) · International Conference on Intelligent Engineering and Next-Gen Healthcare Systems (IEHNS) · doi:10.1109/iehns68708.2026.11607457
Martian DEM Void Filling With Orientation-Guided Diffusion Transformer and Topographic Constraints
Xu, J., Cao, J., Huang, R., Xu, Y., Feng, Y., & Tong, X. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3721742
Benito-Del-Valle, L., Moreno-Sánchez, P. A., Egusquiza, I., Vitoria, I., Picón, A., Saratxaga, C. L., & Galdrán, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-25180-0_17
Enhancing pan-cancer spatial transcriptomics at single-cell resolution with stPainter
Yang, Y., Luo, Y., Zhang, K., Zhang, Z., Peng, H., Cao, C., Liu, Q., Ma, B., Chen, Y., Shen, L., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-76552-x
Efficient AI-Generated Image Detection via Confidence-Aware Cascading
Chen, X., Yu, Y., Wang, H., Zhang, J., & Guo, E. (2026) · doi:10.1109/icbdse70225.2026.11635577
Xue, Y., Qu, H., Li, Z., Xu, H., Yin, J., See, S., Rahmani, H., & Liu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_31
Adverse Weather Image Restoration Method Based on Conditional Diffusion Models
Zhang, X., Wang, X., Peng, X., Zhang, X., Jiang, L., Dong, M., & Ota, K. (2025) · IEEE International Conference on Big Data and Cloud Computing (BDCloud) · doi:10.1109/bdcloud67918.2025.00011
Ding, C., Tan, S., Lin, Q., Jiang, X., Zeng, Z., & Pan, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.06408
A continually expandable foundation model for brain MRIPreprint
Mamalakis, M., Jiménez-Mesa, C., Li, Y., Chen, H., Li, C., Mamalakis, A., Suckling, J., Bethlehem, R. A. I., Price, S. J., Gilbertson, R. J., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.08319
Robust Adaptive Diffusion-Based Trajectory Planning for Autonomous Driving
Liu, Q., Gong, Y., Wang, Y., & Wang, K. (2026) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei70303.2026.11640705
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model
Chen, Z., Shi, T., Xu, P., Nan, K., Wang, Q., Yi, Z., Yang, J., & Tai, Y. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_11
Yan, H., Guo, J., Zhang, Y., Wang, B., Li, Z., Liu, J., Liu, J., Li, L., & Han, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_33
siDiff: De Novo siRNA Design via Efficacy-Guided Discrete Masked DiffusionPreprint
Yue, Z., Zhang, H., Gao, X., Shu, S., & Lai, L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.11.744092
Efficient Adaptation of Video Diffusion Transformers for Robotic Manipulation Prediction
Li, J., Zhu, J., Liu, K., Song, Z., Long, Y., Hu, S., Cheng, B., Huang, T., & Zhou, W. (2026) · International Conference on Control and Intelligent Robotics (ICCIR) · doi:10.1109/iccir70228.2026.11633299
Yang, S., Jansen, B., Hichem Sahli, B., Nguyễn, X. S., & Histace, A. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630088
A 2 SR: Any-Resolution and Any-Step Diffusion Image Super Resolution with Pure ConvNets
Wang, R., & Zhang, K. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630461
Diffu Vader: Validity-Constrained Discrete Diffusion for Flow-Level NIDS Red Teaming
Fard, H., Komarov, I., & Wunder, G. (2026) · International Conference on Computer, Information and Telecommunication Systems · doi:10.1109/cits70307.2026.11637319
Tree Based Diffusion Transformers for Improving Intrusion Detection Performance
Zhong, W., Zhang, X., & Yu, N. (2026) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd69640.2026.11637229
UNIGEODIFF: Unified Geometry-Aware Diffusion for Single-Image 3D Furniture Generation
Li, W., Tan, Z., & Liu, Y. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630365
Improving the Stable Diffusion Model
Gomes, H., & Esteves, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32726-0_47
Chao, J., Tong, G., Liu, Z., Lin, W., Zhang, M., Ma, M., & Zhu, W. (2026) · doi:10.5194/egusphere-2026-3398
Zhou, J., Jing, Y., Sun, Y., He, S., Ye, L., & Jia, T. (2026) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2026.3718715
Liu, H., Li, H., Zheng, Z. Y., Du, J., & Xiao, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35248-4_43
FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow MatchingPreprint
Wang, Z., Bacalum, A., Olby, O., Ventre, C., & Stillman, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.13096
SCALAR++: Efficient Controllable Generation via Scale-wise Visual Autoregressive Learning
Xu, R., Jin, D., Chen, S., Bai, Y., Ma, J., Lan, R., Zeng, J., Ge, Y., Zheng, M., Sun, L., et al. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02984-z
Systematic Literature Review of Vision-Language-Action Models for Generalist Robots
Cheema, U., Badr, Y., Le, T. M., & Fitzsimons, K. (2026) · Robotics · doi:10.3390/robotics15080160
PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes
Chi, Y., Ma, H., Gao, F., Niu, Z., Li, K., & Li, J. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835074
Diffusion-Based Generative Regularization for Cross-Modal Supervised Learning
Asakura, T., Inoue, N., & Shinoda, K. (2026) · IEEE Access · doi:10.1109/access.2026.3724724
Tan, L., Li, S., Kankanhalli, M., & Tan, R. T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_10
Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting
Chen, S., Zhuang, Z., Luo, H., Wu, Q., & Tan, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_22
Chen, Y., Liu, R., Wong, W. K., & Wen, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3723234
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
