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 2,801–2,900 of 3,684
Neon: One-Shot Text-To-Video Tuning via Noise Latent Dynamics
Xiao, X., Lei, S., & Hu, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463840
Cine-shot Director: Native Cinema-Grade Multi-Shot Video Generation Framework
Han, J., Ye, X., Zhen, Z., Song, L., Wang, Q., Li, L., Deng, C., & Feng, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464190
Fast and Accurate Text-to-Motion Generation Through Discrete-Guided Continuous Modeling
Zhu, L., Ge, Y., Li, C., Gao, J., & Li, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464806
Fusionedit: Semantic Fusion and Attention Modulation for Training-Free Image Editing
Lai, Y., Wang, C., & Min, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463249
FlashFoley: Fast Interactive Sketch2audio Generation
Novack, Z., Saito, K., Zhong, Z., Shibuya, T., Cui, S., McAuley, J., Berg-Kirkpatrick, T., Simon, C., Takahashi, S., & Mitsufuji, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465146
Visual Keys to Symphonies: Latent Diffusion for Multi-Scene Video-to-Music Generation
Ng, C. F., So, K., Yang, J., Ovalle, P., Lui, S., Fan, F., & Dong, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462058
CADD: Condition-Anchor Dataset Distillation
Cao, J., Liu, Y., Lang, C., & Jiang, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461272
Wang, Y., Shen, Q., Zhang, B., Huang, Z., Zhu, C., Yao, S., & Wu, Q. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463171
CosyAccent: Duration-Controllable Accent Normalization using Source-Synthesis Training Data
Bai, Q., Shi, S., Wang, S., Ju, Y., Wang, Y., & Li, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460921
HSRI: High-Fidelity Shape Representation with Image Guidance
Liu, P., Xiao, H., Wen, X., Wang, L., & Sun, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462299
Nativetok: Native Visual Tokenization for Improved Image Generation
Wu, B., Huang, M., Jia, W., & Mao, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462037
Asynchrony-Aware Decoupled Multimodal Control for Cued Speech Video Generation
Ma, F., Zhang, X.-P., & Liu, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461568
Wen, Z., Gan, D., Zhu, Y. C., Cheng, J., & Liang, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460807
Quadratic Flow: Constant Acceleration as a Prior for Learning Better Velocity Field
Wu, Z., Sun, B., & He, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461263
Yang, H., Li, J. C. L., Li, K., Ma, W., Xu, M., Zhao, Y., & Po, L.-M. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3684401
ParaEdit: Unifying Parallel Transport and Generative Flows for High-Fidelity Image Editing
Zhou, Y., Wen, J., hong, Y., Ding, K., Zhang, Y., Yang, G., & Xiang, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462013
Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation
Xia, R. (2026) · IEEE Access · doi:10.1109/access.2026.3686260
VMSP: Video-to-Music Generation with Two-Stage Alignment and Synthesis
Gu, X., Jiang, W., Jiang, Y., Su, Z., & Yan, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460579
Stylized Text-to-Motion Synthesis Via Multi-Condition Latent Diffusion
Xie, F., Shiota, T., 高木, 基., & Simo‐Serra, E. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461022
Guo, Z., Wu, X., Dou, Y., Gao, H., & Caumon, G. (2026) · Geoscientific model development · doi:10.5194/gmd-19-7961-2026
Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System IdentificationPreprint
Messaoudi, A. E., Khaous, N., & Cherifi, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.17566
Progressive Thinking for Lane Detection: Holistic Priors to Focused Refinement
Jiang, Y., Liu, Y., & Liu, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463360
FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation
Ding, G., Chen, H., & Xu, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464045
RAP: Real-Time Audio-Driven Portrait Animation with Video Diffusion Transformer
Du, F., Li, T., Qiao, Q., Yu, T., Zhen, D., Zhang, Z., Jia, X., Yang, Y., Yin, S., & Liu, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461916
Magnitude Difference Conditioned All-in-One Image Restoration
Bae, J., & Shin, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461462
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Wen, J., Sun, P., Zhang, W., Qiu, S., Xu, W., Yang, X., & Chu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_26
Zheng, J., Wang, B., Zhou, X., Wu, X., & Zhao, S. (2026) · IEEE Access · doi:10.1109/access.2026.3686219
Universal Denoising Patterns for Diffusion Image Detection
Qian, Y., Cai, Q., Pan, Y., Yao, T., Chen, Y., & Mei, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462468
HSSDCT: Factorized Spatial-Spectral Correlation for Hyperspectral Image Fusion
Lee, C.-M., Ho, Y.-H., Lin, Y.-F., Lee, J.-W., Kang, L.-W., & Hsu, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463990
MVP-Diff: Multi-View Priors Learning for Diffusion-Based Single-View 3D Point Cloud Reconstruction
Li, F., Li, T., Wang, H., Wu, K., & Yu, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461695
Refgen: Reference-Guided Synthetic Data Generation for Anomalous Sound Detection
Liang, W., Qiu, Y., Jiang, A., Han, B., Liu, T., Zheng, X., Fan, P., Lü, C., Liu, J., & Zhang, W.-Q. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461896
VTONGuard: Automatic Detection and Authentication of AI-generated Virtual Try-On Content
Wu, S., Hong, Y., Chen, S., Wang, Z., Sun, X., Zhan, J., Lan, J., & Zhang, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463297
Learning Latent Space for Multi-Order / Resolution Graph-Regularized Image Denoiser
Do, T. T., & Cheung, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461379
Symphony Rendering: Midi and Composer-Conditioned Auto Orchestration with Flow-Matching Transformers
Lei, J., & Kong, Q. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462437
F5E-TTS: Enhancing Speech Synthesis by Aligning Text with Rich Semantic Representations
Chen, Y., Wang, H., Li, N., & Li, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462167
Hu, D., Wu, Z., Zhao, L., Quan, G., Yang, S., Zhang, Y., Shu, H., & Chen, Y. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3686413
Allo{SR}$$^2$$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
Wang, Z., Huang, X., Qiao, J., Li, W., Hu, J., Chen, X., & Lin, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_32
Particle-based Object-centric Motion Policy Learning
Frey, B. (2026) · reposiTUm (TU Wien) · doi:10.34726/hss.2026.141282
Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative ModelsPreprint
Nizam, M. B., & Davis, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.21036
Diffusion-Driven Forgery Detection: Distilling Latent Features for Generalized Image Forensics
Qian, K., Xu, Y., Xu, Y., & Fang, Y. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3687792
4DLoG: Generative modeling of neurodegenerative brain anatomy with 4D longitudinal diffusion model
Jayakumar, N., Deb, S., Jafrasteh, B., Zhao, Q., & Zhang, M. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104368
HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video EvaluationPreprint
Zhang, B., Guan, K., & Song, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.25361
Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with VOXELPreprint
Liu, Y., Crawford, N., Wang, M., Xue, J., & Huang, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.26821
Wang, G., Cai, S., Li, Z. X., & He, G. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3687836
D-Rex: Diffusion Rendering for Relightable Expressive Avatars
Teufel, T., Zhou, X., Iqbal, U., Kautz, J., Habermann, M., Golyanik, V., & Theobalt, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_11
PCTDM: Robust 3D Point Cloud Generation via Diffusion Probabilistic Model
Sun, X., Gao, P., Wang, X., Yang, G., & Jiang, R. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487386
Huo, Y., Xie, R., & Cai, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6304-3_4
Guo, R., Wang, L., Chen, X., Jiang, K., Yue, Z., Han, H., Wang, Y., Tu, F., Wei, S., Hu, Y., et al. (2026) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2026.3684745
Photolithography Overlay Map Generation with Implicit Knowledge Distillation Diffusion Transformer
Yang, Y.-F., & Hsiao, H.-H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01418
Holistic Tokenizer for Autoregressive Image Generation
Zheng, A., Wang, H., Zhao, Y., Deng, W., Wang, T., Zhang, X., & Qi, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01571
Large Scene Generation with Cube-Absorb Discrete Diffusion
Hu, Q. H. W., & Hu, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02336
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Wang, J., Kang, N., Yao, L., Chen, M., Wu, C., Zhang, S., Xue, S., Liu, Y., Wu, T., Liu, X., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01491
Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images!
Zou, Z., Gong, B., & Wang, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01817
OneGT: One-Shot Geometry-Texture Neural Rendering for Head Avatars
Chen, J., Li, B., Zhang, F., Zhao, S., & Qian, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01051
Huang, N. (2026) · International Conference on Artificial Intelligence and Fintech · doi:10.1145/3800973.3801028
Kim, S., Shi, Y., Li, K., Cho, M., & Wang, P. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00168
Zhang, H., Sinha, A., Juefei-Xu, F., Ma, H., Li, K., Fan, Z., Dai, X., Hou, T., Zhang, P., & He, Z. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00799
Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image via Diffusion Transformer
Han, S., Chung, M., Cho, G., Joo, K., & Kim, T.-H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00323
Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss
Gong, M., Ryu, N., Ok, J., & Cho, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00499
Zero-Shot Video Deraining with Video Diffusion Models
Varanka, T., Gonzalez, J. L., Kim, H., Garrido, P., & Yao, X. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00073
Improved Residual Learning in Diffusion Models
Zhang, J., Liu, D., Park, E., Zhang, S., & Xu, C. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3689939
Efficient Quantization of Text-to-Video Diffusion Models with OmniQuant-Style PTQ on Consumer GPUs
Zhang, S., & Fu, Z. (2026) · International Conference on Electronics Technology and Artificial Intelligence (ETAI) · doi:10.1109/etai68332.2026.11485459
PD-CBDM: Training Class-Balancing Diffusion Models with Perceptual Distinguish Loss
Hu, J., Luo, W., Chen, T., Yang, X., & Hou, Z. (2026) · Mathematics · doi:10.3390/math14101576
A Few-Step Generative Model on Cumulative Flow Maps
Li, Z., Chen, D., Sun, Y., & Zhu, B. (2026) · ACM Transactions on Graphics · doi:10.1145/3811380
A Flow Matching Algorithm for Many-Shot Adaptation to Unseen DistributionsPreprint
Ingebrand, T., Zhao, R., Gupta, K., Fridovich-Keil, D., Chinchali, S., & Topcu, U. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.06272
Liu, Y., Zhang, Y., Li, W., Zhao, Y., Liu, R., & Chen, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.06356
InstaFlow-Pan: One-Step Flow Matching for High-Fidelity Pansharpening
Liu, Q., Qin, Y., Li, Z. K., Cao, X., & Liu, J. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3691482
Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual GenerationPreprint
Zheng, B., Luo, W., Yang, G., Zhang, C., & Hu, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.06207
GIL-3D: U-Shaped Diffusion Transformers for Generalizable 3D Imitation Learning
Wang, X., Mei, A., Wu, L., Gan, Z., & Zhu, G. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3692096
Improving SAR Automatic Target Recognition via OOD Background-Aware Data Generation
Dai, M., Tan, Y., Ma, Z., & Cong, Y. (2026) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce69494.2026.11504683
Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation
Qiao, C., Liu, E., Ren, J., & He, L. (2026) · Sensors · doi:10.3390/s26102944
Diffusion-Enhanced Tree Planning for Autonomous Driving
Liu, Q., Gong, Y., Jiang, B., Chang, C., Li, Z., Wang, X., Ge, J., Cui, J., & Li, L. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3692076
Follow the Mean: Reference-Guided Flow MatchingPreprint
Curvo, P. M. P., Zhdanov, M., Eijkelboom, F., & van de Meent, J.-W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.10302
A Cold Diffusion Approach for Percussive Dereverberation
Makris, D., Barják, A., & Kaliakatsos-Papakostas, M. A. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728826
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation ModelsPreprint
Li, Z., Yoshikai, Y., Nemoto, S., Kusuhara, H., & Mizuno, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.09949
Efficient Speech Enhancement via Flow Matching with Gated Bidirectional Mamba2
Yuan, J., Zhou, R., & Fan, C. (2026) · Applied Sciences · doi:10.3390/app16104757
The Diffusion EncoderPreprint
Premkumar, A., & Lucioni, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.13399
Xu, X., Wu, X., Ren, H., Zhao, H., & Gan, S. (2026) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml68972.2026.11507078
MDP3: A Multimodal 3-D Diffusion Policy for Visuomotor Control
Li, D., Liu, J., & Zhang, W. (2026) · IEEE Access · doi:10.1109/access.2026.3693095
Yuan, X., Li, P., & Wu, L. (2026) · Journal of Energy Storage · doi:10.1016/j.est.2026.122595
CUBic: Coordinated Unified Bimanual Perception and Control FrameworkPreprint
Wang, X., Ding, P., Xu, J., Wang, D., & Fan, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.13452
滕, 龙. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.153069
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting
Yang, S., Gu, Z., Hou, L., Tao, X., Wan, P., Chen, X., & Liao, J. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3693147
Composable multi-satellite precipitation estimation for evolving observing systemsPreprint
Yang, Y., Sun, H., sun, X., Han, W., Xu, X., Song, X., Li, J., Gao, Z., & Huang, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.14426
Zhu, X., Jiang, S., & Cai, Q. (2026) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3804601.3804694
Generative Motion In-Betweening by Diffusion Over Continuous Implicit Representations
Fan, S., Henderson, P., & Ho, E. S. L. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3693336
Multi-Condition Latent Diffusion Network for Semantic-aware Knowledge Graph Completion
Li, S., Zhang, L., Jin, B., & Wei, X. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116161
Cao, P., Yan, R., Zhao, X., Zhou, F., Zhao, W., Song, Q., & Yang, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3694503
Efficient 3D Content Reconstruction and GenerationPreprint
Li, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.18052
Controlla: Learning Controllability via Graph-Constrained Latent GeometryPreprint
Murthy, J. S., Monsefi, A. K., & Ramnath, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.16603
IDFreq: Identity-preserved human video generation via frequency-based decomposition
Wan, Z., Tang, S., Cao, J., & Li, Y. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104828
GenTS: A Comprehensive Benchmark Library for Generative Time Series ModelsPreprint
Wang, C., Wang, X., Li, P., & Wang, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.17804
Song, Y. H., Kim, H. J., & Chung, . (2026) · doi:10.5194/egusphere-2026-1958
Zhang, Y., Liu, S., Li, Y., Song, Q., Li, J., Zhang, J., Xu, R., & Zhang, C. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-7087-4_21
Integrating Keyword Extraction with Diffusion Models for Generative Text Summarization
Zhang, X., Wang, Y., Xing, X., Pan, C., Zhang, L., & Li, J. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522640
SLG-Flow: A Unified Framework from Semantic Labeling to Visual Generation
Feng, F., Wang, L., Chen, J., Wang, L., & Wang, L. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-8978-4_29
Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos
Liu, Y., Li, Q., Zhang, H. C., He, K., Yang, X., Li, H., Xu, D., & Li, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38186-6_49
DiT1dLnet: A Fast and Accurate Diffusion Model Structure Based on Robot Behavior Imitation
Liao, J., He, W., Yu, Q., & Chen, F. (2026) · Mathematics · doi:10.3390/math14111785
A diffusion-Mamba synergetic framework for face retouching reversal
Xing, F., Shi, X., Zhou, C., & Yue, H. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115170
Lee, H., & Kim, J.-Y. (2026) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3770743.3804346
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
