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 3,501–3,600 of 3,684
Tiny Inference-Time Scaling with Latent Verifiers
Bucciarelli, D., Turri, E., Baraldi, L., Cornia, M., Baraldi, L., & Cucchiara, R. (2026) · doi:10.1109/cvprf71909.2026.00280
No Cache Left Idle: Accelerating Diffusion Model via Extreme-Slimming Caching
Wen, T., Li, H., Chen, Y., Zhou, X., Zhu, L., & Wang, X. (2026) · doi:10.1109/cvprf71909.2026.00397
PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generation
Appelle, A., & Lynch, J. P. (2026) · doi:10.1109/cvprf71909.2026.00430
WGS: Watertight Geometry Standardization for Scalable 3D Generation
Hao, D., Jia, T., Zhang, K., Chen, W., Hu, Z., Yin, Y., Zhang, R., Zhu, L., Yuan, L., Wang, X. E., et al. (2026) · doi:10.1109/cvprf71909.2026.00059
Cross-Resolution Diffusion Models via Network Pruning
Ren, J., Zhu, J., & Wang, H. (2026) · doi:10.1109/cvprf71909.2026.00408
Eevee: Towards Close-Up High-Resolution Video-Based Virtual Try-On
Zeng, J., Bai, Y., Chen, R., Zhang, X., Sun, L., Jin, D., Xu, R., Zhang, N., Song, D., & Chu, X. (2026) · doi:10.1109/cvprf71909.2026.00444
Xu, Z., Rao, Z., Cao, J., Liu, X., Fang, Z., Zhang, H., Tang, S., & Tang, F. (2026) · doi:10.1109/cvprf71909.2026.00362
Xie, L., Sun, L. C., Neall, A., Wu, T., Cai, S., & Wetzstein, G. (2026) · doi:10.1109/cvprf71909.2026.00387
What Matters for Scalable and Robust Learning in End-to-End Driving Planners?
Holtz, D., Hanselmann, N., Doll, S., Cordts, M., & Schiele, B. (2026) · doi:10.1109/cvprf71909.2026.00094
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
Qiu, H., Liu, S., Zhou, Z., An, Z., Ren, W., Liu, Z., Schult, J., He, S., Chen, S., Cong, Y., et al. (2026) · doi:10.1109/cvprf71909.2026.00443
BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models
Wang, J., Zhang, Y., Hasan, M. M., Lei, X., Zhang, J., Zhu, J., Wu, Q., & Zhao, D. (2026) · doi:10.1109/cvprf71909.2026.00072
Framedit: Diffusion Transformer with Matrix Attention for Efficient Video Generation
Le, M. K., Do, K., Nguyen, D. T., & Tran, T. (2026) · doi:10.1109/cvprf71909.2026.00409
PhysLDM: Latent Diffusion for High-Fidelity Deformable SimulationPreprint
Zhang, Y., Xu, X., & Pan, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.07609
Liu, X., Xian, T., Geng, X., Zhao, D., & Liu, W. (2026) · Journal of Imaging · doi:10.3390/jimaging12100494
Velocity Scaling in Flow MatchingPreprint
Saied, Y., & Fleuret, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.10823
Zheng, B., Liu, Z., Ou, J., Chen, R., & Hu, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11479
Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient LearningPreprint
Kleutgens, J., Tec, M., Battiloro, C., Dominici, F., & Daras, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.12340
scCADI: Cell-Aware Diffusion Model for Single-Cell RNA-seq Imputation
Yan, J., Zhao, M., Jiang, Y., Tang, J., & Guo, F. (2026) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-026-00881-0
YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous TeleoperationPreprint
Zhang, Y., Li, Y., Du, Y., Ma, Y., & Yang, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11657
Data-Driven Gaze-Head Coordination Modeling for Natural Facial Video Generation
Liu, X., Wen, Y., & Sugano, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3742186
$C^{3} M G$: Clinically-Controlled Cardiac Mesh Generator Based on Rectified Flow Matching
Fouadi, H., Kas, M., Ruichek, Y., & Merabet, Y. E. (2026) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms69103.2026.00117
IntactWorld: Joint World Modeling with Intact FeaturesPreprint
Tan, B., Zhang, X., Xia, Y., Zhu, Q., Ji, D., Yang, X., & Zhang, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11174
iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive SparsityPreprint
Han, C., Wang, A., Ai, B., Bian, X., Yao, J., Huang, Z., & Ding, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11302
Does Synthetic Image Generation Improve Explainability? A Concept-Based Case Study in Histopathology
Moreno-Sánchez, P. A., Vitoria, I., López-Saratxaga, C., Benito-Del-Valle, L., & Galdrán, A. (2026) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms69103.2026.00089
Cai, H. (2026) · arXiv (Cornell University)
Improving image processing and noise removal using generative deep learning techniques
Yousif, F. A., Ramadhan, S. K., & Mostfa, A. A. (2026) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v15.i5.pp4667-4678
Frozen Vision–Language Priors and Multilook Supervision for Diffusion-Based SAR Image Despeckling
Zhai, H., & Song, H. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3742485
Opening the Black Box of Classifier-Free Guidance via Information BottleneckPreprint
Gao, J., Zheng, T., Zou, J., Yang, F., Fan, L., Tang, L., Li, B., & Wang, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.13369
Wang, Y., Wang, C., & Cai, J. (2026) · IEEE Access · doi:10.1109/access.2026.3742887
TTS-Q: Speaker-Aware Post-Training Quantization of Text-to-Speech Diffusion TransformersPreprint
Feng, X., Li, Y., Feng, W., Lin, Y.-C., Li, K., Wang, X., Yang, K., Yang, C., Tian, Y., Li, W., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.12474
Speech-Conditioned Image Generation via Direct Projection into a Diffusion Decoder
Gantulga, M.-E., & Orgil, J. (2026) · International Symposium on Computer Science and Educational Technology (ISCSET) · doi:10.1109/iscset70652.2026.11722710
Bridge-DiT: Observation-Conditioned Brownian Bridge Reconstruction of Visible Satellite Imagery
Peng, B., Zhang, W., Lyu, X., Yang, S., Qian, Q., Li, Z., & Zhang, Y. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3742491
Розробка моделей дифузії для генерації відеопослідовностей
(2026) · Ìnformatika, kulʹtura, tehnìka. · doi:10.15276/ict.03.2026.93
Low-Noise Direct Denoising Sampling for DPM++ Samplers with Denoised Outputs
Liang, Z., & Wang, J. (2026) · Sensors · doi:10.3390/s26206480
Yang, L., Zeng, W., Zhang, N., Cao, X. S., Rui, T., & Sun, C. (2026) · IEEE Transactions on Industrial Cyber-Physical Systems · doi:10.1109/ticps.2026.3743037
CoTalker: Audio-Driven Interactive Conversational Head Generation
Lin, Z., Wang, R., Chen, M., Hu, H., Gu, Q., Cheng, Z., Xie, R., & Song, L. (2026) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew69720.2026.11720806
VARI: Robust Text-to-Video Generation via Group-Structured Intent AlignmentPreprint
Zhu, M., Chan, H., Liu, S., Zhang, Y., & Chen, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.18189
Image Tokenizers Should Be Trained Between ImagesPreprint
Beißwenger, O., Dihlmann, J.-N., & Lensch, H. P. A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.16759
Compute-optimal data scaling for neural surrogates via multi-fidelity trainingPreprint
Setinek, P., Paischer, F., Thuerey, N., Brandstetter, J., & Koehler, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.17221
Ren, W., Chen, K., Hu, X., Gan, J., Zhang, X., Guo, S., & Yang, G. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3741659
W4A4 MXFP4 Quantized Video Generation Inference Technical Report
Wu, X., Hao, M., Su, H., Xu, J., Cao, S., Mou, Z., Zheng, Y., Yan, Y., Yang, Y., Yan, X., et al. (2026) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew69720.2026.11720833
Aurora: An ISO-Conditioned Restormer for RAW Denoising
Viswanath, V., Senthilkumar, N., Saha, A., Tamizharasi, T., Pujara, J., & Subramaniyaswamy, V. (2026) · IEEE Access · doi:10.1109/access.2026.3743184
Engram Injection: A Study of Temporal Validity in Parametric Language-Model MemoryPreprint
Siavoshian, S., Ramadan, O., Diab, A. M. E.-A., Saeed, A. K., Rodriguez, B. M., & Rodriguez, B. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.15882
JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an ImagePreprint
Boduljak, G., Lan, Y., Rupprecht, C., & Vedaldi, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.16591
Kim, S., Jeong, J., Fu, J., & Uh, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.16365
Darv, P. (2026) · AND journal of Architectures Cities and Architects
Liang, F. Y., Lei, S. H., Hu, T. D., li, F. Z., Ye, F. J., & Jiang, S. A. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02661-8
Generative Representation Learning for Scalable Latent TokenizationPreprint
Baade, A., Sargent, K., Sitzmann, V., Chan, E. R., Johnson, J., Fei-Fei, L., & Wetzstein, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.20533
Designing Transformers for Continuous Diffusion Language ModelsPreprint
Luo, W., Chen, Y., Jiang, H., Cheng, G., & Hu, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22330
Yu, Q., Qiu, Z., Yan, J., Li, H., Qin, Q., Wang, K., Luo, S., Ju, J., Mi, Y., Lu, T., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.20818
Cao, H., & Chen, J. (2026) · Mathematics · doi:10.3390/math14203759
DiTMark: Secure Watermarking for Model Ownership in Diffusion Transformers
Chivaran, N., Li, Q., & Ni, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6834-4_22
Conditional Mean Flows: Few-Step Densities for Simulation-Based InferencePreprint
Arruda, J., Hasenauer, J., & Radev, S. T. (2026) · arXiv (Cornell University)
Phee, J. H., & Balch, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22727
DiT-Conv: Convolution Replaces Attention in Diffusion Transformers
Yuan, Y., & Meng, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728840
Liu, Y., Sun, Y., Xu, H., Zhao, L., 赵, S. 寿. Z., Li, J., & Hao, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729605
Quantized SDiT with Non-structured Positional Embedding for Signal Synthesis
Xing, Y., Li, Y., Zhang, Z., & Harras, K. A. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728740
ESC: Escaping 2D Diffusion Ambiguity with Geometric Constraints for Consistent Novel View SynthesisPreprint
Luo, G. Y., Severo, D., Karrer, B., Pal, C., Romero, A., & Drozdzal, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23732
Latent Blending for Long Video Generation Using Diffusion Models
Urs, P. P., Bhat, P. S., Rao, R. D., Gowda, C. S., Gayatri, T., & Natarajan, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-34561-5_33
Cross-Modality Diffusion for Descriptor Manifold Translation in Visible-Infrared Matching
Zang, H., Yu, J., Guan, J., Xu, T., Liu, Z., Wu, J., & Lu, J. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3745005
DanceGroup: Identity-aware Diffusion Transformer for Motion-Specifiable Multi-Character Animation
Liu, Z., Chen, Z., Lai, J., & Xie, X. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728602
Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction
Ahasan, M. I., Yang, G., Noor, A. F. M. A., Mahmud, S. M. H., & Rahman, M. M. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729732
MLFRG: A Multimodal Flow Matching Framework for Context-Aware Facial Reaction Generation*
Yang, B., Song, K., Ni, R., & Song, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729548
Generative Forecasting of Longitudinal 3D-OCT Under Anti-VEGF Therapy for Diabetic Macular Edema
Feng, Y., Liang, C., & Wang, S. (2026) · Diagnostics · doi:10.3390/diagnostics16203382
Shi, X., Zhao, H., Cun, X., Wu, Q., & Jin, X. (2026) · Computers & Graphics · doi:10.1016/j.cag.2026.104802
FaceComposer: Learning Coherent and Realistic Face Composition from References
Li, L., Guo, L., Yang, S., Wang, Y., Zheng, Q., Kot, A. C., Lin, W., & Chen, L. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729126
Chinmayi, R. M., Goel, P., Munshi, P. M., Verma, R., & Das, B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-34561-5_11
Lai, X., Wu, J., Li, Y., Qian, L., Zhang, H., & Liu, L. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729454
Li, Y., He, B., Tian, Y., Huang, Y.-C., Zhang, C., Chen, R., Liu, Y., Gao, Y., & Xu, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23002
Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion TransformersPreprint
Xing, B., Zhang, Y., Ding, J., Lu, L., & Wang, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22975
Zhang, J., Fang, T., & Peng, J. I. N. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728466
ImageArmor: Simple, Yet Effective Image Immunization Against Diffusion-based Editing
Khamaiseh, S. Y., Chiacchira, S., Aljadayah, A., Alsobeh, A., Al-Alaj, A., & Elariss, O. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729631
DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS TrainiumPreprint
Ma, B., Yu, M., Kodamalla, V., Liu, J., Li, D., & Li, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23047
FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream TeachersPreprint
Nguyen, N., Nguyen, D., 稲泉, Metaxas, D. N., Hoai, M., Pham, C., & Tran, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22537
FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible GranularityPreprint
Zhao, Y., Xu, J., Zhi, Y., Zhao, Y., Zhao, Z., Han, X., Guo, C., & Gao, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23659
MOSS-Image Technical ReportPreprint
AI, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23374
Training-Free Spatial Routing for Multi-Condition Structural Control in Diffusion Transformers
Zhang, X., & Tang, Y. (2026) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc70922.2026.00031
DiT-Turboquant: Calibration-Free Vector Quantization for Diffusion Transformer Weights
Lin, C., Wei, J., & Tang, Y. (2026) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc70922.2026.00020
Boosting the understanding ability of diffusion model with masked image modeling
Pei, J., Feng, Y., Bi, H., Diao, W., Guo, Z., & Sun, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115123
Batley, R. T., & Saha, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.25565
FlashMap: Flow Map Speculative DecodingPreprint
Shen, J., Zhou, Z., Lee, R., May, J., & Ho, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.24365
UMI-WM: Interactive World Modeling for Bimanual Manipulation from Wrist CamerasPreprint
Guo, J., Zhao, H., Zhang, X., Zheng, Y., Wu, H., Gao, C., Zhou, J., Yan, S., & Yuan, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23913
3D diffusion models for medical imaging
Schilling, F.-P., Barco, D., Denzel, P., & Stadelmann, M. A. (2026) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2026.101832
SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationPreprint
He, Y., Shen, C., Lei, W., Li, M., Lan, T., Liu, K., Tang, H., & Qu, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.25844
Monitoring Electrical Transformer Mechanics via Crowdsourced Imaging
Zhao, S., Lu, Y., Li, L., Dai, D., & Yang, L. (2026) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3795866.3844152
BCT: Bayes-Consistent Tempering for Flow Language ModelsPreprint
Oba, D., Furuta, H., & Okazaki, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.27641
Yang, R., Lai, T., & Huang, H. (2026) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss60577.2026.11730639
Dai, Z., Shi, M., Zhao, X., Zhang, M., Li, J., He, Z., Yin, S., & Wang, J. (2026) · Research Square · doi:10.21203/rs.3.rs-11306819/v1
Generative künstliche Intelligenz
Ambach, D. (2026) · Springer eBooks · doi:10.1007/978-3-662-73474-2_5
Diffusion Echo State Network for Text Generation
BENEDETTI, G. (2026) · Electronic Theses and Dissertations Repository (University of Pisa)
Integrating Flow Matching and Model Predictive Control for Safe Robot NavigationPreprint
Holzmann, P., Pfefferkorn, M., Carvalho, J., Younes, A., Le, A. T., Chalvatzaki, G., Peters, J., & Findeisen, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.29377
Yamaki, R., Mochihashi, D., Shimada, N., Shinagawa, S., & Taniguchi, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.29415
Orbitol: Crystal Generation on Wyckoff OrbitsPreprint
Žugec, I., Rosenthal, J., Lončarić, I., van de Meent, J.-W., & Veljković, T. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.30086
Hierarchical Masked Diffusion Language ModelsPreprint
Gupta, P., Satwik, Aggarwal, A., Gurnani, B., Mondal, A. K., Khandelwal, D., Garg, D., & Singla, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.29255
HierPAS: Accelerating Video Generation Models with Hierarchical Precision and Adaptive Sparsity
Liu, C., Song, Y., Chen, R., & Yang, F. (2026) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3770743.3803937
Gao, Q. (2026) · International Conference on Artificial Intelligence Technologies and Applications (ICAITA) · doi:10.1109/icaita71179.2026.11737111
Frequency-Aware Decoder Calibration for Robust Latent Image Generation
Gong, Y. (2026) · International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR) · doi:10.1145/3847445.3847467
TranSAGE: Automating Spatial Accelerator Generation for Large-Scale Transformer Models
Zhang, C., Sun, Y., Zhang, W., Chen, Q., & Zhao, J. (2026) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3845814.3850039
Liu, H., Jin, H., Zhao, Z., Hu, P., Fang, G., Song, L., 秦岚, & Yang, G. (2026) · International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR) · doi:10.1145/3847445.3847473
PosePlaner: Denoising Any Feed-Forward Pose Predictor from Pairwise Planar GeometryPreprint
Chen, Y., Tan, B., Shen, Y., Xu, Y., & Xue, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.34845
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
