Built on

A. Jacob, J. Daniel D, H. Jonathan, T. Daniel, and v. d. B. Rianne, “Structured denoising diffusion models in discrete state-spaces,” Advances in Neural Information Processing Systems , vol. 34, pp. 17 981–17 993, 2021
2021
Earlier work this paper cites.
S. Nikolay, C. Junyoung, B. Mikolaj, E. Erich, and O. Aaron van den, “Step-unrolled denoising autoencoders for text generation,” arXiv preprint arXiv:2112.06749 , 2021
Original
2021
Earlier work this paper cites.
K. Gwanghyun and Y. Jong Chul, “Diffusionclip: Text-guided image manipulation using diffusion models,” 2021
2021
Earlier work this paper cites.
N. Alex, D. Prafulla, R. Aditya, S. Pranav, M. Pamela, M. Bob, S. Ilya, and C. Mark, “Glide: Towards photorealistic image generation and editing with text-guided diffusion models,” arXiv preprint arXiv:2112.10741 , 2021
Original
2021
Earlier work this paper cites.
H. Emiel, N. Didrik, J. Priyank, F. Patrick, and W. Max, “Argmax flows and multinomial diffusion: Towards non-autoregressive language models,” arXiv preprint arXiv:2102.05379 , vol. 3, no. 4, p. 5, 2021
Original
2021
Earlier work this paper cites.
B. Dmitry, R. Ivan, V. Andrey, K. Valentin, and B. Artem, “Label-efficient semantic segmentation with diffusion models,” arXiv preprint arXiv:2112.03126 , 2021
Original
2021
Earlier work this paper cites.
C. Ting, Z. Ruixiang, and H. Geoffrey, “Analog bits: Generating discrete data using diffusion models with self-conditioning,” arXiv preprint arXiv:2208.04202 , 2022
Original
2022
Earlier work this paper cites.
L. Xiang Lisa, T. John, G. Ishaan, L. Percy, and H. Tatsunori B, “Diffusion-lm improves controllable text generation,” arXiv preprint arXiv:2205.14217 , 2022
Original
2022
Earlier work this paper cites.

Similar

G. Shansan, L. Mukai, F. Jiangtao, W. Zhiyong, and K. LingPeng, “Diffuseq: Sequence to sequence text generation with diffusion models,” arXiv preprint arXiv:2210.08933 , 2022
Original
2022
Cited alongside, same era.
L. Guangyi, F. Zeyu, G. Yuan, Y. Zichao, L. Xiaodan, B. Junwei, H. Xiaodong, C. Shuguang, L. Zhen, and H. Zhiting, “Composable text control operations in latent space with ordinary differential equations,” arXiv preprint arXiv:2208.00638 , 2022
Original
2022
Cited alongside, same era.
H. Zhengfu, S. Tianxiang, W. Kuanning, H. Xuanjing, and Q. Xipeng, “Diffusionbert: Improving generative masked language models with diffusion models,” arXiv preprint arXiv:2211.15029 , 2022
Original
2022
Cited alongside, same era.
A. Omri, L. Dani, and F. Ohad, “Blended diffusion for text-driven editing of natural images,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 18 208–18 218
2022
Cited alongside, same era.

Then

R. Robin, B. Andreas, and O. Björn, “Text-guided synthesis of artistic images with retrieval-augmented diffusion models,” arXiv preprint arXiv:2207.13038 , 2022
Original
2022
Later among the works it cites.
G. Shuyang, C. Dong, B. Jianmin, W. Fang, Z. Bo, C. Dongdong, Y. Lu, and G. Baining, “Vector quantized diffusion model for text-to-image synthesis,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 10 696–10 706
2022
Later among the works it cites.
Y. Dongchao, Y. Jianwei, W. Helin, W. Wen, W. Chao, Z. Yuexian, and Y. Dong, “Diffsound: Discrete diffusion model for text-to-sound generation,” arXiv preprint arXiv:2207.09983 , 2022
Original
2022
Later among the works it cites.
K. Heeseung, K. Sungwon, and Y. Sungroh, “Guided-tts: A diffusion model for text-to-speech via classifier guidance,” in International Conference on Machine Learning , 2022, pp. 11 119–11 133
2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2023

Diffusion Models in NLP: A Survey

Zhu, Yuansong, Zhao, Yu

Understand

Diffusion models have become a powerful family of deep generative models, with record-breaking performance in many applications.

This paper first gives an overview and derivation of the basic theory of diffusion models, then reviews the research results of diffusion models in the field of natural language processing, from text generation, text-driven image generation and other four aspects, and analyzes and summarizes the relevant literature materials sorted out, and finally records the experience and feelings of this topic literature review research.

Built on

A. Jacob, J. Daniel D, H. Jonathan, T. Daniel, and v. d. B. Rianne, “Structured denoising diffusion models in discrete state-spaces,” Advances in Neural Information Processing Systems , vol. 34, pp. 17 981–17 993, 2021
2021
Earlier work this paper cites.
S. Nikolay, C. Junyoung, B. Mikolaj, E. Erich, and O. Aaron van den, “Step-unrolled denoising autoencoders for text generation,” arXiv preprint arXiv:2112.06749 , 2021
Original
2021
Earlier work this paper cites.
K. Gwanghyun and Y. Jong Chul, “Diffusionclip: Text-guided image manipulation using diffusion models,” 2021
2021
Earlier work this paper cites.
N. Alex, D. Prafulla, R. Aditya, S. Pranav, M. Pamela, M. Bob, S. Ilya, and C. Mark, “Glide: Towards photorealistic image generation and editing with text-guided diffusion models,” arXiv preprint arXiv:2112.10741 , 2021
Original
2021
Earlier work this paper cites.
H. Emiel, N. Didrik, J. Priyank, F. Patrick, and W. Max, “Argmax flows and multinomial diffusion: Towards non-autoregressive language models,” arXiv preprint arXiv:2102.05379 , vol. 3, no. 4, p. 5, 2021
Original
2021
Earlier work this paper cites.
B. Dmitry, R. Ivan, V. Andrey, K. Valentin, and B. Artem, “Label-efficient semantic segmentation with diffusion models,” arXiv preprint arXiv:2112.03126 , 2021
Original
2021
Earlier work this paper cites.
C. Ting, Z. Ruixiang, and H. Geoffrey, “Analog bits: Generating discrete data using diffusion models with self-conditioning,” arXiv preprint arXiv:2208.04202 , 2022
Original
2022
Earlier work this paper cites.
L. Xiang Lisa, T. John, G. Ishaan, L. Percy, and H. Tatsunori B, “Diffusion-lm improves controllable text generation,” arXiv preprint arXiv:2205.14217 , 2022
Original
2022
Earlier work this paper cites.

Similar

G. Shansan, L. Mukai, F. Jiangtao, W. Zhiyong, and K. LingPeng, “Diffuseq: Sequence to sequence text generation with diffusion models,” arXiv preprint arXiv:2210.08933 , 2022
Original
2022
Cited alongside, same era.
L. Guangyi, F. Zeyu, G. Yuan, Y. Zichao, L. Xiaodan, B. Junwei, H. Xiaodong, C. Shuguang, L. Zhen, and H. Zhiting, “Composable text control operations in latent space with ordinary differential equations,” arXiv preprint arXiv:2208.00638 , 2022
Original
2022
Cited alongside, same era.
H. Zhengfu, S. Tianxiang, W. Kuanning, H. Xuanjing, and Q. Xipeng, “Diffusionbert: Improving generative masked language models with diffusion models,” arXiv preprint arXiv:2211.15029 , 2022
Original
2022
Cited alongside, same era.
A. Omri, L. Dani, and F. Ohad, “Blended diffusion for text-driven editing of natural images,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 18 208–18 218
2022
Cited alongside, same era.

Then

R. Robin, B. Andreas, and O. Björn, “Text-guided synthesis of artistic images with retrieval-augmented diffusion models,” arXiv preprint arXiv:2207.13038 , 2022
Original
2022
Later among the works it cites.
G. Shuyang, C. Dong, B. Jianmin, W. Fang, Z. Bo, C. Dongdong, Y. Lu, and G. Baining, “Vector quantized diffusion model for text-to-image synthesis,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 10 696–10 706
2022
Later among the works it cites.
Y. Dongchao, Y. Jianwei, W. Helin, W. Wen, W. Chao, Z. Yuexian, and Y. Dong, “Diffsound: Discrete diffusion model for text-to-sound generation,” arXiv preprint arXiv:2207.09983 , 2022
Original
2022
Later among the works it cites.
K. Heeseung, K. Sungwon, and Y. Sungroh, “Guided-tts: A diffusion model for text-to-speech via classifier guidance,” in International Conference on Machine Learning , 2022, pp. 11 119–11 133
2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

R. Aditya, D. Prafulla, N. Alex, C. Casey, and C. Mark, “Hierarchical text-conditional image generation with clip latents,” arXiv preprint arXiv:2204.06125 , 2022

Original

2022

Cited alongside, same era.

S. Chitwan, C. William, S. Saurabh, L. Lala, W. Jay, D. Emily, G. Seyed Kamyar Seyed, A. Burcu Karagol, M. S Sara, L. Rapha Gontijo et al. , “Photorealistic text-to-image diffusion models with deep language understanding,” arXiv preprint arXiv:2205.11487 , 2022

Original

2022

Cited alongside, same era.

W. Weilun, B. Jianmin, Z. Wengang, C. Dongdong, C. Dong, Y. Lu, and L. Houqiang, “Semantic image synthesis via diffusion models,” arXiv preprint arXiv:2207.00050 , 2022

Original

2022

Cited alongside, same era.

H. Rongjie, Z. Zhou, L. Huadai, L. Jinglin, C. Chenye, and R. Yi, “Prodiff: Progressive fast diffusion model for high-quality text-to-speech,” in Proceedings of the 30th ACM International Conference on Multimedia , 2022, pp. 2595–2605

2022

Later among the works it cites.

Y. Peiyu, X. Sirui, M. Xiaojian, J. Baoxiong, P. Bo, G. Ruigi, Z. Yixin, Z. Song-Chun, and W. Ying Nian, “Latent diffusion energy-based model for interpretable text modeling,” arXiv preprint arXiv:2206.05895 , 2022

Original

2022

Later among the works it cites.

L. Xihui, P. Dong Huk, A. Samaneh, Z. Gong, C. Arman, H. Yuxiao, S. Humphrey, R. Anna, and D. Trevor, “More control for free! image synthesis with semantic diffusion guidance,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , 2023, pp. 289–299

2023

Closest in time.