Bibliography:

  1. ​ ‘DALL·E’ tag

  2. ​ Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

  3. ​ JPEG-LM: LLMs as Image Generators with Canonical Codec Representations

  4. ​ MAR: Autoregressive Image Generation without Vector Quantization

  5. ​ STAR: Scale-wise Text-to-image generation via Auto-Regressive representations

  6. ​ Chameleon: Mixed-Modal Early-Fusion Foundation Models

  7. ​ Visual Autoregressive Modeling (VAR): Scalable Image Generation via Next-Scale Prediction

  8. ​ IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers

  9. ​ Rejuvenating image-GPT as Strong Visual Representation Learners

  10. ​ Image Captioners Are Scalable Vision Learners Too

  11. ​ Artificial intelligence and art: Identifying the esthetic judgment factors that distinguish human & machine-generated artwork

  12. ​ VALL-E: Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

  13. ​ Retrieval-Augmented Multimodal Language Modeling

  14. ​ Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer

  15. ​ CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

  16. ​ CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

  17. ​ MaskGIT: Masked Generative Image Transformer

  18. ​ CM3: A Causal Masked Multimodal Model of the Internet

  19. ​ ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation

  20. ​ Emojich—zero-shot emoji generation using Russian language: a technical report

  21. ​ LAFITE: Towards Language-Free Training for Text-to-Image Generation

  22. ​ NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

  23. ​ L-Verse: Bidirectional Generation Between Image and Text

  24. ​ Telling Creative Stories Using Generative Visual Aids

  25. ​ Unifying Multimodal Transformer for Bi-directional Image and Text Generation

  26. ​ Illiterate DALL·E Learns to Compose

  27. ​ What Users Want? WARHOL: A Generative Model for Recommendation

  28. ​ ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation

  29. ​ Chinese AI lab challenges Google, OpenAI with a model of 1.75 trillion parameters

  30. ​ M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis

  31. ​ CogView: Mastering Text-to-Image Generation via Transformers

  32. ​ GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

  33. ​ VideoGPT: Video Generation using VQ-VAE and Transformers

  34. ​ China’s GPT-3? BAAI Introduces Superscale Intelligence Model ‘Wu Dao 1.0’: The Beijing Academy of Artificial Intelligence (BAAI) releases Wu Dao 1.0, China’s first large-scale pretraining model.

  35. ​ Paint by Word

  36. ​ Generating Images with Sparse Representations

  37. ​ M6: A Chinese Multimodal Pretrainer

  38. ​ DALL·E 1: Creating Images from Text: We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language

  39. ​ Taming Transformers for High-Resolution Image Synthesis

  40. ​ Text-to-Image Generation Grounded by Fine-Grained User Attention

  41. ​ X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

  42. ​ iGPT: Generative Pretraining from Pixels

  43. ​ Image GPT (iGPT): We find that, just as a large transformer model trained on language can generate coherent text, the same exact model trained on pixel sequences can generate coherent image completions and samples

  44. ​ The messy, secretive reality behind OpenAI’s bid to save the world: The AI moonshot was founded in the spirit of transparency. This is the inside story of how competitive pressure eroded that idealism

  45. ​ Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning

  46. ​ Image Transformer

  47. ​ VQ-VAE: Neural Discrete Representation Learning

  48. ​ Categorical Reparameterization with Gumbel-Softmax

  49. ​ The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

  50. ​ Borisdayma/dalle-Mini: DALL·E-Mini

  51. ​ Kingnobro/IconShop: (SIGGRAPH Asia 2023) Code of "IconShop: Text-Guided Vector Icon Synthesis With Autoregressive Transformers"

  52. ​ 8f3782f015fca64bf71d2992d31a7e5b7bbd85fe.html

  53. ​ IconShop

  54. ​ d9b367925ce98d93105c4b2cca98e514aa36352b.html

  55. ​ How Sber Built RuDALL-E: Interview With Sergei Markov

  56. ​ 763e99870bf2e2d9a85b6e34dd47cfb4e5a53704.html

  57. ​ The Little Red Boat Story (Make-A-Scene): Our Own Model Was Used to Generate All the Images in the Story, by Providing a Text and Simple Sketch Input

  58. ​ design#future-tag-features

    [Transclude the forward-link's context]

  59. ​ https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA

  60. ​ 9b851d946d9ca37cf712409432960a1945beb0ef.html

  61. ​ Chameleon: Mixed-Modal Early-Fusion Foundation Models

  62. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2405.09818%2523facebook.html

  63. ​ Visual Autoregressive Modeling (VAR): Scalable Image Generation via Next-Scale Prediction

  64. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2404.02905%2523bytedance.html

  65. ​ IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers

  66. ​ %252Fdoc%252Fai%252Fnn%252Ftransformer%252Fgpt%252Fdall-e%252F1%252F2023-wu-2.pdf.html

  67. ​ Rejuvenating image-GPT as Strong Visual Representation Learners

  68. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2312.02147.html

  69. ​ Artificial intelligence and art: Identifying the esthetic judgment factors that distinguish human & machine-generated artwork

  70. ​ %252Fdoc%252Fai%252Fnn%252Ftransformer%252Fgpt%252Fdall-e%252F1%252F2023-samo.pdf.html

  71. ​ VALL-E: Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

  72. ​ Furu Wei

  73. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2301.02111%2523microsoft.html

  74. ​ Retrieval-Augmented Multimodal Language Modeling

  75. ​ Percy Liang

  76. ​ Mike Lewis

  77. ​ Luke Zettlemoyer

  78. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2211.12561%2523facebook.html

  79. ​ CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

  80. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2205.15868.html

  81. ​ CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

  82. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2204.14217%2523baai.html

  83. ​ CM3: A Causal Masked Multimodal Model of the Internet

  84. ​ Mike Lewis

  85. ​ Luke Zettlemoyer

  86. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2201.07520%2523facebook.html

  87. ​ ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation

  88. ​ Yu Sun

  89. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2112.15283%2523baidu.html

  90. ​ L-Verse: Bidirectional Generation Between Image and Text

  91. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2111.11133.html

  92. ​ Chinese AI lab challenges Google, OpenAI with a model of 1.75 trillion parameters

  93. ​ https%253A%252F%252Fen.pingwest.com%252Fa%252F8693%2523baai.html

  94. ​ M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis

  95. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2105.14211%2523alibaba.html

  96. ​ CogView: Mastering Text-to-Image Generation via Transformers

  97. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2105.13290%2523baai.html

  98. ​ VideoGPT: Video Generation using VQ-VAE and Transformers

  99. ​ Aravind Srinivas

  100. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2104.10157.html

  101. ​ China’s GPT-3? BAAI Introduces Superscale Intelligence Model ‘Wu Dao 1.0’: The Beijing Academy of Artificial Intelligence (BAAI) releases Wu Dao 1.0, China’s first large-scale pretraining model.

  102. ​ https%253A%252F%252Fsyncedreview.com%252F2021%252F03%252F23%252Fchinas-gpt-3-baai-introduces-superscale-intelligence-model-wu-dao-1-0%252F%2523baai.html

  103. ​ DALL·E 1: Creating Images from Text: We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language

  104. ​ Aditya A. Ramesh

  105. ​ Speaker Details: EmTech MIT 2023

  106. ​ Vedant Misra

  107. ​ Gretchen Krueger

  108. ​ Sandhini Agarwal

  109. ​ https%253A%252F%252Fopenai.com%252Fresearch%252Fdall-e.html

  110. ​ X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

  111. ​ Hannaneh Hajishirzi—University of Washington

  112. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2009.11278%2523allen.html

  113. ​ iGPT: Generative Pretraining from Pixels

  114. ​ Speaker Details: EmTech MIT 2023

  115. ​ Alec Radford

  116. ​ %252Fdoc%252Fai%252Fnn%252Ftransformer%252Fgpt%252Fdall-e%252F1%252F2020-chen-2.pdf%2523openai.html

  117. ​ Image GPT (iGPT): We find that, just as a large transformer model trained on language can generate coherent text, the same exact model trained on pixel sequences can generate coherent image completions and samples

  118. ​ Speaker Details: EmTech MIT 2023

  119. ​ Alec Radford

  120. ​ https%253A%252F%252Fopenai.com%252Findex%252Fimage-gpt%252F.html

  121. ​ The messy, secretive reality behind OpenAI’s bid to save the world: The AI moonshot was founded in the spirit of transparency. This is the inside story of how competitive pressure eroded that idealism

  122. ​ https%253A%252F%252Fwww.technologyreview.com%252F2020%252F02%252F17%252F844721%252Fai-openai-moonshot-elon-musk-sam-altman-greg-brockman-messy-secretive-reality%252F.html

  123. ​ Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning

  124. ​ %252Fdoc%252Fai%252Fnn%252Fdiffusion%252F2018-sharma.pdf%2523google.html

  125. Wikipedia Bibliography:

    1. ​ Yi Jiang

    2. ​ Alan Yuille

    3. ​ Jinyu Li

    4. ​ Jure Leskovec

    5. ​ Jie Tang

    6. ​ Han Zhang

    7. ​ Pieter Abbeel

    8. ​ Ilya Sutskever

    9. ​ Karen Hao