Machine Learning Credits

Hotpot builds on and is informed by many amazing machine learning researchers, papers, and projects:

• The amazingly talented Katherine Crowson
• High-Resolution Image Synthesis with Latent Diffusion Models
• Attention Is All You Need
• Zero-Shot Text-to-Image Generation
• Learning Transferable Visual Models From Natural Language Supervision
• Palette: Image-to-Image Diffusion Models
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Stability.ai
• VQGAN+CLIP
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
• Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation
• Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
• Transfer Learning for Illustration Classification
• Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network
• Fast Interactive Object Annotation with Curve-GCN
• Semantic Human Matting
• Information-Flow Matting
• Deep Image Matting
• ERSGAN
• StarGAN
• DisenBooth: Identity Preserving Disentangled Tuning For Subject Driven Text To Image Generation
• DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
• A Generalist FaceX via Learning Unified Facial Representation
• MonoFormer: One Transformer for Both Diffusion and Autoregression
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
• Gemma 2: Improving Open Language Models at a Practical Sizes
• Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
• LoRA: Low-Rank Adaptation of Large Language Models
• DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
• StackBlur
• AvatarMe: Realistically Renderable 3D Facial Reconstruction in-the-wild
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
• Generative Image Modeling using Style and Structure Adversarial Networks
• Towards Real-World Blind Face Restoration with Generative Facial Prior
• City-GAN: Learning architectural styles using a custom Conditional GAN architecture
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Computer Vision group
• Semantic Image Inpainting With Deep Generative Models and image restoration with GANS
• LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions
• KoDALLE
• bmtm
• Benjamin Trom
• Jack Qiao
• Dall-E Mini
• Neural Style
• Face API
• Image Style Transfer Using Convolutional Neural Networks
• TraVeLGAN: Image-to-image Translation by Transformation Vector Learning
• Style-Transfer via Texture-Synthesis
• Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization
• Bringing Old Photos Back to Life
• Old Photo Restoration via Deep Latent Space Translation
• DeOldify
• ImagineNet: Restyling Apps Using Neural Style Transfer
• Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
• Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
• Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network