Stars
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
Source Code for Neurips 2023 Publication: <ChatGPT-Powered Hierarchical Comparisons for Image Classification Download PDF>
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)
🚀 Power Your World with AI - Explore, Extend, Empower.
An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images
Taming Transformers for High-Resolution Image Synthesis
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Official Implementation of Paper "Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling" (ICML 2023)
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
A latent text-to-image diffusion model
Latent Point Diffusion Models for 3D Shape Generation
[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".
Learning to compose soft prompts for compositional zero-shot learning.
Official implementation of "ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing"
Improved Embedded Topic Models in Hyperbolic Space
Official PyTorch implementation for the paper "CARD: Classification and Regression Diffusion Models"
wds2014 / HyperMiner
Forked from NoviceStone/HyperMinerRepo for NeurIPS "HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding"
Tensorflow (1.0 or 2.0) and Pytorch implementations of the Sinkhorn algorithm [1] for computing the optimal transport (OT) distance between two discrete distributions.
Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".