Stars
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
Official repository of "Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning," which has been presented at ICML 2025
pix2tex: Using a ViT to convert images of equations into LaTeX code.
A metric suite leveraging the logical inference capabilities of LLMs, for radiology report generation both with and without grounding
A performance library for machine learning applications.
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Locally Hierarchical Auto-Regressive Modeling for Image Generation (HQ-Transformer)
Upscaling Karlo text-to-image generation using Stable Diffusion v2.
Official implementation of the paper "FLAME: Free-form Language-based Motion Synthesis & Editing"
A curated list of text-guided generative models resources
COYO-700M: Large-scale Image-Text Pair Dataset
Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)
The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)
A minimal implementation of Gaussian process regression in PyTorch
GLIDE: a diffusion-based text-conditional image synthesis model
A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)
PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs
Taming Transformers for High-Resolution Image Synthesis