Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various r…

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods…

Code for the paper "Training Diffusion Models with Reinforcement Learning"

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

A curated list of reinforcement learning with human feedback resources (continually updated)

The official implementation of Self-Play Fine-Tuning (SPIN)

AI-Generated Images as Data Source: The Dawn of Synthetic Era

Scenic: A Jax Library for Computer Vision Research and Beyond

Reading list for research topics in embodied vision

Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)