Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function. Even though relatively simple approaches (e.g., rejection sampling based on reward scores) have been investigated, fine-tuning text-to-image models with the reward function remains challenging. In this work, we propose using online reinforcement learning (RL) to fine-tune text-to-image models. We focus on diffusion models, defining the fine-tuning task as an RL problem, and updating the pre-trained text-to-image diffusion models using policy gradient to maximize the feedbacktrained reward. Our approach, coined DPOK, integrates policy optimization with KL regularization. We conduct an analysis of KL regularization for both RL fine-tuning and supervised fine-tuning. In our experiments, we show that DPOK is generally superior to supervised fine-tuning with respect to both image-text alignment and image quality.

This paper studies a diffusion-based framework to address the low-light image enhancement problem.

IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model & task scaling. We conduct extensive empirical studies and reveal the following key insights: 1) performing gradient descent updates by alternating on diverse modalities, loss functions, and tasks, with varying input resolutions, efficiently improves the model.

Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we meet PhD students and early-career researchers, find out how machine learning is used for particle physics discoveries, cast an eye over the latest AI Index Report, and watch a robot beating elite players at table tennis. In an article published in Nature this month, Sony AI introduced Ace, a table tennis robot that has beaten professional players in competitive matches. The system combines event-based vision sensors and a control system based on model-free reinforcement learning, as well as state-of-the-art high-speed robot hardware. The ninth edition of the Artificial Intelligence Index Report was published on 13 April 2026 .