Related papers: Region-Constrained Group Relative Policy Optimizat…

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Instruction-based image editing with diffusion models has achieved impressive results, yet existing methods struggle with fine-grained instructions specifying precise attributes such as colors, positions, and quantities. While recent…

Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to…

Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based…

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as…

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…

The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…

Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains…

Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. However, in the later stages of training, the model tends to…

Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality scene text images, but the limited coverage of glyph…

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative…

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still suffer from the sparse reward problem: the terminal reward of…

Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preference signals. However, its effectiveness is fundamentally…

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic…