Related papers: Subject-driven Text-to-Image Generation via Prefer…

Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently…

Despite advancements in text-to-image generation (T2I), prior methods often face text-image misalignment problems such as relation confusion in generated images. Existing solutions involve cross-attention manipulation for better…

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images. However, prevalent subject-driven models primarily rely on single-concept input…

A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individuals. We introduce MR-FlowDPO, a novel approach that enhances…

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative embeddings are derived from user-defined negative prompts,…

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable…

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…

Research on generative models to produce human-aligned / human-preferred outputs has seen significant recent contributions. Between text and image-generative models, we narrowed our focus to text-based generative models, particularly to…

Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for text-to-image and text-to-video generation. However, we find that directly applying these…

Subject-driven image generation aims at generating images containing customized subjects, which has recently drawn enormous attention from the research community. However, the previous works cannot precisely control the background and…

Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these…

Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and…

Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image…

This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to…

Reward models trained on human preference data have demonstrated strong effectiveness in aligning Large Language Models (LLMs) with human intent under the framework of Reinforcement Learning from Human Feedback (RLHF). However, RLHF remains…

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…