Related papers: Alignment-Guided Score Matching for Text-to-Image …

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the…

Diffusion models have achieved impressive results in generative tasks for text-to-video (T2V) synthesis. However, achieving accurate text alignment in T2V generation remains challenging due to the complex temporal dependencies across…

Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been…

Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of…

Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tuning Large Language Models (LLMs). While cutting-edge…

Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffusion models, have made significant progress in 3D…

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that…

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In…

Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect…

Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs,…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mapping noise to data,…

Diffusion models have recently advanced human motion generation, producing realistic and diverse animations from textual prompts. However, adapting these models to unseen actions or styles typically requires additional motion capture data…

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…

Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically requires…