Related papers: Inference-Time Alignment of Diffusion Models with …
Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to improving the quality of text-to-image diffusion models.…
Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…
Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…
Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference…
Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diffusion models can be categorized into two main strategies:…
The integration of preference alignment with diffusion models (DMs) has emerged as a transformative approach to enhance image generation and editing capabilities. Although integrating diffusion models with preference alignment strategies…
Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data…
Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity of the reference…
Diffusion-based planning, learning, and control methods present a promising branch of powerful and expressive decision-making solutions. Given the growing interest, such methods have undergone numerous refinements over the past years.…
Diffusion models have emerged as a key pillar of foundation models in visual domains. One of their critical applications is to universally solve different downstream inverse tasks via a single diffusion prior without re-training for each…
Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques focus on individual samples, struggling in applications that require the sample population…
The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless…
Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the…
Diffusion model alignment aims to bridge the gap between generated outputs and human preferences by enhancing both semantic consistency with textual prompts and overall visual quality. Existing alignment methods face a challenging…
Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…
Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…
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…
Despite many attempts to leverage pre-trained text-to-image models (T2I) like Stable Diffusion (SD) for controllable image editing, producing good predictable results remains a challenge. Previous approaches have focused on either…
Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement,…
Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time. However, we observe that these approaches are usually restricted to differentiable or…