Related papers: Discrete Diffusion Trajectory Alignment via Stepwi…

Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers…

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. In the case of diffusion models (DMs), though RL training improves alignment from early timesteps, critical issues…

Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking:…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in…

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,…

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a…

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing…

We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting…

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…

Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering a promising perspective. However, due to the computational…

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes…