Related papers: Reward-Aware Trajectory Shaping for Few-step Visua…
This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective…
Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality…
Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…
Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching…
Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…
Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…
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…
Accelerating diffusion model sampling is crucial for efficient AIGC deployment. While diffusion distillation methods -- based on distribution matching and trajectory matching -- reduce sampling to as few as one step, they fall short on…
The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and suffer from…
Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions. The existing approaches reformulate denoising as a Markov decision process…
While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…
While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step…
Diffusion models offer superior generation quality at the expense of extensive sampling steps. Distillation methods, with Distribution Matching Distillation (DMD) as a popular example, can mitigate this issue, but performance degradation…
Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…
Trajectory prediction remains a critical yet challenging component in autonomous driving systems, requiring sophisticated reasoning capabilities while meeting strict real-time deployment constraints. While knowledge distillation has…
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…
In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing…
In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of…