Related papers: Video Diffusion Alignment via Reward Gradients
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…
We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…
This paper investigates the performance of diffusion models for video anomaly detection (VAD) within the most challenging but also the most operational scenario in which the data annotations are not used. As being sparse, diverse,…
Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making…
We propose a technique that propagates information forward through video data. The method is conceptually simple and can be applied to tasks that require the propagation of structured information, such as semantic labels, based on video…
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…
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…
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural…
Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increasing availability of pre-trained image and video…
Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…
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…
Guided or controlled data generation with diffusion models\blfootnote{Partial preliminary results of this work appeared in International Conference on Machine Learning 2025 \citep{li2025provable}.} has become a cornerstone of modern…
Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise…
Diffusion models, a family of generative models based on deep learning, have become increasingly prominent in cutting-edge machine learning research. With a distinguished performance in generating samples that resemble the observed data,…
Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems. Reward function is crucial for most of…
The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editing has gained substantial attention and seen a swift rise in…
We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a…
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…
Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider,…
The landscape of computer graphics has undergone significant transformations with the recent advances of differentiable rendering models. These rendering models often rely on heuristic designs that may not fully align with the final…