相关论文: HP-Edit: A Human-Preference Post-Training Framewor…

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a…

Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this…

Our goal is to develop fine-grained real-image editing methods suitable for real-world applications. In this paper, we first summarize four requirements for these methods and propose a novel diffusion-based image editing framework with…

The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Graphic layouts serve as an important and engaging medium for visual communication across different channels. While recent layout generation models have demonstrated impressive capabilities, they frequently fail to align with nuanced human…

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised…

Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which…

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Diffusion models have demonstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial computational cost. In this paper, we propose an Efficient…

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…

Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and…

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…

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the…

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…