相关论文: PatchDPO: Patch-level DPO for Finetuning-free Pers…

Differentially private synthetic data is a promising alternative for sensitive data release. Many differentially private generative models have been proposed in the literature. Unfortunately, they all suffer from the low utility of the…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…

DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have…

We present SignDPO, a novel multi-level Direct Preference Optimisation (DPO) framework designed to enhance the alignment of skeleton-based Sign Language Translation. While current skeleton-based models have made significant progress using…

Differentially private (DP) image synthesis aims to generate synthetic images from a sensitive dataset, alleviating the privacy leakage concerns of organizations sharing and utilizing synthetic images. Although previous methods have…

Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for researchers and practitioners who lack substantial computational…

Zero-shot depth estimation (DE) models exhibit strong generalization performance as they are trained on large-scale datasets. However, existing models struggle with high-resolution images due to the discrepancy in image resolutions of…

Recent advances in diffusion models have improved Real-World Image Super-Resolution (Real-ISR), but existing methods lack human feedback integration, risking misalignment with human preference and may leading to artifacts, hallucinations…

In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a…

Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage…

Personalizing image generation and editing is particularly challenging when we only have a few images of the subject, or even a single image. A common approach to personalization is concept learning, which can integrate the subject into…

Vision generation remains a challenging frontier in artificial intelligence, requiring seamless integration of visual understanding and generative capabilities. In this paper, we propose a novel framework, Vision-Driven Prompt Optimization…

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…

The scarcity of publicly available medical imaging data limits the development of effective AI models. This work proposes a memory-efficient patch-wise denoising diffusion probabilistic model (DDPM) for generating synthetic medical images,…

The emergence of text-to-image generation models has led to the recognition that image enhancement, performed as post-processing, would significantly improve the visual quality of the generated images. Exploring diffusion models to enhance…

In recent years, learning-based color and tone enhancement methods for photos have become increasingly popular. However, most learning-based image enhancement methods just learn a mapping from one distribution to another based on one…

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image…