相关论文: Confidence-aware Reward Optimization for Fine-tuni…

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Recent advancements in text-to-image (T2I) diffusion models have demonstrated remarkable capabilities in generating high-fidelity images. However, these models often struggle to faithfully render complex user prompts, particularly in…

Achieving fairness in text-to-image generation demands mitigating social biases without compromising visual fidelity, a challenge critical to responsible AI. Current fairness evaluation procedures for text-to-image models rely on…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior…

Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models is a promising path to improve human preference alignment, factuality, and aesthetics. We…

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typically user preference. This discards…

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified prompts, leading to suboptimal image-text alignment, aesthetics, and quality. We propose a…

The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless…

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic images. Despite the progress, these models still struggle to…

Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or…

This paper investigates image inpainting with preference alignment. Instead of introducing a novel method, we go back to basics and revisit fundamental problems in achieving such alignment. We leverage the prominent direct preference…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently…

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious…

Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source…

Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often resulting in unrealistic movements and frequent violations of…