中文
相关论文

相关论文: CHATS: Combining Human-Aligned Optimization and Te…

200 篇论文

Diffusion models have demonstrated significant promise in various generative tasks; however, they often struggle to satisfy challenging constraints. Our approach addresses this limitation by rethinking training-free loss-guided diffusion…

机器学习 · 计算机科学 2024-11-19 William Huang , Yifeng Jiang , Tom Van Wouwe , C. Karen Liu

Advances in generative models increase the need for sample quality assessment. To do so, previous methods rely on a pre-trained feature extractor to embed the generated samples and real samples into a common space for comparison. However,…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Jingyi Xu , Hieu Le , Dimitris Samaras

We investigate the generation of minority samples using pretrained text-to-image (T2I) latent diffusion models. Minority instances, in the context of T2I generation, can be defined as ones living on low-density regions of text-conditional…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Soobin Um , Jong Chul Ye

We provide an overview of the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in…

机器学习 · 统计学 2025-06-13 Justin Le

Recent advances in deep learning, such as powerful generative models and joint text-image embeddings, have provided the computational creativity community with new tools, opening new perspectives for artistic pursuits. Text-to-image…

计算机视觉与模式识别 · 计算机科学 2022-04-20 Yingtao Tian , Marco Cuturi , David Ha

In the last two years, text-to-image diffusion models have become extremely popular. As their quality and usage increase, a major concern has been the need for better output control. In addition to prompt engineering, one effective method…

计算机视觉与模式识别 · 计算机科学 2024-11-25 Clément Bonnet , Ariel N. Lee , Franck Wertel , Antoine Tamano , Tanguy Cizain , Pablo Ducru

Diffusion model alignment aims to bridge the gap between generated outputs and human preferences by enhancing both semantic consistency with textual prompts and overall visual quality. Existing alignment methods face a challenging…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Xin Xie , Jiaxian Guo , Dong Gong

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges.…

机器学习 · 计算机科学 2024-02-06 Chengyang Zhang , Yong Zhang , Qitan Shao , Bo Li , Yisheng Lv , Xinglin Piao , Baocai Yin

Recent developments in large language models (LLM) and generative AI have unleashed the astonishing capabilities of text-to-image generation systems to synthesize high-quality images that are faithful to a given reference text, known as a…

人机交互 · 计算机科学 2023-03-17 Yutong Xie , Zhaoying Pan , Jinge Ma , Luo Jie , Qiaozhu Mei

Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and…

计算机视觉与模式识别 · 计算机科学 2024-01-01 Guansong Lu , Yuanfan Guo , Jianhua Han , Minzhe Niu , Yihan Zeng , Songcen Xu , Zeyi Huang , Zhao Zhong , Wei Zhang , Hang Xu

As a challenging task, text-to-image generation aims to generate photo-realistic and semantically consistent images according to the given text descriptions. Existing methods mainly extract the text information from only one sentence to…

计算机视觉与模式识别 · 计算机科学 2022-09-29 Xintian Wu , Hanbin Zhao , Liangli Zheng , Shouhong Ding , Xi Li

Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt-image alignment. We revisit…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Yunzhe Zhang , Hongfu Liu , Pengyu Hong

Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted…

计算机视觉与模式识别 · 计算机科学 2025-06-23 Manuel Brack , Sudeep Katakol , Felix Friedrich , Patrick Schramowski , Hareesh Ravi , Kristian Kersting , Ajinkya Kale

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Yang Zhang , Teoh Tze Tzun , Lim Wei Hern , Tiviatis Sim , Kenji Kawaguchi

Text-to-Image generative systems are progressing rapidly to be a source of advertisement and media and could soon serve as image searches or artists. However, there is a significant concern about the representativity bias these models…

人机交互 · 计算机科学 2024-10-21 Asma Yamani , Malak Baslyman

While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Nupur Kumari , Bingliang Zhang , Richard Zhang , Eli Shechtman , Jun-Yan Zhu

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Yang Li , Songlin Yang , Xiaoxuan Han , Wei Wang , Jing Dong , Yueming Lyu , Ziyu Xue

We investigate a general approach for improving user prompts in text-to-image (T2I) diffusion models by finding prompts that maximize a reward function specified at test-time. Although diverse reward models are used for evaluating image…

机器学习 · 计算机科学 2025-09-30 Semin Kim , Yeonwoo Cha , Jaehoon Yoo , Seunghoon Hong

Text-to-image generative models often reflect the biases of the training data, leading to unequal representations of underrepresented groups. This study investigates inclusive text-to-image generative models that generate images based on…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Cheng Zhang , Xuanbai Chen , Siqi Chai , Chen Henry Wu , Dmitry Lagun , Thabo Beeler , Fernando De la Torre

Text-to-image models have made significant strides, producing impressive results in generating images from textual descriptions. However, creating a scalable pipeline for deploying these models in production remains a challenge. Achieving…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Parmida Atighehchian , Henry Wang , Andrei Kapustin , Boris Lerner , Tiancheng Jiang , Taylor Jensen , Negin Sokhandan