English
Related papers

Related papers: Synthetic Curriculum Reinforces Compositional Text…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Linqing Wang , Ximing Xing , Yiji Cheng , Zhiyuan Zhao , Donghao Li , Tiankai Hang , Jiale Tao , Qixun Wang , Ruihuang Li , Comi Chen , Xin Li , Mingrui Wu , Xinchi Deng , Shuyang Gu , Chunyu Wang , Qinglin Lu

Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Shipeng Cao , Biao Qian , Haipeng Liu , Yang Wang , Meng Wang

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yusuf Dalva , Guocheng Gordon Qian , Maya Goldenberg , Tsai-Shien Chen , Kfir Aberman , Sergey Tulyakov , Pinar Yanardag , Kuan-Chieh Jackson Wang

Improving visual text synthesis has long been a challenging and evolving frontier for image generation models. While recent state-of-the-art (SOTA) models have made remarkable strides in text generation capabilities, existing benchmarks…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Peirong Zhang , Haowei Xu , Jiaxin Zhang , Xuhan Zheng , Guitao Xu , Yuyi Zhang , Junle Liu , Zhenhua Yang , Wei Zhou , Lianwen Jin

Scene graph generation (SGG) analyzes images to extract meaningful information about objects and their relationships. In the dynamic visual world, it is crucial for AI systems to continuously detect new objects and establish their…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Naitik Khandelwal , Xiao Liu , Mengmi Zhang

Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Haoxin Li , Boyang Li

Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text…

Computation and Language · Computer Science 2024-06-04 Tianqi Zhong , Zhaoyi Li , Quan Wang , Linqi Song , Ying Wei , Defu Lian , Zhendong Mao

Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Yanbo Wang , Justin Dauwels , Yilun Du

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Zhehao Huang , Yuhang Liu , Yixin Lou , Zhengbao He , Mingzhen He , Wenxing Zhou , Tao Li , Kehan Li , Zeyi Huang , Xiaolin Huang

Text-to-image (T2I) diffusion models excel at generating photorealistic images but often fail to render accurate spatial relationships. We identify two core issues underlying this common failure: 1) the ambiguous nature of data concerning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Gaoyang Zhang , Bingtao Fu , Qingnan Fan , Qi Zhang , Runxing Liu , Hong Gu , Huaqi Zhang , Xinguo Liu

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Kaishen Wang , Ruibo Chen , Tong Zheng , Heng Huang

In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language…

Computer Vision and Pattern Recognition · Computer Science 2019-12-20 Bowen Li , Xiaojuan Qi , Thomas Lukasiewicz , Philip H. S. Torr

While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jen-Yuan Huang , Tong Lin , Yilun Du

The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Spencer Ramsey , Jeffrey Lee , Amina Grant

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to…

Artificial Intelligence · Computer Science 2026-02-02 Linjia Kang , Zhimin Wang , Yongkang Zhang , Duo Wu , Jinghe Wang , Ming Ma , Haopeng Yan , Zhi Wang

Despite their impressive realism, modern text-to-image models still struggle with compositionality, often failing to render accurate object counts, attributes, and spatial relations. To address this challenge, we present a training-free…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Minsuk Ji , Sanghyeok Lee , Namhyuk Ahn

Deep learning models for skin disease classification require large, diverse, and well-annotated datasets. However, such resources are often limited due to privacy concerns, high annotation costs, and insufficient demographic representation.…

Image and Video Processing · Electrical Eng. & Systems 2025-08-01 Jamil Fayyad , Nourhan Bayasi , Ziyang Yu , Homayoun Najjaran

In this paper, we propose a novel generative network (SegAttnGAN) that utilizes additional segmentation information for the text-to-image synthesis task. As the segmentation data introduced to the model provides useful guidance on the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-27 Yuchuan Gou , Qiancheng Wu , Minghao Li , Bo Gong , Mei Han

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Hao Wang , Xingyu Lin , Yimeng Zhang , Tai Sing Lee

Text-to-image synthesis aims to automatically generate images according to text descriptions given by users, which is a highly challenging task. The main issues of text-to-image synthesis lie in two gaps: the heterogeneous and homogeneous…

Computer Vision and Pattern Recognition · Computer Science 2018-08-22 Mingkuan Yuan , Yuxin Peng