English
Related papers

Related papers: Language Models Can See: Plugging Visual Controls …

200 papers

In this work, we study the problem of generating novel images from complex multimodal prompt sequences. While existing methods achieve promising results for text-to-image generation, they often struggle to capture fine-grained details from…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Amandeep Kumar , Muzammal Naseer , Sanath Narayan , Rao Muhammad Anwer , Salman Khan , Hisham Cholakkal

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture implied rules from…

Computation and Language · Computer Science 2024-07-08 Fan Zhang , Kebing Jin , Hankz Hankui Zhuo

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Jiarui Yu , Haoran Li , Yanbin Hao , Bin Zhu , Tong Xu , Xiangnan He

Text-to-image generative models like DALL-E and Stable Diffusion have revolutionized visual content creation across various applications, including advertising, personalized media, and design prototyping. However, crafting effective textual…

Artificial Intelligence · Computer Science 2025-07-22 Donghoon Kim , Minji Bae , Kyuhong Shim , Byonghyo Shim

We present a technique for zero-shot generation of a 3D model using only a target text prompt. Without any 3D supervision our method deforms the control shape of a limit subdivided surface along with its texture map and normal map to obtain…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Nasir Mohammad Khalid , Tianhao Xie , Eugene Belilovsky , Tiberiu Popa

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a diminished capability to effectively reason over and synthesize…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Kuei-Chun Kao , Hsu Tzu-Yin , Yunqi Hong , Ruochen Wang , Cho-Jui Hsieh

Prompt engineering is a powerful tool used to enhance the performance of pre-trained models on downstream tasks. For example, providing the prompt "Let's think step by step" improved GPT-3's reasoning accuracy to 63% on MutiArith while…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Cheng Shi , Sibei Yang

Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Zihao Wang , Wei Liu , Qian He , Xinglong Wu , Zili Yi

The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Gensheng Pei , Tao Chen , Yujia Wang , Xinhao Cai , Xiangbo Shu , Tianfei Zhou , Yazhou Yao

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Xihui Liu , Dong Huk Park , Samaneh Azadi , Gong Zhang , Arman Chopikyan , Yuxiao Hu , Humphrey Shi , Anna Rohrbach , Trevor Darrell

We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Junfeng Wu , Yi Jiang , Chuofan Ma , Yuliang Liu , Hengshuang Zhao , Zehuan Yuan , Song Bai , Xiang Bai

Revolutionary advancements in text-to-image models have unlocked new dimensions for sophisticated content creation, such as text-conditioned image editing, enabling the modification of existing images based on textual guidance. This…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Haoyu Zheng , Wenqiao Zhang , Yaoke Wang , Juncheng Li , Zheqi Lv , Xin Min , Mengze Li , Dongping Zhang , Siliang Tang , Yueting Zhuang

Visual metaphor generation is a challenging task that aims to generate an image given an input text metaphor. Inherently, it needs language understanding to bind a source concept with a target concept, in a way that preserves meaning while…

Computation and Language · Computer Science 2025-08-27 Girish A. Koushik , Fatemeh Nazarieh , Katherine Birch , Shenbin Qian , Diptesh Kanojia

Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, symbolic-domain controllable music generation has lagged behind partly due to the lack of a…

Sound · Computer Science 2025-06-17 Weihan Xu , Julian McAuley , Taylor Berg-Kirkpatrick , Shlomo Dubnov , Hao-Wen Dong

Perceptually Aligned Gradients (PAG) refer to an intriguing property observed in robust image classification models, wherein their input gradients align with human perception and pose semantic meanings. While this phenomenon has gained…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Roy Ganz , Michael Elad

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Youngsik Yun , Jihie Kim

Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Zhe Li , Weihao Yuan , Yisheng He , Lingteng Qiu , Shenhao Zhu , Xiaodong Gu , Weichao Shen , Yuan Dong , Zilong Dong , Laurence T. Yang

Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities…

Machine Learning · Computer Science 2026-04-10 Yucheng Zhou , Dubing Chen , Huan Zheng , Jianbing Shen

Multi-aspect controllable text generation aims to control the generated texts in attributes from multiple aspects (e.g., "positive" from sentiment and "sport" from topic). For ease of obtaining training samples, existing works neglect…

Computation and Language · Computer Science 2024-05-31 Yi Liu , Xiangyu Liu , Xiangrong Zhu , Wei Hu

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

Computation and Language · Computer Science 2022-03-31 Wenliang Dai , Lu Hou , Lifeng Shang , Xin Jiang , Qun Liu , Pascale Fung