English
Related papers

Related papers: Impact of Pretraining Word Co-occurrence on Compos…

200 papers

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

How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Xiaohui Chen , Satya Narayan Shukla , Mahmoud Azab , Aashu Singh , Qifan Wang , David Yang , ShengYun Peng , Hanchao Yu , Shen Yan , Xuewen Zhang , Baosheng He

As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not encountered during training -- has garnered significant…

Computation and Language · Computer Science 2025-01-22 Haoyu Zhao , Simran Kaur , Dingli Yu , Anirudh Goyal , Sanjeev Arora

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Marc-Antoine Lavoie , Anas Mahmoud , Aldo Zaimi , Arsene Fansi Tchango , Steven L. Waslander

We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior conclusions that CLIP models can inadvertently…

Machine Learning · Computer Science 2024-03-08 Ibrahim Alabdulmohsin , Xiao Wang , Andreas Steiner , Priya Goyal , Alexander D'Amour , Xiaohua Zhai

Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings. However, the extent to which this extrapolation relies on robust reasoning is unclear. In…

Computation and Language · Computer Science 2023-03-17 Yasaman Razeghi , Robert L. Logan , Matt Gardner , Sameer Singh

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Runhui Huang , Yanxin Long , Jianhua Han , Hang Xu , Xiwen Liang , Chunjing Xu , Xiaodan Liang

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Ali Abdollah , Amirmohammad Izadi , Armin Saghafian , Reza Vahidimajd , Mohammad Mozafari , Amirreza Mirzaei , Mohammadmahdi Samiei , Mahdieh Soleymani Baghshah

In-context learning (ICL) has emerged as a powerful capability for large language models (LLMs) to adapt to downstream tasks by leveraging a few (demonstration) examples. Despite its effectiveness, the mechanism behind ICL remains…

Machine Learning · Computer Science 2025-06-03 Pengfei He , Yingqian Cui , Han Xu , Hui Liu , Makoto Yamada , Jiliang Tang , Yue Xing

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Fawaz Sammani , Nikos Deligiannis

Medical imaging provides essential visual insights for diagnosis, and multimodal large language models (MLLMs) are increasingly utilized for its analysis due to their strong generalization capabilities; however, the underlying factors…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Zhenyang Cai , Junying Chen , Rongsheng Wang , Weihong Wang , Yonglin Deng , Dingjie Song , Yize Chen , Zixu Zhang , Benyou Wang

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Yunhao Ge , Jie Ren , Andrew Gallagher , Yuxiao Wang , Ming-Hsuan Yang , Hartwig Adam , Laurent Itti , Balaji Lakshminarayanan , Jiaping Zhao

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Darina Koishigarina , Arnas Uselis , Seong Joon Oh

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to…

Artificial Intelligence · Computer Science 2024-10-23 Zhijie Tan , Xu Chu , Weiping Li , Tong Mo

In this study, we propose an enhancement to the similarity computation mechanism in multi-modal contrastive pretraining frameworks such as CLIP. Prior theoretical research has demonstrated that the optimal similarity metrics between paired…

Machine Learning · Computer Science 2025-10-20 Naoki Yoshida , Satoshi Hayakawa , Yuhta Takida , Toshimitsu Uesaka , Hiromi Wakaki , Yuki Mitsufuji

Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Kecheng Zheng , Yifei Zhang , Wei Wu , Fan Lu , Shuailei Ma , Xin Jin , Wei Chen , Yujun Shen

Figuring out which objects or concepts words refer to is a central language learning challenge for young children. Most models of this process posit that children learn early object labels from co-occurrences of words and their referents…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Alvin Wei Ming Tan , Jane Yang , Tarun Sepuri , Khai Loong Aw , Robert Z. Sparks , Zi Yin , Virginia A. Marchman , Michael C. Frank , Bria Long

The potential of multimodal generative artificial intelligence (mAI) to replicate human grounded language understanding, including the pragmatic, context-rich aspects of communication, remains to be clarified. Humans are known to use…

Despite the recent increase in research on artificial intelligence for music, prominent correlations between key components of lyrics and rhythm such as keywords, stressed syllables, and strong beats are not frequently studied. This is…

Sound · Computer Science 2025-07-10 Callie C. Liao , Duoduo Liao , Jesse Guessford

Several benchmarks have concluded that our best vision-language models (e.g., CLIP) are lacking in compositionality. Given an image, these benchmarks probe a model's ability to identify its associated caption amongst a set of compositional…

Computation and Language · Computer Science 2024-09-27 Amita Kamath , Cheng-Yu Hsieh , Kai-Wei Chang , Ranjay Krishna