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