相关论文: Does language help generalization in vision models…

What does learning to model relationships between strings teach large language models (LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and recognize an assortment of visual concepts of increasing…

This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images. It focuses on applications for low-resource languages and understanding human language acquisition. We introduce a task…

CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a huge dataset. LiT improved this by only training the text…

Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some…

Large language models readily adapt to novel settings, even without task-specific training data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we propose ESPER which extends language-only zero-shot models to…

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question…

We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models…

Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…

Generalist multimodal large language models (MLLMs) have achieved impressive performance across a wide range of vision-language tasks. However, their performance on medical tasks, particularly in zero-shot settings where generalization is…

This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…

We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the…

Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…

The success of vision-language models is primarily attributed to effective alignment across modalities such as vision and language. However, modality gaps persist in existing alignment algorithms and appear necessary for human perception as…

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract…

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently…

Prompt tuning for vision-language models such as CLIP involves optimizing the text prompts used to generate image-text pairs for specific downstream tasks. While hand-crafted or template-based prompts are generally applicable to a wider…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Does language help make sense of the visual world? How important is it to actually see the world rather than having it described with words? These basic questions about the nature of intelligence have been difficult to answer because we…