相关论文: If you can describe it, they can see it: Cross-Mod…

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability…

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an…

Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they…

Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provide the model with…

Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective…

Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource…

Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs,…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

When confronted with objects of unknown types in an image, humans can effortlessly and precisely tell their visual boundaries. This recognition mechanism and underlying generalization capability seem to contrast to state-of-the-art image…

Knowledge is acquired by humans through experience, and no boundary is set between the kinds of knowledge or skill levels we can achieve on different tasks at the same time. When it comes to Neural Networks, that is not the case. The…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

In pursuit of detecting unstinted objects that extend beyond predefined categories, prior arts of open-vocabulary object detection (OVD) typically resort to pretrained vision-language models (VLMs) for base-to-novel category generalization.…

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and…

Recent large-scale vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and generating textual descriptions for visual content. However, these models lack an understanding of user-specific concepts. In…

Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product placement to entertainment and personalized design. Here we…

What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input comes from a…

Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector,…