Related papers: MVP: Multimodality-guided Visual Pre-training

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy…

Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance…

Most of the currently existing vision and language pre-training (VLP) methods have mainly focused on how to extract and align vision and text features. In contrast to the mainstream VLP methods, we highlight that two routinely applied steps…

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches…

Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then…

To extend the application of vision-language models (VLMs) from web images to sensor-mediated physical environments, we propose Multi-View Physical-prompt for Test-Time Adaptation (MVP), a forward-only framework that moves test-time…

Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality…

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from token masking in text,…

Vision Transformer (ViT) has become one of the most popular neural architectures due to its great scalability, computational efficiency, and compelling performance in many vision tasks. However, ViT has shown inferior performance to…

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders…

Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually…

Multimodal pre-training remains constrained by the descriptive bias of image-caption pairs, leading models to favor surface linguistic cues over grounded visual understanding. We introduce MMRPT, a masked multimodal reinforcement…

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…