相关论文: Let ViT Speak: Generative Language-Image Pre-train…

All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is…

In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios.…

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent…

The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and multimodal understanding capability, which quickly set new…

In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their prowess, the closed-source nature and computational demands…

General purpose Vision Language Models (VLMs) have received tremendous interest in recent years, owing to their ability to learn rich vision-language correlations as well as their broad zero-shot competencies. One immensely popular line of…

Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…

Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing…

Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean…

In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual…

Currently, the most dominant approach to establishing language-image alignment is to pre-train text and image encoders jointly through contrastive learning, such as CLIP and its variants. In this work, we question whether such a costly…

Text-to-image generation has made significant advancements with the introduction of text-to-image diffusion models. These models typically consist of a language model that interprets user prompts and a vision model that generates…

In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for monolithic MLLMs…

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like GPT have revolutionized NLP, most visual generative…

3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms.…

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…

LLMs have demonstrated remarkable capabilities in linguistic reasoning and are increasingly adept at vision-language tasks. The integration of image tokens into transformers has enabled direct visual input and output, advancing research…