Related papers: Ovis: Structural Embedding Alignment for Multimoda…

Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in understanding and generating content across various modalities, such as images and text. However, their interpretability remains a challenge, hindering…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…

The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the…

Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

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…

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…

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning tasks remains limited. This limitation can be attributed to…

Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this…

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws…

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal…

Recent advancements in multimodal large language models (MLLMs) have achieved significant multimodal generation capabilities, akin to GPT-4. These models predominantly map visual information into language representation space, leveraging…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often…

Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. Following LLaVA's paradigm, mainstream LVLMs typically employ…

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…