Related papers: Vision-Centric Activation and Coordination for Mul…

Multimodal retrieval systems typically employ Vision Language Models (VLMs) that encode images and text independently into vectors within a shared embedding space. Despite incorporating text encoders, VLMs consistently underperform…

Visual language tasks require AI models to comprehend and reason with both visual and textual content. Driven by the power of Large Language Models (LLMs), two prominent methods have emerged: (1) the hybrid integration between LLMs and…

Recent advances in multimodal training have significantly improved the integration of image understanding and generation within a unified model. This study investigates how vision-language models (VLMs) handle image-understanding 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…

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood. Existing interpretability research has primarily…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Large Vision-Language Models (LVLMs) incur high computational costs due to significant redundancy in their visual tokens. To effectively reduce this cost, researchers have proposed various visual token pruning methods. However, existing…

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

Multimodal Large Language Models (MLLMs) have showcased exceptional Chain-of-Thought (CoT) reasoning ability in complex textual inference tasks including causal reasoning. However, will these causalities remain straightforward when crucial…

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

Vision-Language Models (VLMs) excel at high-level scene understanding but falter on fine-grained perception tasks requiring precise localization. This failure stems from a fundamental mismatch, as generating exact numerical coordinates is a…

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

Multimodal Large Language Models (MLLMs) such as GPT-4V and Gemini Pro face challenges in achieving human-level perception in Visual Question Answering (VQA), particularly in object-oriented perception tasks which demand fine-grained…

Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial computational overhead. In this work, we revisit the necessity…

Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks…

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently…

Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data.…

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each…

The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This…