Related papers: Scaling Vision Transformers to 22 Billion Paramete…

Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable AI algorithms for comprehending and grasping a language. As a major approach,…

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have…

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a…

This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the…

Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications. However, there is a notable paucity of detailed, open-sourced methodologies on…

Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully…

Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness. While these are remarkable…

Large Language Models (LLMs) show potential for enhancing robotic path planning. This paper assesses visual input's utility for multimodal LLMs in such tasks via a comprehensive benchmark. We evaluated 15 multimodal LLMs on generating valid…

Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent works proposed several parameter-efficient transfer learning…

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Visual instruction tuning has recently shown encouraging progress with open-source large multimodal models (LMM) such as LLaVA and MiniGPT-4. However, most existing studies of open-source LMM are performed using models with 13B parameters…

Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase…

This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. Motivated by the universality of the Multi-layer Transformer architecture (e.g, GPT) widely used…

We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves…

Vision-Language Translation (VLT) is a challenging task that requires accurately recognizing multilingual text embedded in images and translating it into the target language with the support of visual context. While recent Large…