相关论文: Visual Instruction Tuning towards General-Purpose …

Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of task generalization since preparing a task-specific example…

Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are derived from image…

We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions. Unlike existing approaches that integrate prior knowledge and pre-define the output space (e.g., categories and…

Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Evaluating the generalisation capabilities of multimodal models based solely on their performance on out-of-distribution data fails to capture their true robustness. This work introduces a comprehensive evaluation framework that…

Automatically evaluating vision-language tasks is challenging, especially when it comes to reflecting human judgments due to limitations in accounting for fine-grained details. Although GPT-4V has shown promising results in various…

We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which…

Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models. More recently, instruction-tuned multimodal (IT) models…

Transformer design is the de facto standard for natural language processing tasks. The success of the transformer design in natural language processing has lately piqued the interest of researchers in the domain of computer vision. When…

Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this…

While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are…

Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing…

Multimodal models like LLaVA-1.5 achieve state-of-the-art visual understanding through visual instruction tuning on multitask datasets, enabling strong instruction-following and multimodal performance. However, multitask learning faces…

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1)…

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Visual instruction tuning (VIT) has emerged as a crucial technique for enabling multi-modal large language models (MLLMs) to follow user instructions adeptly. Yet, a significant gap persists in understanding the attributes of high-quality…

There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one…

Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…