VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models

• URL: http://arxiv.org/abs/2405.16919v2
• Date: Tue, 28 May 2024 06:12:45 GMT
• Title: VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
• Authors: Zejun Li, Ruipu Luo, Jiwen Zhang, Minghui Qiu, Zhongyu Wei,
• Abstract summary: This paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleaved and aligned manner.
• Score: 32.10766568096317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleaved and aligned manner, which effectively bridges the modality gap within LMMs during long-term generation. Additionally, we construct an instruction dataset to facilitate LMMs in adapting to reasoning with VoCoT. By introducing VoCoT into the prevalent open-source LMM architecture, we introduce VolCano. With only 7B parameters and limited input resolution, VolCano demonstrates excellent performance across various scenarios, surpassing SOTA models, including GPT-4V, in tasks requiring complex reasoning. Our code, data and model will be available at https://github.com/RupertLuo/VoCoT.

Related papers

• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Exploring the Capabilities of Large Multimodal Models on Dense Text [58.82262549456294]
  We propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved.
  arXiv  Detail & Related papers  (2024-05-09T07:47:25Z)
• Model Composition for Multimodal Large Language Models [71.5729418523411]
  We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model. Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
  arXiv  Detail & Related papers  (2024-02-20T06:38:10Z)
• CaMML: Context-Aware Multimodal Learner for Large Models [16.30752006781618]
  We introduce Context-Aware MultiModal Learner (CaMML) for tuning large multimodal models (LMMs) CaMML is crafted to seamlessly integrate multimodal contextual samples into large models, empowering the model to derive knowledge from analogous, domain-specific, up-to-date information. Based on CaMML, we have developed two multimodal models, CaMML-7B and CaMML-13B, that have shown exceptional performance across an array of benchmark datasets for multimodal tasks.
  arXiv  Detail & Related papers  (2024-01-06T07:54:58Z)
• CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs [48.269363759989915]
  The research focuses on two aspects: first, image-to-image matching, and second, multi-image-to-text matching. We conduct evaluations on a range of both open-source and closed-source large models, including GPT-4V, Gemini, OpenFlamingo, and MMICL.
  arXiv  Detail & Related papers  (2024-01-05T00:26:07Z)
• Multimodal Question Answering for Unified Information Extraction [15.798187192290746]
  Multimodal information extraction aims to extract structured information from unstructured multimedia content. Most current MIE models are task-specific and data-intensive. We propose a novel multimodal question answering (MQA) framework to unify three MIE tasks.
  arXiv  Detail & Related papers  (2023-10-04T17:58:05Z)
• MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities [159.9847317300497]
  We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes.
  arXiv  Detail & Related papers  (2023-08-04T17:59:47Z)
• FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing [88.6654909354382]
  We present a pure transformer-based framework, dubbed the Flexible Modal Vision Transformer (FM-ViT) for face anti-spoofing. FM-ViT can flexibly target any single-modal (i.e., RGB) attack scenarios with the help of available multi-modal data. Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin.
  arXiv  Detail & Related papers  (2023-05-05T04:28:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.