paper-with-me

홈 › Papers

VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering

2025-04-11 · Qi Zhi Lim, Chin Poo Lee, Kian Ming Lim, Kalaiarasi Sonai Muthu Anbananthen

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often suffer from limited reasoning capabilities, reliance on modality conversion, and inadequate alignment between visual and textual representations. To address these limitations, this paper introduces Vision-Language Multimodal Transformer (VLMT), a unified architecture that integrates a transformer-based vision encoder with a sequence-to-sequence language model. VLMT employs a direct token-level injection mechanism to fuse visual and textual inputs within a shared embedding space, eliminating the need for intermediate projection layers. To enhance cross-modal alignment and reasoning, a three-stage pretraining strategy is proposed to progressively align vision-language representations and improve the model's capacity for multimodal understanding. Based on the pretrained backbone, two task-specific modules are instantiated to form a two-stage MMQA framework: a multimodal reranker that predicts document relevance scores and utilizes a relative threshold with top-k strategy for context retrieval, and a multimodal question answering model that generates contextually grounded answers based on the retrieved evidence. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed approach. On MultimodalQA validation set, VLMT-Large achieves 76.5% Exact Match and 80.1% F1, outperforming the previous state-of-the-art by +9.1% in Exact Match and +8.8% in F1. On WebQA, it attains a QA score of 47.6, surpassing prior models such as PERQA by +3.2. These results highlight VLMT's strong capabilities in multimodal reasoning and its potential to advance real-world information retrieval and question answering systems.

📄 PDF Abstract BibTeX arXiv:2504.08269

Code (0)

등록된 구현이 없습니다.

Tasks

cross-modal alignmentInformation RetrievalMulti-hop Question AnsweringMultimodal ReasoningQuestion AnsweringRetrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Brain encoding models based on multimodal transformers can transfer across language and vision

2023-05-20 · NeurIPS 2023 11

Encoding models have been used to assess how the human brain represents concepts in language and vision. While language and vision rely on similar concept representations, current encoding models are typically trained an…

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

2022-03-30 · CVPR 2022 1 · Estelle Aflalo, Meng Du, Shao-Yen Tseng, Yongfei Liu 외

Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP model…

Question AnsweringVisual Commonsense ReasoningVisual Question AnsweringVisual Question Answering (VQA)

Multimodal Graph Transformer for Multimodal Question Answering

2023-04-30 · Xuehai He, Xin Eric Wang

Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning a…

Question Answering

VL-Mamba: Exploring State Space Models for Multimodal Learning

2024-03-20 · Yanyuan Qiao, Zheng Yu, Longteng Guo, Sihan Chen 외

Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in …

Language ModelingLanguage ModellingLarge Language ModelMamba+3

Multimodal Learning: Are Captions All You Need?

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In today's digital world, it is increasingly common for information to be multimodal: images or videos often accompany text. Sophisticated multimodal architectures such as ViLBERT, VisualBERT, and LXMERT have achieved st…

AllImage Captioning