paper-with-me

Papers

A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

2023-05-08 · Yunxin Li, Baotian Hu, Xinyu Chen, Yuxin Ding, Lin Ma, Min Zhang

Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct option. Previous methods utilizing pretrained vision-language models (VLMs) have achieved impressive performances, yet they show a lack of multimodal context reasoning capability, especially for text-modal information. To address this issue, we propose a Multi-modal Context Reasoning approach, named ModCR. Compared to VLMs performing reasoning via cross modal semantic alignment, it regards the given textual abstract semantic and objective image information as the pre-context information and embeds them into the language model to perform context reasoning. Different from recent vision-aided language models used in natural language processing, ModCR incorporates the multi-view semantic alignment information between language and vision by introducing the learnable alignment prefix between image and text in the pretrained language model. This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues. We conduct extensive experiments on two corresponding data sets and experimental results show significantly improved performance (exact gain by 4.8% on PMR test set) compared to previous strong baselines. Code Link: \url{https://github.com/YunxinLi/Multimodal-Context-Reasoning}.

📄 PDF Abstract BibTeX arXiv:2305.04530

Code (1)

yunxinli/multimodal-context-reasoning 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Conditional and Modal Reasoning in Large Language Models

2024-01-30 · Wesley H. Holliday, Matthew Mandelkern, Cedegao E. Zhang

The reasoning abilities of large language models (LLMs) are the topic of a growing body of research in AI and cognitive science. In this paper, we probe the extent to which twenty-nine LLMs are able to distinguish logica…

Logical Reasoning

LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations

2026-05-01 · Huangbiao Xu, Huanqi Wu, Xiao Ke, Yuxin Peng arxiv

Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availabi…

Action Quality Assessment

Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval

2025-11-20 · Chunxu Liu, Jiyuan Yang, Ruopeng Gao, Yuhan Zhu 외 arxiv

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Langu…

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues

2021-05-15 · ACL 2022 5 · Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng 외

It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query. In this work, we …

Multimodal ReasoningNatural Language InferenceVisual Commonsense Reasoning

Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought

2025-07-10 · Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa arxiv

Large vision-language models (LVLMs) have demonstrated remarkable capabilities by integrating pre-trained vision encoders with large language models (LLMs). Similar to single-modal LLMs, chain-of-thought (CoT) prompting …