paper-with-me

Papers

Think Visually: Question Answering through Virtual Imagery

2018-05-25 · ACL 2018 7 · Ankit Goyal, Jian Wang, Jia Deng

In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.

📄 PDF Abstract BibTeX arXiv:1805.11025

Code (1)

umich-vl/think_visually 공식 구현 tf

Tasks

Question AnsweringVisual Commonsense Reasoning

Methods 이 논문이 사용한 방법론

Memory Network 설명 없음

Similar Papers 제목 키워드 기반

Ontology-based question answering over corporate structured data

2021-11-08 · Sergey Gorshkov, Constantin Kondratiev, Roman Shebalov

Ontology-based approach to the Natural Language Understanding (NLU) processing allows to improve questions answering quality in dialogue systems. We describe our NLU engine architecture and evaluate its implementation. T…

Natural Language UnderstandingQuestion Answering

Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

2024-12-18 · CVPR 2025 1 · Jihan Yang, Shusheng Yang, Anjali W. Gupta, Rilyn Han 외

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space''…

Question AnsweringSpatial Reasoning

Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions

2023-06-16 · Chad DeChant, Iretiayo Akinola, Daniel Bauer

When robots perform long action sequences, users will want to easily and reliably find out what they have done. We therefore demonstrate the task of learning to summarize and answer questions about a robot agent's past a…

Language ModelingLanguage ModellingLarge Language ModelQuestion Answering

See and Think: Embodied Agent in Virtual Environment

2023-11-26 · Zhonghan Zhao, Wenhao Chai, Xuan Wang, Li Boyi 외

Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embo…

MinecraftQuestion AnsweringRetrieval

UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models

2024-06-04 · Zhuoyang Li, Liran Deng, Hui Liu, Qiaoqiao Liu 외

OwnThink stands as the most extensive Chinese open-domain knowledge graph introduced in recent times. Despite prior attempts in question answering over OwnThink (OQA), existing studies have faced limitations in model rep…

Graph Question AnsweringQuestion AnsweringRAGRetrieval-augmented Generation+1