paper-with-me

Papers

Enhancing the Spatial Awareness Capability of Multi-Modal Large Language Model

2023-10-31 · Yongqiang Zhao, Zhenyu Li, Zhi Jin, Feng Zhang, Haiyan Zhao, Chengfeng Dou, Zhengwei Tao, Xinhai Xu, Donghong Liu

The Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM, encompassing diverse skills related to understanding spatial relationships among objects and between objects and the scene area. Industries such as autonomous driving, smart healthcare, robotics, virtual, and augmented reality heavily demand MLLM's spatial awareness capabilities. However, there exists a noticeable gap between the current spatial awareness capabilities of MLLM and the requirements set by human needs. To address this issue, this paper proposes using more precise spatial position information between objects to guide MLLM in providing more accurate responses to user-related inquiries. Specifically, for a particular multi-modal task, we utilize algorithms for acquiring geometric spatial information and scene graphs to obtain relevant geometric spatial information and scene details of objects involved in the query. Subsequently, based on this information, we direct MLLM to address spatial awareness-related queries posed by the user. Extensive experiments were conducted in benchmarks such as MME, MM-Vet, and other multi-modal large language models. The experimental results thoroughly confirm the efficacy of the proposed method in enhancing the spatial awareness tasks and associated tasks of MLLM.

📄 PDF Abstract BibTeX arXiv:2310.20357

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingLanguage ModelingLanguage ModellingLarge Language ModelMMEMM-Vet

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion

2025-11-21 · Jiajie Guo, Qingpeng Zhu, Jin Zeng, Xiaolong Wu 외 arxiv

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited…

Self-Supervised LearningSpatial Reasoning

SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs

2026-02-26 · Guanting Ye, Qiyan Zhao, Wenhao Yu, Liangyu Yuan 외 arxiv

3D Large Vision-Language Models (3D LVLMs) built upon Large Language Models (LLMs) have achieved remarkable progress across various multimodal tasks. However, their inherited position-dependent modeling mechanism, Rotary…

Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

2025-03-03 · Wenbin Wang, Yongcheng Jing, Liang Ding, Yingjie Wang 외

High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches…

RAGRetrievalRetrieval-augmented Generation

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

2024-12-10 · Arijit Ray, Jiafei Duan, Ellis Brown, Reuben Tan 외

Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason ab…

Action RecognitionSpatial Reasoning

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness

2026-07-26 · Qiao Yan, Yihan Wang, Zhenghao Xing, Jiaqi Xu 외 arxiv

Autonomous driving under adverse weather remains a critical challenge, yet existing vision-language benchmarks mainly evaluate under standard conditions, synthetic corruptions, or single modality. As a result, it remains…

Reinforcement LearningScene UnderstandingAutonomous Driving