Buchumschlag

GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Wenshuai, Xiang, Xiantai, Wen, Zixiao, Zhou, Guangyao, Niu, Ben, Wang, Feng, Huang, Lijia, Wang, Qiantong, Hu, Yuxin
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection
von: Xiang, Xiantai, et al.
Veröffentlicht: (2026)

SiamGM: Siamese Geometry-Aware and Motion-Guided Network for Real-Time Satellite Video Object Tracking
von: Wen, Zixiao, et al.
Veröffentlicht: (2026)

D$^3$R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images
von: Wen, Zixiao, et al.
Veröffentlicht: (2026)

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
von: Li, Ling, et al.
Veröffentlicht: (2024)

GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
von: Yan, Yibo, et al.
Veröffentlicht: (2024)

The Bathroom Model: A Realistic Approach to Hash Table Algorithm Optimization
von: Wang, Qiantong
Veröffentlicht: (2025)

From "Hallucination" to "Suture": Insights from Language Philosophy to Enhance Large Language Models
von: Wang, Qiantong
Veröffentlicht: (2025)

GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning
von: Yang, Xiao, et al.
Veröffentlicht: (2026)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
von: Chen, Houlun, et al.
Veröffentlicht: (2026)

Vision-Language Models in Remote Sensing: Current Progress and Future Trends
von: Li, Xiang, et al.
Veröffentlicht: (2023)

Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing
von: Lyu, Shuchang, et al.
Veröffentlicht: (2026)

Large Vision-Language Models for Remote Sensing Visual Question Answering
von: Siripong, Surasakdi, et al.
Veröffentlicht: (2024)

Self-supervised Audiovisual Representation Learning for Remote Sensing Data
von: Heidler, Konrad, et al.
Veröffentlicht: (2021)

Copy-Move Forgery Detection and Question Answering for Remote Sensing Image
von: Zhang, Ze, et al.
Veröffentlicht: (2024)

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
von: Luo, Zhiming, et al.
Veröffentlicht: (2026)

GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning
von: Fiaz, Mustansar, et al.
Veröffentlicht: (2025)

ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks
von: Shabbir, Akashah, et al.
Veröffentlicht: (2025)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
von: Liu, Junming, et al.
Veröffentlicht: (2026)

RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering
von: Wang, Yuduo, et al.
Veröffentlicht: (2023)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
von: Wang, Jiaqi, et al.
Veröffentlicht: (2025)

Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models
von: Wang, Dongdong, et al.
Veröffentlicht: (2026)

Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology
von: Wu, Kaiyu, et al.
Veröffentlicht: (2026)

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering
von: Liao, Zhaohe, et al.
Veröffentlicht: (2024)

AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
von: Wang, Yuxin, et al.
Veröffentlicht: (2026)

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
von: Zhang, Xue, et al.
Veröffentlicht: (2025)

Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining
von: Li, Yuxuan, et al.
Veröffentlicht: (2026)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
von: Wu, Junfei, et al.
Veröffentlicht: (2025)

Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis
von: Weng, Xingxing, et al.
Veröffentlicht: (2026)

Reinforcing Video Reasoning with Focused Thinking
von: Dang, Jisheng, et al.
Veröffentlicht: (2025)

RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering
von: Lin, Hui, et al.
Veröffentlicht: (2024)

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
von: Zhou, Yue, et al.
Veröffentlicht: (2024)

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
von: Yang, Jie, et al.
Veröffentlicht: (2025)

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems
von: Wang, Zhengren, et al.
Veröffentlicht: (2024)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
von: Zhang, Yi, et al.
Veröffentlicht: (2025)

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
von: Huang, Chi-Pin, et al.
Veröffentlicht: (2025)

RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering
von: Zi, Xing, et al.
Veröffentlicht: (2025)

Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
von: Liu, Yinhong, et al.
Veröffentlicht: (2024)

Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
von: Liu, Jiaqi, et al.
Veröffentlicht: (2025)

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
von: Li, Songze, et al.
Veröffentlicht: (2025)

Visual Question Answering on Multiple Remote Sensing Image Modalities
von: Boussaid, Hichem, et al.
Veröffentlicht: (2025)