Image de couverture de livre

Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gou, Yunhao, Chen, Kai, Liu, Zhili, Hong, Lanqing, Jin, Xin, Li, Zhenguo, Kwok, James T., Zhang, Yu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation
par: Gou, Yunhao, et autres
Publié: (2024)

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
par: Gou, Yunhao, et autres
Publié: (2025)

Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning
par: Gou, Yunhao, et autres
Publié: (2023)

Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts
par: Liu, Zhili, et autres
Publié: (2024)

Implicit Concept Removal of Diffusion Models
par: Liu, Zhili, et autres
Publié: (2023)

Mixed Autoencoder for Self-supervised Visual Representation Learning
par: Chen, Kai, et autres
Publié: (2023)

MIRAGE: A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence
par: Liu, Chonghan, et autres
Publié: (2025)

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
par: Wang, Yibo, et autres
Publié: (2024)

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
par: Wu, Linquan, et autres
Publié: (2026)

MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
par: Gao, Ruiyuan, et autres
Publié: (2024)

CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs
par: Zhong, Yingji, et autres
Publié: (2024)

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
par: Zhou, Jingqi, et autres
Publié: (2024)

Decoupling the Image Perception and Multimodal Reasoning for Reasoning Segmentation with Digital Twin Representations
par: Li, Yizhen, et autres
Publié: (2025)

MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes
par: Gao, Ruiyuan, et autres
Publié: (2024)

Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing
par: Li, Yan, et autres
Publié: (2026)

MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval
par: Ge, Xuri, et autres
Publié: (2026)

AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models
par: Zhang, Jiarui, et autres
Publié: (2026)

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
par: Li, Yunxin, et autres
Publié: (2025)

Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding
par: Pu, Bowei, et autres
Publié: (2025)

AliFuse: Aligning and Fusing Multi-modal Medical Data for Computer-Aided Diagnosis
par: Chen, Qiuhui, et autres
Publié: (2024)

Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training
par: Xing, Jinbo, et autres
Publié: (2026)

Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images
par: Zhang, Yichi, et autres
Publié: (2025)

Efficient Multi-modal Large Language Models via Visual Token Grouping
par: Huang, Minbin, et autres
Publié: (2024)

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
par: Huang, Qing, et autres
Publié: (2026)

Hybrid Latent Reasoning with Decoupled Policy Optimization
par: Cheng, Tao, et autres
Publié: (2026)

Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts
par: Zhao, Yuyang, et autres
Publié: (2023)

Integrating Text and Image Pre-training for Multi-modal Algorithmic Reasoning
par: Zhang, Zijian, et autres
Publié: (2024)

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
par: Jin, Song, et autres
Publié: (2026)

QTrack: Query-Driven Reasoning for Multi-modal MOT
par: Ashraf, Tajamul, et autres
Publié: (2026)

RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
par: Guo, Meng-Hao, et autres
Publié: (2025)

From Consistency to Complementarity: Aligned and Disentangled Multi-modal Learning for Time Series Understanding and Reasoning
par: Ni, Hang, et autres
Publié: (2026)

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
par: Liu, Yuqi, et autres
Publié: (2025)

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
par: Xiang, Kun, et autres
Publié: (2024)

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
par: Chen, Kai, et autres
Publié: (2023)

Empowering Sparse-Input Neural Radiance Fields with Dual-Level Semantic Guidance from Dense Novel Views
par: Zhong, Yingji, et autres
Publié: (2025)

Reasoning in Space via Grounding in the World
par: Chen, Yiming, et autres
Publié: (2025)

GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
par: Liu, Ruiheng, et autres
Publié: (2026)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
par: Wu, Juncheng, et autres
Publié: (2026)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
par: Xue, Haotian, et autres
Publié: (2025)

MagicDrive: Street View Generation with Diverse 3D Geometry Control
par: Gao, Ruiyuan, et autres
Publié: (2023)