Cover Image

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhong, Qihuang, Ding, Liang, Xuan, Wenjie, Liu, Juhua, Du, Bo, Tao, Dacheng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethink Sparse Signals for Pose-guided Text-to-image Generation
by: Xuan, Wenjie, et al.
Published: (2025)

LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?
by: Ye, Maoyuan, et al.
Published: (2025)

Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
by: He, Haibin, et al.
Published: (2025)

When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
by: Xuan, Wenjie, et al.
Published: (2024)

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
by: Zhong, Qihuang, et al.
Published: (2026)

SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA
by: He, Haibin, et al.
Published: (2025)

RFL-CDNet: Towards Accurate Change Detection via Richer Feature Learning
by: Gan, Yuhang, et al.
Published: (2024)

Detect Changes like Humans: Incorporating Semantic Priors for Improved Change Detection
by: Gan, Yuhang, et al.
Published: (2024)

GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
by: He, Haibin, et al.
Published: (2025)

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
by: He, Haibin, et al.
Published: (2024)

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
by: Ye, Maoyuan, et al.
Published: (2023)

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

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
by: Ye, Maoyuan, et al.
Published: (2024)

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
by: He, Haibin, et al.
Published: (2026)

Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
by: Wang, Wenbin, et al.
Published: (2024)

Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation
by: Zhang, Jing, et al.
Published: (2026)

See, Think, Learn: A Self-Taught Multimodal Reasoner
by: Sharma, Sourabh, et al.
Published: (2025)

Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
by: Chen, Yiyang, et al.
Published: (2025)

Question Aware Vision Transformer for Multimodal Reasoning
by: Ganz, Roy, et al.
Published: (2024)

Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving
by: Liao, Dacheng, et al.
Published: (2024)

Review of Hallucination Understanding in Large Language and Vision Models
by: Ho, Zhengyi, et al.
Published: (2025)

ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
by: Zhang, Xike, et al.
Published: (2026)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
by: Wu, Juncheng, et al.
Published: (2026)

E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
by: Zhong, Qihuang, et al.
Published: (2022)

ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
by: Zhong, Qihuang, et al.
Published: (2024)

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
by: Zhong, Qihuang, et al.
Published: (2022)

Epistemic-aware Vision-Language Foundation Model for Fetal Ultrasound Interpretation
by: He, Xiao, et al.
Published: (2025)

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2026)

Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
by: Gong, Xuan, et al.
Published: (2026)

Hierarchy-Aware Fine-Tuning of Vision-Language Models
by: Li, Jiayu, et al.
Published: (2025)

One Flight Over the Gap: A Survey from Perspective to Panoramic Vision
by: Lin, Xin, et al.
Published: (2025)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
by: Liang, Siyuan, et al.
Published: (2024)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
by: Yang, Yi, et al.
Published: (2025)

Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
by: Chen, Yang, et al.
Published: (2024)

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
by: Ye, Mang, et al.
Published: (2025)

On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
by: Zhao, Haimei, et al.
Published: (2022)

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation
by: Ning, Zhenhua, et al.
Published: (2025)

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
by: Xiang, Kun, et al.
Published: (2024)

UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy
by: Xu, Yicheng, et al.
Published: (2026)

PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking
by: Lv, Meng, et al.
Published: (2026)