Cover Image

Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Longwei, Feng, Feng, Zhang, Shaojie, Chen, Xin, Li, Hang, Du, Anan, Yu, Hailong, Fu, Pei, Luo, Zhenbo, Luan, Jian
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

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
by: Zhang, Shaojie, et al.
Published: (2025)

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment
by: Sun, Yuchen, et al.
Published: (2026)

Rethinking Causal Mask Attention for Vision-Language Inference
by: Pei, Xiaohuan, et al.
Published: (2025)

PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues
by: Qi, Yukun, et al.
Published: (2026)

Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning
by: Zhang, Shaojie, et al.
Published: (2025)

Exploration of Masked and Causal Language Modelling for Text Generation
by: Micheletti, Nicolo, et al.
Published: (2024)

DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models
by: Zhou, Xueyu, et al.
Published: (2026)

MaskSearch: Querying Image Masks at Scale
by: He, Dong, et al.
Published: (2023)

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
by: Zhang, Shaojie, et al.
Published: (2025)

Contrastive Masked Autoencoders are Stronger Vision Learners
by: Huang, Zhicheng, et al.
Published: (2022)

MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
by: Zhang, Guohui, et al.
Published: (2025)

AntLM: Bridging Causal and Masked Language Models
by: Yu, Xinru, et al.
Published: (2024)

Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition
by: Zhang, Yiru, et al.
Published: (2025)

MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation
by: Wei, Wei, et al.
Published: (2025)

MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
by: Zhang, Xin, et al.
Published: (2025)

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
by: Fang, Yiyang, et al.
Published: (2026)

SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
by: Liang, Feng, et al.
Published: (2022)

IMTBench: A Multi-Scenario Cross-Modal Collaborative Evaluation Benchmark for In-Image Machine Translation
by: Lyu, Jiahao, et al.
Published: (2026)

GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models
by: Wang, Shaokang, et al.
Published: (2026)

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
by: Song, Chull Hwan, et al.
Published: (2024)

StableMask: Refining Causal Masking in Decoder-only Transformer
by: Yin, Qingyu, et al.
Published: (2024)

TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
by: Xu, Boshen, et al.
Published: (2025)

Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation
by: Li, Yongkang, et al.
Published: (2024)

Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows
by: Wei, Lindsey Linxi, et al.
Published: (2024)

Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling
by: Kesgin, Himmet Toprak, et al.
Published: (2024)

From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
by: Xiao, Changming, et al.
Published: (2023)

Towards Robust Vision Transformer via Masked Adaptive Ensemble
by: Lin, Fudong, et al.
Published: (2024)

InstructOCR: Instruction Boosting Scene Text Spotting
by: Duan, Chen, et al.
Published: (2024)

Masking Causality and Conditional Dependence
by: Yang, Zou, et al.
Published: (2026)

Clustering in Causal Attention Masking
by: Karagodin, Nikita, et al.
Published: (2024)

Contextual Text Denoising with Masked Language Models
by: Sun, Yifu, et al.
Published: (2019)

Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs
by: Hu, HaoYuan, et al.
Published: (2024)

Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
by: Luo, Yifu, et al.
Published: (2025)

Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation
by: Young, Richard J.
Published: (2025)

Language-driven Grasp Detection with Mask-guided Attention
by: Van Vo, Tuan, et al.
Published: (2024)

Text-driven Human Motion Generation with Motion Masked Diffusion Model
by: Chen, Xingyu
Published: (2024)

OmniTry: Virtual Try-On Anything without Masks
by: Feng, Yutong, et al.
Published: (2025)

Scaling up Masked Diffusion Models on Text
by: Nie, Shen, et al.
Published: (2024)

MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation
by: Li, Changhao, et al.
Published: (2025)

Entropy-aware Masking for Masked Language Modeling
by: Srinivasagan, Gokul, et al.
Published: (2026)