Cover Image

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Seonghoon, Nam, Dongjun, Lee, Byung-Kwan, Son, Jeany
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
by: Yu, Seonghoon, et al.
Published: (2025)

Latent Expression Generation for Referring Image Segmentation and Grounding
by: Yu, Seonghoon, et al.
Published: (2025)

Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation
by: Yu, Seonghoon, et al.
Published: (2024)

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
by: Lee, Byung-Kwan, et al.
Published: (2025)

See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
by: Wu, Zhiheng, et al.
Published: (2026)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
by: Liu, Chengzhi, et al.
Published: (2025)

Seeing Culture: A Benchmark for Visual Reasoning and Grounding
by: Satar, Burak, et al.
Published: (2025)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
by: Xu, Haolei, et al.
Published: (2026)

Think Visually, Reason Textually: Vision-Language Synergy in ARC
by: Zhang, Beichen, et al.
Published: (2025)

Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
by: Guo, Ziyu, et al.
Published: (2025)

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

See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation
by: Hu, Chih Yao, et al.
Published: (2025)

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
by: Chen, Kaitao, et al.
Published: (2025)

Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
by: Lee, Chanhui, et al.
Published: (2025)

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
by: Xiao, Xin, et al.
Published: (2024)

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
by: Zhan, Qiusi, et al.
Published: (2025)

GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
by: Ebouky, Brown, et al.
Published: (2026)

Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning
by: Singh, Ayush, et al.
Published: (2024)

Chatting with Images for Introspective Visual Thinking
by: Wu, Junfei, et al.
Published: (2026)

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
by: Yu, Zhuoran, et al.
Published: (2025)

Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
by: Yu, Haorui, et al.
Published: (2025)

A Simple Baseline with Single-encoder for Referring Image Segmentation
by: Yu, Seonghoon, et al.
Published: (2024)

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

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
by: Liu, Tianhui, et al.
Published: (2026)

VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages
by: Atuhurra, Jesse, et al.
Published: (2025)

Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
by: Qu, Kevin, et al.
Published: (2026)

MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning
by: Kumar, Somnath, et al.
Published: (2024)

ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting
by: Mishra, Abhijit, et al.
Published: (2025)

GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks
by: Kang, Haoqiang, et al.
Published: (2025)

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
by: Hu, Wenbo, et al.
Published: (2025)

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
by: Zhang, Di, et al.
Published: (2024)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
by: Hu, Yushi, et al.
Published: (2023)

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
by: Xiao, Wenyi, et al.
Published: (2025)

Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning
by: Huang, Yihong, et al.
Published: (2026)

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
by: Li, Chengzu, et al.
Published: (2026)

Unbiased Visual Reasoning with Controlled Visual Inputs
by: Li, Zhaonan, et al.
Published: (2025)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
by: Yuan, Qianhao, et al.
Published: (2026)

On Data Synthesis and Post-training for Visual Abstract Reasoning
by: Zhu, Ke, et al.
Published: (2025)

Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
by: Cho, Beomsik, et al.
Published: (2025)

PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis
by: Lokesh, K, et al.
Published: (2026)