Cover Image

Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Hao, Wang, Fei, Chen, Junjie, Nie, Yiqi, Zhao, Jiaqi, Li, Qiankun, Huang, Subin
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

UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
by: Ni, Shuo, et al.
Published: (2026)

TIR-Flow: Active Video Search and Reasoning with Frozen VLMs
by: Jin, Hongbo, et al.
Published: (2026)

Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
by: Xia, Jiaer, et al.
Published: (2025)

Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
by: Sun, Xiaoxiao, et al.
Published: (2026)

3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
by: Zheng, Xinye, et al.
Published: (2026)

Training-Free Multimodal Deepfake Detection via Graph Reasoning
by: Liu, Yuxin, et al.
Published: (2025)

Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
by: Shi, Chufan, et al.
Published: (2026)

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
by: Li, Sifan, et al.
Published: (2025)

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
by: Guo, Yufei, et al.
Published: (2024)

TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
by: Guo, Chaohong, et al.
Published: (2025)

ApET: Approximation-Error Guided Token Compression for Efficient VLMs
by: Ma, Qiankun, et al.
Published: (2026)

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
by: Ge, Yuyao, et al.
Published: (2025)

Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction
by: Liu, Yanjiao, et al.
Published: (2026)

Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
by: Wu, Jingze, et al.
Published: (2026)

Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs
by: Liu, Yuxin, et al.
Published: (2026)

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
by: Zhu, Lei, et al.
Published: (2024)

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
by: Zhang, Xintong, et al.
Published: (2025)

Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
by: Elmansoury, Sary, et al.
Published: (2025)

VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
by: Törtei, Brigitta Malagurski, et al.
Published: (2025)

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
by: Wang, Yining, et al.
Published: (2024)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
by: Berman, Shmuel, et al.
Published: (2025)

Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning
by: Park, Subin, et al.
Published: (2026)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
by: Lin, Jiaping, et al.
Published: (2026)

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
by: Huang, Ting, et al.
Published: (2025)

Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
by: Zha, Junli, et al.
Published: (2026)

From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
by: Wang, Changpeng, et al.
Published: (2025)

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
by: Guo, Garvin, et al.
Published: (2026)

VRIQ: Benchmarking and Analyzing Visual-Reasoning IQ of VLMs
by: Khezresmaeilzadeh, Tina, et al.
Published: (2026)

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
by: Guo, Xiefan, et al.
Published: (2025)

MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal
by: Nie, Yiqi, et al.
Published: (2026)

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
by: Park, Simon, et al.
Published: (2025)

Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators
by: Lunia, Harsh
Published: (2024)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
by: Tu, Jinzhe, et al.
Published: (2026)

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

Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning
by: Tekin, Selim Furkan, et al.
Published: (2026)

ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs
by: Gao, Yiling, et al.
Published: (2026)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
by: Li, Yiwei, et al.
Published: (2026)

ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
by: Lyu, Kailin, et al.
Published: (2025)

3D Visual Illusion Depth Estimation
by: Yao, Chengtang, et al.
Published: (2025)