Cover Image

Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Xueqi, Yang, Shuo, Jiang, Yanbei, Liu, Shu, Liu, Zhenzhen, Ao, Jiayang, Ma, Xingjun, Erfani, Sarah Monazam, Bailey, James
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
by: Ma, Xueqi, et al.
Published: (2025)

Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
by: Jiang, Yanbei, et al.
Published: (2025)

Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
by: Ma, Xueqi, et al.
Published: (2025)

Unlearnable Examples For Time Series
by: Jiang, Yujing, et al.
Published: (2024)

End-to-End Anti-Backdoor Learning on Images and Time Series
by: Jiang, Yujing, et al.
Published: (2024)

Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis
by: Ma, Xueqi, et al.
Published: (2025)

LDReg: Local Dimensionality Regularized Self-Supervised Learning
by: Huang, Hanxun, et al.
Published: (2024)

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
by: Huang, Hanxun, et al.
Published: (2025)

Detecting Backdoor Samples in Contrastive Language Image Pretraining
by: Huang, Hanxun, et al.
Published: (2025)

Efficient Neural Implicit Representation for 3D Human Reconstruction
by: Huang, Zexu, et al.
Published: (2024)

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles
by: Ma, Yiming, et al.
Published: (2026)

Open-World Amodal Appearance Completion
by: Ao, Jiayang, et al.
Published: (2024)

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
by: Jiang, Yanbei, et al.
Published: (2025)

AudioMosaic: Contrastive Masked Audio Representation Learning
by: Huang, Hanxun, et al.
Published: (2026)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
by: Wu, Zhenkai, et al.
Published: (2025)

Exploring Weak-to-Strong Generalization for CLIP-based Classification
by: Li, Jinhao, et al.
Published: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
by: Li, Jinhao, et al.
Published: (2024)

Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
by: Arcos-Holzinger, Sandra, et al.
Published: (2026)

The Role of Quantum Measurements when Testing the Quantum Nature of Gravity
by: Miki, Daisuke, et al.
Published: (2025)

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
by: Zhang, Wanyue, et al.
Published: (2026)

AIR: Post-training Data Selection for Reasoning via Attention Head Influence
by: Liu, Jinrui, et al.
Published: (2025)

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
by: Mou, Tingshu, et al.
Published: (2026)

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
by: Nam, Andrew, et al.
Published: (2025)

SafeCoT: Improving VLM Safety with Minimal Reasoning
by: Ma, Jiachen, et al.
Published: (2025)

VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion
by: Liu, Pei, et al.
Published: (2025)

SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
by: Zhang, Jian, et al.
Published: (2026)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
by: Li, Juncheng, et al.
Published: (2025)

When and Why Grouping Attention Heads Accelerates Muon Optimization
by: Zhang, Hongtao, et al.
Published: (2026)

MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique
by: Liu, Shuhang, et al.
Published: (2025)

On the Role of Attention Heads in Large Language Model Safety
by: Zhou, Zhenhong, et al.
Published: (2024)

VLM-UDMC: VLM-Enhanced Unified Decision-Making and Motion Control for Urban Autonomous Driving
by: Liu, Haichao, et al.
Published: (2025)

Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
by: Yu, Yongcan, et al.
Published: (2025)

Testing the quantum nature of gravity through interferometry
by: Liu, Yubao, et al.
Published: (2025)

Semiclassical gravity phenomenology under the causal-conditional quantum measurement prescription II: Heisenberg picture and apparent optical entanglement
by: Liu, Yubao, et al.
Published: (2024)

Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation
by: Fan, Hongxing, et al.
Published: (2025)

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

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
by: Chen, Boyuan, et al.
Published: (2024)

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
by: Wang, Ruofan, et al.
Published: (2025)

From Order to Distribution: A Spectral Characterization of Forgetting in Continual Learning
by: Xu, Zonghuan, et al.
Published: (2026)