Cover Image

Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yanbei, Ma, Xueqi, Liu, Shu, Erfani, Sarah Monazam, Liu, Tongliang, Bailey, James, Lau, Jey Han, Ehinger, Krista A.
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
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)

Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
by: Ma, Xueqi, et al.
Published: (2026)

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

KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph
by: Jiang, Yanbei, et al.
Published: (2024)

PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning
by: Jiang, Yanbei, et al.
Published: (2025)

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
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)

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

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

Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
by: Hiller, Markus, et al.
Published: (2024)

Generalized Planning for the Abstraction and Reasoning Corpus
by: Lei, Chao, et al.
Published: (2024)

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

Evaluating Evidence Attribution in Generated Fact Checking Explanations
by: Xing, Rui, et al.
Published: (2024)

Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective
by: Truong, Thinh Hung, et al.
Published: (2025)

Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
by: Jiang, Yanbei, et al.
Published: (2026)

Decomposed Opinion Summarization with Verified Aspect-Aware Modules
by: Li, Miao, et al.
Published: (2025)

From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark
by: Lei, Chao, et al.
Published: (2025)

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

Sequential Amodal Segmentation via Cumulative Occlusion Learning
by: Ao, Jiayang, et al.
Published: (2024)

State-Based Disassembly Planning
by: Lei, Chao, et al.
Published: (2025)

Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise
by: Zhang, Zhenkai, et al.
Published: (2023)

Factual Dialogue Summarization via Learning from Large Language Models
by: Zhu, Rongxin, et al.
Published: (2024)

CMA-R:Causal Mediation Analysis for Explaining Rumour Detection
by: Tian, Lin, et al.
Published: (2024)

MoDEM: Mixture of Domain Expert Models
by: Simonds, Toby, et al.
Published: (2024)

Interaction Matters: An Evaluation Framework for Interactive Dialogue Assessment on English Second Language Conversations
by: Gao, Rena, et al.
Published: (2024)

REL: Working out is all you need
by: Simonds, Toby, et al.
Published: (2024)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
by: Shetty, Anudeex, et al.
Published: (2024)

Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
by: Gao, Shengxiang, et al.
Published: (2025)

A Sentiment Consolidation Framework for Meta-Review Generation
by: Li, Miao, 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)

GPSBench: Do Large Language Models Understand GPS Coordinates?
by: Truong, Thinh Hung, et al.
Published: (2026)

WHoW: A Cross-domain Approach for Analysing Conversation Moderation
by: Chen, Ming-Bin, et al.
Published: (2024)

Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG
by: Setiawan, David Samuel, et al.
Published: (2026)

CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics
by: Chen, Ming-Bin, et al.
Published: (2026)

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

Planning-Driven Programming: A Large Language Model Programming Workflow
by: Lei, Chao, et al.
Published: (2024)

On the Interplay between Human Label Variation and Model Fairness
by: Kurniawan, Kemal, et al.
Published: (2025)