Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Yanbei, Ma, Xueqi, Liu, Shu, Erfani, Sarah Monazam, Liu, Tongliang, Bailey, James, Lau, Jey Han, Ehinger, Krista A.
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

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

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

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

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

Unlearnable Examples For Time Series
por: Jiang, Yujing, et al.
Publicado: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

State-Based Disassembly Planning
por: Lei, Chao, et al.
Publicado: (2025)

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

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

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

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

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

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

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

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

A Sentiment Consolidation Framework for Meta-Review Generation
por: Li, Miao, et al.
Publicado: (2024)

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

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

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

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

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

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

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

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