Imagen de Portada

Sparse Visual Thought Circuits in Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Zhou, Yunpeng
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Agents
por: Zhou, Yunpeng
Publicado: (2026)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
por: Che, Liwei, et al.
Publicado: (2026)

ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
por: Liu, Xiwei, et al.
Publicado: (2026)

Balanced Thinking: Improving Chain of Thought Training in Vision Language Models
por: Perek, Shaked, et al.
Publicado: (2026)

Language Model Circuits Are Sparse in the Neuron Basis
por: Arora, Aryaman, et al.
Publicado: (2026)

A Resource-Rational Principle for Modeling Visual Attention Control
por: Bai, Yunpeng
Publicado: (2026)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
por: Zhao, Qingqing, et al.
Publicado: (2025)

Moving Pictures of Thought: Extracting Visual Knowledge in Charles S. Peirce's Manuscripts with Vision-Language Models
por: Pedretti, Carlo Teo, et al.
Publicado: (2025)

VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
por: Zhang, Haoran, et al.
Publicado: (2025)

AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
por: Wen, Yibin, et al.
Publicado: (2025)

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
por: Zhou, Qiji, et al.
Publicado: (2024)

VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models
por: Lim, Hyesu, et al.
Publicado: (2026)

CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution
por: Ren, Tianchi, et al.
Publicado: (2025)

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
por: Wu, Jialin, et al.
Publicado: (2026)

Sparse Probabilistic Graph Circuits
por: Rektoris, Martin, et al.
Publicado: (2025)

Visual Distraction Undermines Moral Reasoning in Vision-Language Models
por: Yang, Xinyi, et al.
Publicado: (2026)

ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
por: Chen, Xiaoshu, et al.
Publicado: (2026)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
por: Marks, Samuel, et al.
Publicado: (2024)

Structural Instability of Feature Composition
por: Zhou, Yunpeng
Publicado: (2026)

GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models
por: Shi, Nannan, et al.
Publicado: (2025)

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
por: Pang, Rock Yuren, et al.
Publicado: (2025)

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
por: Yang, Yankai, et al.
Publicado: (2026)

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
por: Shen, Xu, et al.
Publicado: (2026)

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
por: Tian, Xinyu, et al.
Publicado: (2025)

CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt
por: Islam, Md Touhidul, et al.
Publicado: (2026)

Synthesizing Visual Concepts as Vision-Language Programs
por: Wüst, Antonia, et al.
Publicado: (2025)

Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
por: Jin, Xinchen, et al.
Publicado: (2026)

Modeling Language as a Sequence of Thoughts
por: Borazjanizadeh, Nasim, et al.
Publicado: (2025)

Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation
por: Gao, Yunpeng, et al.
Publicado: (2024)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
por: Chen, Xi, et al.
Publicado: (2025)

Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability
por: Zhou, Lijie
Publicado: (2026)

Pixelis: Reasoning in Pixels, from Seeing to Acting
por: Zhou, Yunpeng
Publicado: (2026)

Thought of Search: Planning with Language Models Through The Lens of Efficiency
por: Katz, Michael, et al.
Publicado: (2024)

Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
por: Yang, Hao, et al.
Publicado: (2024)

Universe of Thoughts: Enabling Creative Reasoning with Large Language Models
por: Suzuki, Yuto, et al.
Publicado: (2025)

ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
por: Zhou, Yuhao, et al.
Publicado: (2026)

SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
por: Liu, Yuhuan, et al.
Publicado: (2026)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
por: Li, Qing, et al.
Publicado: (2025)

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
por: Merler, Matteo, et al.
Publicado: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
por: Ye, Jiacheng, et al.
Publicado: (2024)