Cover Image

Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Jingcheng, Xiong, Tianhu, Qian, Shengyi, Nahrstedt, Klara, Wu, Mingyuan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding Counting Mechanisms in Large Language and Vision-Language Models
by: Hasani, Hosein, et al.
Published: (2025)

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
by: Yeh, Chun-Hsiao, et al.
Published: (2026)

Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
by: Zhan, Yufei, et al.
Published: (2025)

Multi-Object Hallucination in Vision-Language Models
by: Chen, Xuweiyi, et al.
Published: (2024)

Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videos
by: Tiwari, Aditi, et al.
Published: (2025)

TraceNet: Segment one thing efficiently
by: Wu, Mingyuan, et al.
Published: (2024)

UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models
by: Pi, Xinyu, et al.
Published: (2024)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
by: Wu, Junfei, et al.
Published: (2025)

Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism
by: Chen, Tao, et al.
Published: (2026)

EventVL: Understand Event Streams via Multimodal Large Language Model
by: Li, Pengteng, et al.
Published: (2025)

Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning
by: Zhang, Jinxu
Published: (2024)

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
by: Zhang, Jieyu, et al.
Published: (2024)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
by: Wang, Jiaqi, et al.
Published: (2025)

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
by: Chen, Pingyi, et al.
Published: (2025)

Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA
by: Song, Python, et al.
Published: (2025)

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
by: Kou, Qian, et al.
Published: (2026)

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model
by: Ji, Yatai, et al.
Published: (2024)

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation
by: Zhang, Jihai, et al.
Published: (2025)

Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
by: Xu, Wanting, et al.
Published: (2024)

SoccerMaster: A Vision Foundation Model for Soccer Understanding
by: Yang, Haolin, et al.
Published: (2025)

Check Field Detection Agent (CFD-Agent) using Multimodal Large Language and Vision Language Models
by: Halder, Sourav, et al.
Published: (2025)

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

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
by: Wu, Zhiyu, et al.
Published: (2024)

Review of Hallucination Understanding in Large Language and Vision Models
by: Ho, Zhengyi, et al.
Published: (2025)

Environmental Understanding Vision-Language Model for Embodied Agent
by: Bang, Jinsik, et al.
Published: (2026)

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
by: Yin, Jianghao, et al.
Published: (2026)

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
by: Dong, Xinpeng, et al.
Published: (2026)

Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
by: Kim, Keuntae, et al.
Published: (2026)

Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset
by: Chen, Qian, et al.
Published: (2026)

Jailbreaks on Vision Language Model via Multimodal Reasoning
by: Noheria, Aarush, et al.
Published: (2026)

Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
by: Wang, Yizhou, et al.
Published: (2025)

UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation
by: Zhao, Xiangyu, et al.
Published: (2024)

PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis
by: Hua, Shengyi, et al.
Published: (2025)

MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image
by: Song, Shezheng, et al.
Published: (2024)

ACT360: An Efficient 360-Degree Action Detection and Summarization Framework for Mission-Critical Training and Debriefing
by: Tiwari, Aditi, et al.
Published: (2025)

Adapting Vision-Language Models for E-commerce Understanding at Scale
by: Nulli, Matteo, et al.
Published: (2026)

In-Context Learning Improves Compositional Understanding of Vision-Language Models
by: Nulli, Matteo, et al.
Published: (2024)

RAU: Reference-based Anatomical Understanding with Vision Language Models
by: Li, Yiwei, et al.
Published: (2025)

Pseudo Dataset Generation for Out-of-Domain Multi-Camera View Recommendation
by: Lee, Kuan-Ying, et al.
Published: (2024)

DentVLM: A Multimodal Vision-Language Model for Comprehensive Dental Diagnosis and Enhanced Clinical Practice
by: Meng, Zijie, et al.
Published: (2025)