Image de couverture de livre

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Garvin, Chen, Yu, Wang, Xiang, Li, Shuai, Zhao, Xinpei, Liu, Huaxing, Dong, Shuai
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
par: Guo, Garvin, et autres
Publié: (2026)

Monet: Reasoning in Latent Visual Space Beyond Images and Language
par: Wang, Qixun, et autres
Publié: (2025)

Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimuli
par: Chen, Chenglizhao, et autres
Publié: (2026)

Dual Latent Memory for Visual Multi-agent System
par: Yu, Xinlei, et autres
Publié: (2026)

MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
par: Xi, Suyang, et autres
Publié: (2026)

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
par: Guo, Guangfu, et autres
Publié: (2026)

LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
par: Hao, Haihong, et autres
Publié: (2026)

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
par: Yang, Zeyuan, et autres
Publié: (2025)

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
par: Guo, Ziyu, et autres
Publié: (2026)

DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder
par: Liu, Tao, et autres
Publié: (2023)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
par: Che, Liwei, et autres
Publié: (2026)

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
par: Wu, Linquan, et autres
Publié: (2026)

CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
par: Zhang, Yang, et autres
Publié: (2026)

Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
par: Xue, Qiyao, et autres
Publié: (2025)

Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
par: Li, Zejun, et autres
Publié: (2025)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
par: Li, Qiaoru, et autres
Publié: (2026)

Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning
par: Xu, Yu, et autres
Publié: (2026)

Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
par: Xu, Haoran, et autres
Publié: (2026)

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
par: Shi, Fan, et autres
Publié: (2025)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
par: Liu, Jiahang, et autres
Publié: (2025)

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
par: Zhu, Chunzheng, et autres
Publié: (2026)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
par: Li, Yiwei, et autres
Publié: (2026)

Exploring Visual Prompting: Robustness Inheritance and Beyond
par: Li, Qi, et autres
Publié: (2025)

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
par: Dong, Shuai, et autres
Publié: (2025)

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
par: Ge, Yuyao, et autres
Publié: (2025)

Unbiased Visual Reasoning with Controlled Visual Inputs
par: Li, Zhaonan, et autres
Publié: (2025)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
par: Yu, Mingyu, et autres
Publié: (2026)

SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets
par: Wan, Shenghua, et autres
Publié: (2024)

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
par: Huang, Siyuan, et autres
Publié: (2026)

CorrDetail: Visual Detail Enhanced Self-Correction for Face Forgery Detection
par: Zhou, Binjia, et autres
Publié: (2025)

Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relations
par: Li, Chengtai, et autres
Publié: (2026)

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
par: Jiang, Yanbei, et autres
Publié: (2025)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
par: Zhang, Qizhe, et autres
Publié: (2024)

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
par: Xie, Hongxia, et autres
Publié: (2024)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
par: Xue, Haotian, et autres
Publié: (2025)

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
par: Tian, Changyuan, et autres
Publié: (2026)

Enhancing Advanced Visual Reasoning Ability of Large Language Models
par: Li, Zhiyuan, et autres
Publié: (2024)

Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models
par: Chen, Yan, et autres
Publié: (2025)

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
par: Dong, Zhuobai, et autres
Publié: (2025)

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
par: Huang, Chi-Pin, et autres
Publié: (2025)