Imagen de Portada

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Xintong, Gao, Zhi, Zhang, Bofei, Li, Pengxiang, Zhang, Xiaowen, Liu, Yang, Yuan, Tao, Wu, Yuwei, Jia, Yunde, Zhu, Song-Chun, Li, Qing
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
por: Li, Pengxiang, et al.
Publicado: (2024)

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
por: Gao, Zhi, et al.
Publicado: (2024)

MIRROR: Multimodal Iterative Reasoning via Reflection on Visual Regions
por: Zhang, Haoyu, et al.
Publicado: (2026)

AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process
por: Zhang, Xintong, et al.
Publicado: (2026)

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
por: Li, Pengxiang, et al.
Publicado: (2025)

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
por: Li, Pengxiang, et al.
Publicado: (2025)

Long-Horizon Visual Imitation Learning via Plan and Code Reflection
por: Chen, Quan, et al.
Publicado: (2025)

GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
por: Shi, Chenrui, et al.
Publicado: (2025)

Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
por: Wu, Wei, et al.
Publicado: (2025)

Memory-Centric Embodied Question Answering
por: Zhai, Mingliang, et al.
Publicado: (2025)

Adaptive Model Ensemble for Continual Learning
por: Mao, Yuchuan, et al.
Publicado: (2025)

Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces
por: Li, Pengxiang, et al.
Publicado: (2025)

Multi-Sourced Compositional Generalization in Visual Question Answering
por: Li, Chuanhao, et al.
Publicado: (2025)

CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update
por: Gao, Zhi, et al.
Publicado: (2023)

A Set-to-Set Distance Measure in Hyperbolic Space
por: Li, Pengxiang, et al.
Publicado: (2025)

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
por: Yu, Peilin, et al.
Publicado: (2025)

Curvature Learning for Generalization of Hyperbolic Neural Networks
por: Fan, Xiaomeng, et al.
Publicado: (2025)

STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning
por: Zhang, Xiaowen, et al.
Publicado: (2026)

TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
por: Zhang, Bofei, et al.
Publicado: (2025)

Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search
por: Zhou, Yunqi, et al.
Publicado: (2025)

Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction
por: Chen, Xu, et al.
Publicado: (2026)

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
por: Ge, Yuyao, et al.
Publicado: (2025)

SCI-Reason: A Dataset with Chain-of-Thought Rationales for Complex Multimodal Reasoning in Academic Areas
por: Ma, Chenghao, et al.
Publicado: (2025)

Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation
por: Zhai, Mingliang, et al.
Publicado: (2025)

Hyperbolic Dual Feature Augmentation for Open-Environment
por: Yu, Peilin, et al.
Publicado: (2025)

Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
por: Fan, Xiaomeng, et al.
Publicado: (2025)

Fine-Grained 3D Facial Reconstruction for Micro-Expressions
por: Sun, Che, et al.
Publicado: (2026)

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
por: Chen, Shiqi, et al.
Publicado: (2025)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
por: Berman, Shmuel, et al.
Publicado: (2025)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
por: Zhang, Yichi, et al.
Publicado: (2026)

Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs
por: Yu, Jiaao, et al.
Publicado: (2025)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
por: Li, Xintong, et al.
Publicado: (2026)

3D Visual Illusion Depth Estimation
por: Yao, Chengtang, et al.
Publicado: (2025)

AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement
por: Pei, Siqi, et al.
Publicado: (2026)

Temporally Consistent Stereo Matching
por: Zeng, Jiaxi, et al.
Publicado: (2024)

Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
por: Li, Xintong, et al.
Publicado: (2025)

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
por: Li, Jiangyang, et al.
Publicado: (2026)

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
por: Cao, Jiajun, et al.
Publicado: (2025)

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
por: Li, Hanyu, et al.
Publicado: (2025)

VACoT: Rethinking Visual Data Augmentation with VLMs
por: Xu, Zhengzhuo, et al.
Publicado: (2025)