Imagen de Portada

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Liyang, Zhu, Muzhi, Zhao, Zhiyue, Zhao, Hengyu, Liu, Ke, Zhong, Linhao, Chen, Hao, Shen, Chunhua
Formato:	Preprint
Publicado:	2026
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

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
por: Zhao, Canyu, et al.
Publicado: (2025)

MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
por: Li, Liyang, et al.
Publicado: (2026)

Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
por: Zhu, Muzhi, et al.
Publicado: (2025)

Generative Active Learning for Long-tailed Instance Segmentation
por: Zhu, Muzhi, et al.
Publicado: (2024)

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
por: Zhao, Canyu, et al.
Publicado: (2025)

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information
por: Di Giammarino, Luca, et al.
Publicado: (2024)

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
por: Zhong, Hao, et al.
Publicado: (2025)

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
por: Liu, Yang, et al.
Publicado: (2023)

GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
por: Ge, Yongtao, et al.
Publicado: (2024)

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
por: Xu, Guangkai, et al.
Publicado: (2024)

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
por: Zhu, Muzhi, et al.
Publicado: (2024)

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
por: Fan, Chengxiang, et al.
Publicado: (2024)

A Simple Image Segmentation Framework via In-Context Examples
por: Liu, Yang, et al.
Publicado: (2024)

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
por: Luo, Zekai, et al.
Publicado: (2025)

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
por: Jia, Yiduo, et al.
Publicado: (2026)

Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert
por: Liu, Mingyu, et al.
Publicado: (2025)

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
por: Zhu, Muzhi, et al.
Publicado: (2025)

NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
por: Huang, Zheng, et al.
Publicado: (2025)

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
por: Zhao, Jianfei, et al.
Publicado: (2025)

ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
por: Bai, Yifan, et al.
Publicado: (2023)

CanViT: Toward Active-Vision Foundation Models
por: Berreby, Yohaï-Eliel, et al.
Publicado: (2026)

Unified Open-World Segmentation with Multi-Modal Prompts
por: Liu, Yang, et al.
Publicado: (2025)

Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
por: Huang, Yinxuan, et al.
Publicado: (2024)

Exploring Spatial Intelligence from a Generative Perspective
por: Zhu, Muzhi, et al.
Publicado: (2026)

Token Warping Helps MLLMs Look from Nearby Viewpoints
por: Lee, Phillip Y., et al.
Publicado: (2026)

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
por: Gao, Zihui, et al.
Publicado: (2026)

LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
por: Fuller, Anthony, et al.
Publicado: (2025)

Pay Attention to Where You Looked
por: Berian, Alex, et al.
Publicado: (2026)

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
por: Chen, Cong, et al.
Publicado: (2025)

Hallucination Begins Where Saliency Drops
por: Zhang, Xiaofeng, et al.
Publicado: (2026)

LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models
por: Shen, Yuxiang, et al.
Publicado: (2026)

Can Foundation Models Revolutionize Mobile AR Sparse Sensing?
por: Zhao, Yiqin, et al.
Publicado: (2025)

Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation
por: Gu, Zejun, et al.
Publicado: (2024)

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
por: Zhu, Haoyi, et al.
Publicado: (2023)

Where do Large Vision-Language Models Look at when Answering Questions?
por: Xing, Xiaoying, et al.
Publicado: (2025)

Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
por: Li, Ouxiang, et al.
Publicado: (2024)

Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors
por: Hashimoto, Hiroki, et al.
Publicado: (2026)

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
por: Liao, Chao, et al.
Publicado: (2025)

Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
por: Michalkiewicz, Mateusz, et al.
Publicado: (2024)

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
por: Wu, Weijia, et al.
Publicado: (2023)