Cover Image

Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Muzhi, Zhong, Hao, Zhao, Canyu, Du, Zongze, Huang, Zheng, Liu, Mingyu, Chen, Hao, Zou, Cheng, Chen, Jingdong, Yang, Ming, Shen, Chunhua
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
by: Li, Liyang, et al.
Published: (2026)

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

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

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

GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks
by: Chen, Cong, et al.
Published: (2025)

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
by: Zhao, Canyu, et al.
Published: (2024)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
by: Zhu, Wenxin, et al.
Published: (2025)

PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models
by: Chen, Jiangong, et al.
Published: (2026)

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

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

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

MARBLE: Multi-Aspect Reward Balance for Diffusion RL
by: Zhao, Canyu, et al.
Published: (2026)

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
by: Liu, Mingyu, et al.
Published: (2025)

Empowering Language Models with Active Inquiry for Deeper Understanding
by: Pang, Jing-Cheng, et al.
Published: (2024)

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

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

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models
by: Wang, Ziyue, et al.
Published: (2024)

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

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

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
by: Ding, Ganggui, et al.
Published: (2024)

Can Large Language Models Identify Authorship?
by: Huang, Baixiang, et al.
Published: (2024)

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

Reviving The Classics: Active Reward Modeling in Large Language Model Alignment
by: Shen, Yunyi, et al.
Published: (2025)

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
by: Zhang, Hongxiang, et al.
Published: (2025)

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
by: Dai, Muzhi, et al.
Published: (2025)

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
by: Chen, Cong, et al.
Published: (2025)

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

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

Intelligent Power Grid Design Review via Active Perception-Enabled Multimodal Large Language Models
by: Tan, Taoliang, et al.
Published: (2025)

Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception
by: Sun, Yanpeng, et al.
Published: (2024)

Active Visual Perception: Opportunities and Challenges
by: Li, Yian, et al.
Published: (2025)

LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
by: Duan, Yinglin, et al.
Published: (2025)

TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models
by: Zhou, Wenhao, et al.
Published: (2025)

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

Cramer-Rao Bound Optimization for Active RIS-Empowered ISAC Systems
by: Zhu, Qi, et al.
Published: (2023)

Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
by: Tang, Lv, et al.
Published: (2023)