Image de couverture de livre

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhong, Hao, Zhu, Muzhi, Du, Zongze, Huang, Zheng, Zhao, Canyu, Liu, Mingyu, Wang, Wen, Chen, Hao, Shen, Chunhua
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
par: Zhu, Muzhi, et autres
Publié: (2025)

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
par: Jia, Yiduo, et autres
Publié: (2026)

NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
par: Huang, Zheng, et autres
Publié: (2025)

Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert
par: Liu, Mingyu, et autres
Publié: (2025)

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
par: Zhao, Canyu, et autres
Publié: (2025)

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
par: Luo, Zekai, et autres
Publié: (2025)

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
par: Zhao, Canyu, et autres
Publié: (2024)

Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning
par: Zhang, Zhicheng, et autres
Publié: (2026)

MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
par: Li, Liyang, et autres
Publié: (2026)

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
par: Li, Liyang, et autres
Publié: (2026)

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
par: Oh, Yeongtak, et autres
Publié: (2026)

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

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
par: Liu, Mingyu, et autres
Publié: (2025)

A Simple Image Segmentation Framework via In-Context Examples
par: Liu, Yang, et autres
Publié: (2024)

Generative Active Learning for Long-tailed Instance Segmentation
par: Zhu, Muzhi, et autres
Publié: (2024)

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
par: Ding, Ganggui, et autres
Publié: (2024)

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
par: Liu, Yang, et autres
Publié: (2023)

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
par: Fan, Chengxiang, et autres
Publié: (2024)

MARBLE: Multi-Aspect Reward Balance for Diffusion RL
par: Zhao, Canyu, et autres
Publié: (2026)

Scaling Language-Centric Omnimodal Representation Learning
par: Xiao, Chenghao, et autres
Publié: (2025)

R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning
par: Zhao, Jiaxing, et autres
Publié: (2025)

Exploring Spatial Intelligence from a Generative Perspective
par: Zhu, Muzhi, et autres
Publié: (2026)

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
par: Tao, Keda, et autres
Publié: (2025)

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
par: Liang, Yongyuan, et autres
Publié: (2025)

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
par: Zhu, Muzhi, et autres
Publié: (2025)

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
par: Zhu, Muzhi, et autres
Publié: (2024)

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
par: Chen, Cong, et autres
Publié: (2025)

MIRG-RL: Multi-Image Reasoning and Grounding with Reinforcement Learning
par: Zheng, Lihao, et autres
Publié: (2025)

Unified Open-World Segmentation with Multi-Modal Prompts
par: Liu, Yang, et autres
Publié: (2025)

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning
par: Zhao, Baining, et autres
Publié: (2025)

Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
par: Ying, Kaining, et autres
Publié: (2025)

Active Perception Agent for Omnimodal Audio-Video Understanding
par: Tao, Keda, et autres
Publié: (2025)

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
par: Zhou, Heng, et autres
Publié: (2026)

Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning
par: Hao, Pengfei, et autres
Publié: (2025)

OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
par: Zhu, Boyu, et autres
Publié: (2025)

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
par: Wang, Xiaodong, et autres
Publié: (2026)

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
par: Guan, Yiran, et autres
Publié: (2026)

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
par: Tao, Keda, et autres
Publié: (2026)

OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
par: Yang, Zhengwei, et autres
Publié: (2026)

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
par: Wang, Hanqing, et autres
Publié: (2025)