Muzhi Zhu

5

Papers

23

Total Citations

Papers (5)

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

NeurIPS 2025arXiv

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

Unified Open-World Segmentation with Multi-Modal Prompts

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data

Generative Active Learning for Long-tailed Instance Segmentation