Muzhi Zhu

Orcid: 0009-0001-3243-2356

According to our database1, Muzhi Zhu authored at least 16 papers between 2014 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO.
CoRR, May, 2025

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration.
CoRR, May, 2025

Masked Channel Modeling for Bootstrapping Visual Pre-training.
Int. J. Comput. Vis., February, 2025

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks.
CoRR, February, 2025

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

A Denoising Pre-training Framework for Accelerating Novel Material Discovery.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

A Simple Image Segmentation Framework via In-Context Examples.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Unveiling Universal Forensics of Diffusion Models with Adversarial Perturbations.
Proceedings of the International Joint Conference on Neural Networks, 2024

Generative Active Learning for Long-tailed Instance Segmentation.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

De novo Protein Design Using Geometric Vector Field Networks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2016
Hybrid-loop servo control system of double toggle mechanical press for flexible forming process based on sliding mode control and neural network techniques.
J. Syst. Control. Eng., 2016

2014
An angle measurement system for bending machine based on binocular active vision.
Proceedings of the 11th IEEE International Conference on Control & Automation, 2014


  Loading...