Muzhi Zhu
13 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (33) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π€ Dynamic Duo (13)
π
Triple Crown
π
Grand Slam
ποΈ
Keyword Collector
(68)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Deep Learning
(10)
Computer Vision
(9)
Machine Learning
(7)
Analysis
(7)
Artificial Intelligence
(6)
Learning Types Β· Deep Learning
(6)
Models
(5)
Core AI
(4)
Learning Types Β· Machine Learning
(4)
Architectures
(3)
Processing
(3)
Core Methods
(2)
Generation
(2)
Learning Paradigms
(2)
Reinforcement Learning
(1)
Keywords
in-context learning
(4)
semantic segmentation
(4)
multimodal large language model
(3)
image segmentation
(3)
reinforcement learning
(2)
few-shot learning
(2)
spatial reasoning
(2)
in-context segmentation
(2)
instance segmentation
(2)
generative model
(2)
image editing
(1)
feature matching
(1)
multimodal learning
(1)
visual reasoning
(1)
image restoration
(1)
markov decision process
(1)
data augmentation
(1)
deep learning
(1)
prompt learning
(1)
self-supervised learning
(1)
Papers
Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
CVPR 2026
Exploring Spatial Intelligence from a Generative Perspective
CVPR 2026
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
CVPR 2026
A Denoising Pre-training Framework for Accelerating Novel Material Discovery
AAAI 2025
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
CVPR 2025
Unified Open-World Segmentation with Multi-Modal Prompts
ICCV 2025
A Simple Image Segmentation Framework via In-Context Examples
NeurIPS 2024
De novo Protein Design Using Geometric Vector Field Networks
ICLR 2024
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
CVPR 2024
Generative Active Learning for Long-tailed Instance Segmentation
ICML 2024
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
ICLR 2024
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
NeurIPS 2024
SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning
ICCV 2023