Xiaobo Hu
5 papers · 2021–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
Top co-authors
Research topics
Machine Learning
(4)
Reinforcement Learning
(3)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Artificial Intelligence
(2)
Applications · Reinforcement Learning
(2)
Core AI
(2)
Core Methods
(2)
Methods
(2)
Data Science & Analytics
(1)
Deep Learning
(1)
Applications · Data Science & Analytics
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
visual reinforcement learning
(2)
contrastive learning
(1)
reinforcement learning
(1)
sample efficiency
(1)
transfer learning
(1)
incremental learning
(1)
mutual information
(1)
normalizing flow
(1)
cross-domain generalization
(1)
recommender system
(1)
model update
(1)
sample reweighting
(1)
domain-invariant representation
(1)
policy consistency
(1)
image augmentation
(1)
overfitting prevention
(1)
latent dynamics model
(1)
video pre-training
(1)
incremental update
(1)
prediction performance
(1)
Papers
Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
CVPR 2026
How to Learn Domain-Invariant Representations for Visual Reinforcement Learning: An Information-Theoretical Perspective
IJCAI 2024
What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction
AAAI 2024
PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow
CVPR 2023
Preventing Overfitting via Sample Reweighting for Recommender System Incremental Update (Student Abstract)
AAAI 2021