Xiaoyue Mi
6 papers · 2021–2026 · 4 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
(20)
Top co-authors
Research topics
Keywords
diffusion model
(2)
contrastive learning
(1)
continual learning
(1)
catastrophic forgetting
(1)
image segmentation
(1)
benchmark evaluation
(1)
adversarial robustness
(1)
video generation
(1)
preference learning
(1)
visual appearance
(1)
image synthesis
(1)
image editing
(1)
context understanding
(1)
adversarial training
(1)
feature disentanglement
(1)
semantic space
(1)
disentangled representation
(1)
adversarial perturbation
(1)
reward hacking
(1)
reward model
(1)
Papers
SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
CVPR 2026
Visual-Friendly Concept Protection via Selective Adversarial Perturbations
AAAI 2026
Adversarial Robust Memory-Based Continual Learner
ICCV 2025
CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models
ACL 2024
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation
CVPR 2024
Progressive Domain Expansion Network for Single Domain Generalization
CVPR 2021