Junxiao Wang
8 papers · 2022–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(4)
Machine Learning
(4)
Learning Types · Machine Learning
(2)
Models
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Application Areas
(1)
Core Methods
(1)
Generation · Computer Vision
(1)
Generation · Natural Language Processing
(1)
Learning Types · Deep Learning
(1)
Techniques
(1)
Keywords
diffusion model
(2)
multimodal learning
(2)
large language model
(2)
vision-language model
(2)
federated learning
(2)
test-time adaptation
(1)
human-robot interaction
(1)
data heterogeneity
(1)
autonomous agent
(1)
modality imbalance
(1)
long-tailed distribution
(1)
gradient inversion
(1)
concept bottleneck model
(1)
classifier calibration
(1)
dialogue system
(1)
defense mechanism
(1)
model stability
(1)
procedural learning
(1)
gradient matching
(1)
mixed reality
(1)
Papers
FedCART: Tackling Long-Tailed Distributions in Federated Adversarial Training via Classifier Refinement
CVPR 2026
Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
EMNLP 2025
Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
ACL 2024
Faithful Vision-Language Interpretation via Concept Bottleneck Models
ICLR 2024
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
NeurIPS 2024
PMR: Prototypical Modal Rebalance for Multimodal Learning
CVPR 2023
Towards Test-Time Refusals via Concept Negation
NeurIPS 2023
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
IJCAI 2022