Junyi Zhu
11 papers · 2021–2026 · 7 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 ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (35) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver
π
Trend Setter
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(63)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(6)
Deep Learning
(5)
Application Areas
(4)
Learning Paradigms
(4)
Optimization & Theory Β· Deep Learning
(4)
Natural Language Processing
(3)
Core AI
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Optimization & Theory Β· Machine Learning
(3)
Applications
(2)
Models
(2)
Understanding
(2)
Computer Vision
(1)
Keywords
federated learning
(4)
parameter-efficient fine-tuning
(2)
model merging
(2)
named entity recognition
(2)
action recognition
(1)
variational inference
(1)
privacy attack
(1)
variance reduction
(1)
multi-task learning
(1)
expectation maximization
(1)
human pose estimation
(1)
3d human reconstruction
(1)
adversarial training
(1)
instruction following
(1)
prompt learning
(1)
text classification
(1)
efficient inference
(1)
reinforcement learning from human feedback
(1)
transfer learning
(1)
robust optimization
(1)
Papers
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
ACL 2026
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
WACV 2026
Adversarial Preference Learning for Robust LLM Alignment
ACL 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
ICLR 2025
Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
EMNLP 2025
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
EMNLP 2024
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures
CVPR 2024
Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training
ICCV 2023
Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization
CVPR 2023
Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning
ICML 2023
R-GAP: Recursive Gradient Attack on Privacy
ICLR 2021