Zhiyu Xue
10 papers · 2021–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) 🌍 Conference Polyglot (7) 🏃 Academic Marathon (5) 🌈 Renaissance Researcher (5)
🧭
Keyword Pioneer
🏃
Academic Marathon
(5)
🌈
Renaissance Researcher
(5)
🏆
Keyword Champion
(2)
💎
Century Club
(10)
🗃️
Keyword Collector
(51)
Conferences
ACL (2)
EACL (2)
AACL (1)
CVPR (1)
EMNLP (1)
IJCAI (1)
IJCNLP (1)
NAACL (1)
Top co-authors
Research topics
Keywords
large language model
(4)
moral reasoning
(2)
intrinsic self-correction
(2)
medical vision-language model
(2)
convex optimization
(1)
visual question answering
(1)
adversarial robustness
(1)
adversarial training
(1)
transfer learning
(1)
instruction following
(1)
ai safety
(1)
safety alignment
(1)
model uncertainty
(1)
communication efficiency
(1)
parameter-efficient fine-tuning
(1)
convergence analysis
(1)
data heterogeneity
(1)
supervised fine-tuning
(1)
synthetic demonstration
(1)
generalization bound
(1)
Papers
Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection
EACL 2026
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
EACL 2026
On the Convergence of Moral Self-Correction in Large Language Models
AACL 2025
Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models
ACL 2025
On the Convergence of Moral Self-Correction in Large Language Models
IJCNLP 2025
Smaller Large Language Models Can Do Moral Self-Correction
NAACL 2025
Initialization Matters for Adversarial Transfer Learning
CVPR 2024
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
ACL 2024
PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
EMNLP 2023
Differentially Private Pairwise Learning Revisited
IJCAI 2021