Junfeng Fang
Scholar

Junfeng Fang

Google Scholar ID: beNNywsAAAAJ
National University of Singapore
Model EditingAI SafetyLLM ExplainabilityAI4Science
Google Scholar↗
Citations & Impact
All-time
Citations
807
 
H-index
16
 
i10-index
19
 
Publications
20
 
Co-authors
8
list available
Contact
No contact links provided.
Publications
69 items
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
2026
Cited
0
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
2026
Cited
0
PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates
2026
Cited
0
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
2026
Cited
0
Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents
2026
Cited
0
Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data
2026
Cited
0
Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation
2026
Cited
0
Unified Context Evolution for LLM Agents
2026
Cited
0
Resume (English only)
Co-authors
8 total
Xiang Wang
Xiang Wang
University of Science and Technology of China
Xiangnan He
Xiangnan He
University of Science and Technology of China
Tat-Seng Chua
Tat-Seng Chua
National University of Singapore
Baolong Bi
Baolong Bi
University of Chinese Academy of Sciences
Kun Wang @ NTU
Kun Wang @ NTU
Nanyang Technological University
Liu, Zhiyuan
Liu, Zhiyuan
Research Fellow, National University of Singapore
Zemin Liu
Zemin Liu
Zhejiang University
Yongduo Sui
Yongduo Sui
Tencent