Junkang Wu
Scholar

Junkang Wu

Google Scholar ID: deBwV5oAAAAJ
University of Science and Technology of China
llmcontrastive learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
466
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
9
list available
Contact
No contact links provided.
Publications
23 items
Know When to Stop, Where to Restart: Accelerating Multi-Turn Agentic On-Policy Distillation
2026
Cited
0
PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment
2026
Cited
0
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
2026
Cited
0
Experience Augmented Policy Optimization for LLM Reasoning
2026
Cited
0
R^2-Mem: Reflective Experience for Memory Search
2026
Cited
0
Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR
2026
Cited
0
Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs
2026
Cited
0
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
2026
Cited
0
Resume (English only)
Co-authors
9 total
Xiangnan He
Xiangnan He
University of Science and Technology of China
Jiancan Wu
Jiancan Wu
University of Science and Technology of China
Xiang Wang
Xiang Wang
University of Science and Technology of China
Wentao Shi
Wentao Shi
University of Science and Technology of China
Zhengyi Yang
Zhengyi Yang
PhD Student, University of Science and Technology of China
Xue Wang
Xue Wang
DAMO Academy, Alibaba
Yuexiang Xie
Yuexiang Xie
Alibaba Group
Kexin Huang
Kexin Huang
University of Science and Technology of China