Yunfang Wu
Scholar

Yunfang Wu

Google Scholar ID: d1YlKkAAAAAJ
Peking University
NLP
Google Scholar↗
Citations & Impact
All-time
Citations
954
 
H-index
17
 
i10-index
30
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
21 items
Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents
2026
Cited
0
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
2026
Cited
1
SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation
arXiv.org · 2026
Cited
1
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
arXiv.org · 2026
Cited
0
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
2025
Cited
0
Think Outside the Policy: In-Context Steered Policy Optimization
2025
Cited
0
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
2025
Cited
0
Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)