Get started
Author

Shaohang Wei

Observed name: Wei, Shaohang
Institution: Peking University
Observed institution: Peking University
OpenAlex ID: A5122981518
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
2026 · Meng, Haoming, Huang, Kexin, et al. · arXiv (Cornell University) · 19
PDF
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
2026 · Yu, Wenhao, Wei, Shaohang, et al. · arXiv (Cornell University) · 10
PDF
Mitigating Overthinking through Reasoning Shaping
2025 · Song, Feifan, Wei, Shaohang, et al. · arXiv (Cornell University) · 4
PDF
Verifier-Induced Support Reshaping in On-Policy Optimization
2026 · Wei, Shaohang, Su, Zikun, et al. · arXiv (Cornell University) · 1
PDF
Experience Augmented Policy Optimization for LLM Reasoning
2026 · Lu, Jinda, Huang, Kexin, et al. · arXiv (Cornell University) · 1
PDF
CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
2026 · Yu, Wenhao, Wang, Zhengcheng, et al. · arXiv (Cornell University)
PDF
On-Policy Visual Evidence Distillation
2026 · Wei, Shaohang, Song, Feifan, et al. · arXiv (Cornell University)
PDF
SWE-Ext: Scaling and Extending Augmented Data for Mid-Training of Repository-Level Coding Tasks
2026 · Wei Li, Xin Zhang, et al. · IEEE International Conference on Software Maintenance (ICSM)
One-Way Policy Optimization for Self-Evolving LLMs
2026 · Yang, Shuo, Lu, Jinda, et al. · arXiv (Cornell University)
PDF
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
2026 · Luo, Wen, Peng, Guangyue, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 34
H-index: 3
I10-index: 2
Year
Topic
Type