Beijing

Zhenpeng Su

Intermediate
@suu990901

Researcher @ Kuaishou | M.E. @ UCAS​ | Focus on ​​LLM Reasoning & Mixture-of-Experts

scholar.google.com/citations?user=KVOZPeIAAAAJ&hl=zh-CN

KlearReasoner. Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

82

LLaMA-MiLe-Loss. Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models

68

chatgpt-comparison-detection-HC3-Plus. Code for HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus

7

Dial-MAE. Code for Dial-MAE:ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems

6

ARPO. The official code of “Agentic Reinforced Policy Optimization”, an agentic RL algorithm optimization.

1
5
Apply