Zhenpeng Su

Venues

Frequent coauthors

Papers

1. CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
   ACL 2026 · Zhenpeng Su
2. Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
   ACL 2026 · Zhenpeng Su
3. Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
   ACL 2026 ·

   Tiehua Mei

   DBLP profile ↗ORCID search ↗
4. CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
   NAACL 2025 · Zhenpeng Su
5. DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
   EMNLP 2025 ·

   Minxuan Lv

   DBLP profile ↗ORCID search ↗
6. Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal
   AAAI 2025 ·

   Haoran Lian

   DBLP profile ↗ORCID search ↗
7. Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
   AAAI 2025 ·

   Guangyuan Ma

   DBLP profile ↗ORCID search ↗
8. Temporal Scaling Law for Large Language Models
   EMNLP 2025 ·

   Yizhe Xiong

   DBLP profile ↗ORCID search ↗
9. Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
   NAACL 2024 · Zhenpeng Su
10. MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
    NAACL 2024 · Zhenpeng Su