Scholar
Runze Liu
Google Scholar ID: LiIfGakAAAAJ
Tsinghua University
Citations & Impact
Citations
293
H-index
9
i10-index
8
Publications
18
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - One paper accepted by NeurIPS 2025
- - Two papers accepted by EMNLP 2025
- - One paper accepted by Reasoning and Planning for LLMs Workshop @ ICLR 2025
- - One paper accepted by ICLR 2025
- - One paper accepted by AAAI 2025 and selected for oral presentation (Top 4.6%)
- - One paper accepted by ICML 2024
- - One paper accepted by ICLR 2024
- - One paper accepted by NeurIPS 2022
- - Preprints:
- - Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
- - ASPO: Asymmetric Importance Sampling Policy Optimization
- - MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference
- - A Survey of Reinforcement Learning for Large Reasoning Models
- - Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- - Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Research Experience
- - Internship at Kuaishou, working with Jiakang Wang and Dr. Fuzheng Zhang
- - Internship at Shanghai AI Laboratory, working with Dr. Biqing Qi and Dr. Chenjia Bai
- - Internship at Peking University, working with Prof. Yali Du and Prof. Yaodong Yang
Education
- - Master's student at Tsinghua University, supervised by Prof. Xiu Li
- - Bachelor's degree with honors from Shandong University, June 2023
Background
- - Research Interests: Large Language Models (LLMs) and Reinforcement Learning (RL), particularly enhancing the reasoning capabilities of LLMs, long-horizon planning agents, and leveraging LLMs to improve RL algorithms.
- - Professional Field: Large Language Models, Multi-modal LLMs, Reinforcement Learning.
