Papers by Runze Liu
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)
Copied to clipboard
Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou
| Challenge: | Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth. |
| Approach: | They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning. |
| Outcome: | The proposed framework outperforms existing methods on ICLR 2025 papers. |
Select Before Use: On the Importance of Reference Model Selection in Preference Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) is used as the initialization and reference model for subsequent preference alignment. |
| Approach: | They propose to use RewardRank to estimate initial implicit alignment between reference model and preference objective to ensure LLMs generate safe, helpful, and instruction-aligned content. |
| Outcome: | Empirical evidence shows that using the selected model as reference can gain up to 67.6% relative increase on length-controlled win rate compared to baselines. |
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs). |
| Approach: | They propose a framework that explicitly decouples FFN and Attention contributions via noise-induced causal interventions to capture model's internal fragility. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines in both uncertainty estimation and calibration while exhibiting superior cross-dataset generalization. |
VLP: Vision-Language Preference Learning for Embodied Manipulation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to reward engineering are time-consuming and expensive to collect human preference labels. |
| Approach: | They propose a vision-language preference learning framework which learns from human feedback . they define three types of language-conditioned preferences and construct a visual preference dataset . |
| Outcome: | The proposed framework outperforms baselines on embodied manipulation tasks and can be applied to other tasks. |