Papers by Xiaokun Sun
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)
Copied to clipboard
Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun
| Challenge: | Existing approaches to safety alignment of large language models rely on costly manual annotations or human review. |
| Approach: | They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation. |
| Outcome: | The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability. |
MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction (2026.acl-long)
Copied to clipboard
| Challenge: | Recent research has attempted to transfer reinforcement learning paradigms to Video Large Language Models (MLLMs) but these methods lack explicit supervision for intrinsic temporal coherence and inter-frame correlations. |
| Approach: | They propose a novel post-training objective: Masked Video Prediction (MVP) that requires the model to reconstruct a masked continuous segment from a set of challenging distractors and employs Group Relative Policy Optimization (GRPO) with a fine-grained reward function to enhance the model's understanding of video context and temporal properties. |
| Outcome: | The proposed model improves video reasoning capabilities by reinforcing temporal reasoning and causal understanding. |