Nianbo Zeng — accepted AI-conference papers

2026

PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization

Xinxin Zhu, Ying He, Haowen Hou, Ruichong Zhang, Nianbo Zeng, Yulin Peng +2

AAAI 2026technical

Reinforcement Fine-tuning (RFT) methods such as Group Relative Policy Optimization (GRPO) have demonstrated strong capabilities in aligning Large Language Models with human preferences. However, these approaches often suffer from limited data efficiency, necessitating extensive on-policy rollouts to

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

SCENERAG: SCENE-LEVEL RETRIEVAL-AUGMENTED GENERATION FOR VIDEO UNDERSTANDING

Nianbo Zeng, Haowen Hou, Fei Yu, Si Shi, Ying He

ICASSP 2026poster

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches typically segment videos into fixed-length chunks, which of…

Cited by 0 Source ↗PDF ↗Scholar ↗