3 papers
cs.AI2026
Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
Jiahua Yang, Zhiwei Yang, Xianpeng Zhang +7
Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods…
cs.AI2026
MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
Xianpeng Zhang, Jiahua Yang, Dongyu Chen +7
Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key info…
cs.AI2026
Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization
Dongyu Chen, Jian Ma, Xianpeng Zhang +5
Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally…