3 papers
cs.CL2025
Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries
Meiling Ning, Zhongbao Zhang, Junda Ye +2
The emergence of LM-based judging reward modeling, represented by generative reward models, has successfully made reinforcement learning from AI feedback (RLAIF) efficient and scal…
cs.LG2025
MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts
Junda Ye, Zhongbao Zhang, Li Sun +1
While graph neural networks (GNNs) have achieved great success in learning from graph-structured data, their reliance on local, pairwise message passing restricts their ability to…
cs.LG2025
CLEAR: Cluster-based Prompt Learning on Heterogeneous Graphs
Feiyang Wang, Zhongbao Zhang, Junda Ye +2
Prompt learning has attracted increasing attention in the graph domain as a means to bridge the gap between pretext and downstream tasks. Existing studies on heterogeneous graph pr…