Junxiang Wang

graph neural network (2) large language model (2) representation learning (2) preference learning (1) graph representation learning (1) prompt engineering (1) graph structure (1) reinforcement learning from human feedback (1) message passing (1) influence maximization (1) social network (1) reward model (1) end-to-end learning (1) human alignment (1) multi-agent system (1) seed set selection (1) automated alignment (1) edge difficulty (1) time series annotation (1) cross-domain annotation (1)