PPL
Jing Yang
Papers (4)
Efficient Multi-objective Prompt Optimization via Pure-exploration BanditsEnhancing Multilingual Counterfactual Generation through Alignment-as-Preference OptimizationGeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses