PPL
Jian Wang
Papers (7)
Global Policy-Space Response Oracles for Two-Player Zero-Sum GamesProbing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic StylisticsLATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM GenerationFFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar ReconstructionGood Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your WeightsGradient-Free Noise Optimization for Reward Alignment in Generative ModelsEnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation