Zhenqi He

representation learning (1) reinforcement learning (1) self-supervised learning (1) cross-lingual transfer (1) category discovery (1) hierarchical structure (1) prompting strategy (1) beam search (1) process reward (1) generalized category discovery (1) hyperbolic embedding (1) hyperbolic space (1) mathematical modeling (1) process reward model (1) text-to-sql generation (1) tree of thought (1) open-world learning (1) spherical projection (1) large language model (1) multilingual prompting (1)