QINGSONG LIU

large language model (3) regret bound (2) causal inference (2) domain adaptation (1) facial landmark detection (1) bayesian inference (1) few-shot learning (1) in-context learning (1) visual reasoning (1) talking head generation (1) upper confidence bound (1) decision rule optimization (1) gradient optimization (1) attentional mechanisms (1) multi-armed bandit (1) self-supervised learning (1) reinforcement learning (1) graphical model (1) linear constraint (1) unsupervised learning (1)