Jiahui Li

large language model (7) reinforcement learning (3) reinforcement learning from human feedback (2) multi-agent reinforcement learning (2) diffusion model (2) credit assignment (2) annotation variance (2) prompt brittleness (2) text classification (2) prompt engineering (2) causal inference (2) 3d vision (1) interactive learning (1) text-to-image generation (1) multimodal learning (1) text annotation (1) policy optimization (1) mutual information (1) speech recognition (1) model alignment (1)