Feng Luo

reward modeling (2) 3d reconstruction (1) finite difference (1) feature matching (1) principal component analysis (1) knowledge distillation (1) cross-lingual transfer (1) multimodal learning (1) backdoor attack (1) semantic representation (1) semantic alignment (1) neural network optimization (1) reinforcement learning from human feedback (1) model alignment (1) contrastive learning (1) differentiable programming (1) surface registration (1) riemannian metric (1) representation learning (1) dimensionality reduction (1)