Alon Benhaim

transformer architecture (1) reinforcement learning (1) direct preference optimization (1) cross-lingual transfer (1) question answering (1) language modeling (1) preference optimization (1) multimodal learning (1) hyperparameter tuning (1) k-nearest neighbor (1) language model (1) foundation model (1) scaling law (1) context length (1) model scaling (1) length extrapolation (1) position embedding (1) language model fine-tuning (1) model initialization (1) multilingual language model (1)