Suchir Salhan

language model (3) small language model (2) representation learning (1) contrastive learning (1) zero-shot learning (1) cognitive modeling (1) curriculum learning (1) cross-lingual transfer (1) named entity recognition (1) multimodal learning (1) language model evaluation (1) model architecture (1) visual grounding (1) child-directed speech (1) multilingual pretraining (1) language acquisition (1) low-resource language (1) sparse autoencoder (1) multi-turn dialogue (1) context window (1)