Georgios Chochlakis

large language model (3) multimodal learning (2) in-context learning (2) transfer learning (1) curriculum learning (1) object detection (1) preference alignment (1) multi-label classification (1) face recognition (1) automatic speech recognition (1) error detection (1) probability distribution (1) speaker diarization (1) video annotation (1) vision-language model (1) distribution alignment (1) masked autoencoder (1) missing modality (1) annotation quality (1) label correction (1)