Martin Q. Ma

Deep Learning (4) Machine Learning (4) Core Methods (4) Learning Types · Machine Learning (4) Artificial Intelligence (3) Core AI (3) Computer Vision (1) Architectures (1) Generation (1) Learning Types · Deep Learning (1) Models (1) Techniques (1)

representation learning (4) self-supervised learning (3) large vision-language model (2) contrastive learning (2) mutual information (2) supervised fine-tuning (1) hallucination mitigation (1) multimodal representation (1) masked autoencoder (1) video reasoning (1) contrastive decoding (1) kernel methods (1) generative feedback (1) frame generation (1) hierarchical latent variable model (1) text-to-visual entropy (1) real-time deployment (1) conditional contrastive learning (1) fair contrastive learning (1) hallucinations (1)