Igor Kiselev

large language model (2) policy optimization (1) variational inference (1) belief propagation (1) probabilistic inference (1) uncertainty quantification (1) self-supervised learning (1) supervised learning (1) instruction following (1) entropy approximation (1) partially observable markov decision process (1) bayesian network (1) graphical model (1) latent action (1) object-centric learning (1) hallucination detection (1) out-of-domain generalization (1) attention map (1) continued pre-training (1) bilingual model (1)