Peter Welinder

annotator modeling (2) probabilistic modeling (2) unsupervised clustering (1) bayesian inference (1) bayesian model (1) hierarchical clustering (1) language model alignment (1) crowdsourcing annotation (1) domain randomization (1) reinforcement learning from human feedback (1) instruction following (1) model alignment (1) off-policy learning (1) label aggregation (1) sim-to-real transfer (1) multi-annotator learning (1) semi-supervised learning (1) image categorization (1) crowdsourced clustering (1) reinforcement learning (1)