Younesse Kaddar

LLM uncertainty quantification · Bayesian deep learning · calibration · Post-training · LLM agents · tool use · instruction tuning · AI safety · RLHF · LLM alignment · reward modelling · preference optimization · Bayesian inference · approximate inference · amortized inference · neural inference · LLM reasoning · Reinforcement Learning · proof synthesis · Neurosymbolic programming · Bayesian probabilistic programming · Probabilistic program synthesis · program synthesis · statistical model discovery · Category theory · categorical semantics · categorical probability