Kiran Koshy Thekumparampil

Post-Training · Reward Modeling · Supvised Finetuning · Data Selection · Agents · Reinforcement Learning · Verifiers · Self-Play · Differential Privacy · Ranking · Language Models · Federated Learning · Distributed optimization · Meta-Learning · Transfer learning · Few-shot learning · Optimization · Minimax · Non-smooth · Stochastic · Generative Adversarial Networks · Generative Models · Disentangling Representation · Graph Neural Networks · Graph Classification