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