Sravan Jayanthi

retrieval augmented generation (1) offline reinforcement learning (1) path planning (1) question answering (1) multimodal learning (1) question generation (1) inverse reinforcement learning (1) synthetic data generation (1) reward learning (1) lifelong learning (1) learning from demonstration (1) synthetic datum (1) large multimodal model (1) fast adaptation (1) policy distillation (1) large language model (1) multimodal retrieval-augmented generation (1) policy mixture (1) heterogeneous demonstration (1)