Jihao Gu

Reinforcement Learning (1)

large language model (3) vision-language model (3) direct preference optimization (2) factuality evaluation (2) mobile agent (2) visual question answering (1) object recognition (1) benchmark evaluation (1) question answering (1) transfer learning (1) video understanding (1) interactive systems (1) safety alignment (1) model alignment (1) zero-shot generalization (1) parameter efficient fine-tuning (1) preference learning (1) hallucination mitigation (1) knowledge capacity (1) reward modeling (1)