Guoqing Ma

contrastive learning (1) reinforcement learning (1) domain generalization (1) multimodal recommendation (1) policy learning (1) adversarial training (1) domain randomization (1) sampling efficiency (1) knowledge graph (1) video summarization (1) modality imbalance (1) sequential recommendation (1) mixture of expert (1) data quality (1) visual encoder (1) data scarcity (1) large language model (1) epistemic planning (1) neuro-symbolic framework (1) data renovation (1)