Yiran Geng

safe reinforcement learning (2) policy learning (2) reinforcement learning (2) sim-to-real transfer (1) robotic manipulation (1) constraint optimization (1) knowledge distillation (1) point cloud (1) test-time adaptation (1) ai safety (1) synthetic data generation (1) object manipulation (1) risk minimization (1) constraint satisfaction (1) multimodal large language model (1) object-centric learning (1) safety benchmark (1) reinforcement learning policy (1) agent system (1) domain adversarial learning (1)