Tianle Zhang

reinforcement learning (2) large language model (2) multimodal large language model (2) adversarial robustness (2) multimodal learning (2) risk management (1) visual grounding (1) contrastive learning (1) policy learning (1) adversarial perturbation (1) adversarial learning (1) adversarial training (1) modality alignment (1) safety alignment (1) distributional robustness (1) knowledge distillation (1) worst-case performance (1) adversarial attack (1) perturbation analysis (1) convex optimization (1)