Yikun Li

reinforcement learning (1) curriculum learning (1) text-to-image generation (1) diffusion model (1) security evaluation (1) code agent (1) identity preservation (1) secure coding (1) face generation (1) large language model (1) patch generation (1) zero-shot personalization (1) vulnerability introduction (1) automated vulnerability repair (1) code semantic equivalence (1) semantic-aware reward (1)