Yexin Liu

Leading image generation models fail over 40% of goal-driven visual reasoning tasks, but decoupling explicit visual planning from generation boosts task completion by up to 14.6 points without fine-tuning.

A novel multi-agent framework reduces hallucinations in language models by 79.46%, enabling reliable reasoning in scientific applications.

Forget full intrinsic decomposition: LightCtrl achieves state-of-the-art single-image relighting by learning sparse, physically meaningful latent proxies from limited PBR data.