Our core research areas include:

• Generative AI: Pioneering high-fidelity text-to-image, video, and 3D generation using diffusion models and user-guided control.
• Robust Computer Vision: Developing reliable vision systems that perform under real-world challenges such as low light, adverse weather, autonomous driving, and other safety-critical applications.
• Efficient Learning: Creating resource-efficient AI through lightweight training, model compression and quantization, and dataset distillation.
• Trustworthy AI: Building frameworks to evaluate and mitigate AI flaws, such as hallucination and bias in generative models.