Users' activation of multiple facial action units (AUs) are highly correlated with their evaluations of text-to-image generation, which can be used to automatically score user preferences for images generated by text-to-image generative models.

We propose to perform one-frame calibration (OFC) with a novel Calibrating Siamese Network (CSN) architecture design for AU recognition and show that it substantially improves the performance of the baseline model by mitigating facial attribute biases (including biases due to wrinkles, eyebrow positions, facial hair, etc.).

Facial expressions provide immediate and practical cues of confusion, frustration, or engagement but remain underexplored in LLM-driven tutoring. We demonstrated that facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration without end-to-end retraining.