I study how machines understand and create beauty.

An agentic system for planning human pose, camera, and lighting for portrait photography in a 3D environment.

A semiotics-theoretic framework for evaluating art interpretation through Peirce's semiosis.

A controllable diffusion approach that uses image structure as a material for non-representational art.

A reasoning framework that interprets visual aesthetics beyond surface-level appeal.

Prompt tuning for multimodal fusion that preserves task-specific cues through selective conditioning.

Open-vocabulary object counting from arbitrary text prompts, without category-specific training.

A text-to-avatar pipeline with explicit control over neural human shape and pose.

Text-driven stylization for neural radiance fields, with flexible artistic control over 3D objects.