SOURCE-LINKED INTELLIGENCE

BEACON: Behavior and Appearance Control for Subject-Specific Video Generation

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In addition to reproducing appearance, a model must replicate the facial behaviors that characterize how a subject expresses emotion over time. However, most state-of-the-art methods condition generation on a single reference image, which contains no information about these temporal dynamics. As a result, they tend to preserve the subject's visual identity but often produce expressions with limited variation and weak subject specificity. To mitigate this i

Read original source ↗ Open in workspace

recordType

paper

region

Global