Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

ArXi:2601.00664v2 Announce Type: replace-cross Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of truly interactive communication, often generating one-way responses that lack emotional engagement. We identify two key challenges toward truly interactive avatars: generating motion in real-time under causal constraints and learning expressive, vibrant reactions without additional labeled data.