AI
EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold
Publication: Hugging Face Daily Papers
Author: Not available in collected metadata
Source published: 27/09/2026, 20:00:00 UTC
Briefing created: 29/09/2026, 09:10:20 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 29/09/2026, 05:18:25 UTC.
Briefings
EvolvingAvatar is a causal 3D head generation model that adapts to user interactions via test-time training, using dyadic audio and video to predict speech activity and guide persistent motion weights. It introduces InterHead-Bench, a 455.95-hour benchmark comparing single-view and dual-view conversations. Experiments show improved motion statistics over baselines, with generation improving by up to 11.1% on the hardest out-of-distribution split as conversations unfold.
Key points
- EvolvingAvatar uses test-time training to adapt to user face video and dyadic audio during interaction, predicting speech activity to guide persistent fast weights and transient jaw adaptation.
- InterHead-Bench is a unified benchmark built from single-view and dual-view conversation videos, achieving improved conversational motion statistics over strong baselines.
Context and limitations
The study relies on single-view and dual-view conversation videos for its benchmark; specific limitations on multi-view data and long-term adaptation stability are not detailed.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 29/09/2026, 09:10:20 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeif4ejf3he6p7zgxj3xijr7fnrzd65n3thw4jkhyutrx3cgtvddjcy