AI Paper Atlas

Research map / Video / Video generation

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

Taekyung Ki, Sangwon Jang, Jaehyeong Jo, Jaehong Yoon, Sung Ju Hwang

CVPR 2026 · Video › Video generation · approach: Talking face generation · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use 10 blocks instead of 5 (smaller latency, larger blocks count) (ablation)Avatar Forcing · RealTalklatency: 0.5 -> 0.3 (latency); FVD 170.87 -> 222.47Mixed
use 2 blocks instead of 5 (ablation)Avatar Forcing · RealTalkFVD / LSE-D / latency: FVD 170.87 -> 155.81; LSE-D 6.723 -> 6.555; latency 0.5 -> 1.5Mixed
add user motion input to the Dual Motion Encoder (ablation)Avatar Forcing · RealTalkReactiveness and Motion RichnessImproved
add DPO preference fine-tuning with synthetic losing samples (ablation)Avatar Forcing · RealTalkrPCC-Exp, rPCC-Pose, SID, VarImproved
add look-ahead to the blockwise causal mask (ablation)Avatar Forcing · RealTalktemporal smoothness (qualitative)Improved
use diffusion forcing instead of autoregressive diffusion (ablation)Avatar Forcing · long-horizon generationmotion driftImproved
use causal blockwise diffusion forcing instead of bidirectional INFP*Avatar Forcing · RealTalklatency: 3.4 -> 0.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy