AI Paper Atlas

Research map / Video / Video generation

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

Haotian Wang, Yuzhe Weng, Jun Du, Haoran Xu, Xiaoyan Wu, Shan He, Bing Yin, Cong Liu, Jianqing Gao, Qingfeng Liu

AAAI 2026 · Video › Video generation · approach: Talking face generation · 3 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
add self-supervised pre-training of SpeechAE (ablation)READ · HDTFSync-C: 7.965 -> 8.658Improved
add self-supervised pre-training of SpeechAE (ablation)READ · HDTFSync-D: 7.361 -> 6.890Improved
add self-supervised pre-training of SpeechAE (ablation)READ · HDTFFID: 15.305 -> 15.073Improved
add SpeechAE for temporal compression of speech features (ablation)READ · HDTFSync-C: 2.086 -> 8.658Improved
add SpeechAE for temporal compression of speech features (ablation)READ · HDTFSync-D: 12.415 -> 6.890Improved
add SpeechAE for temporal compression of speech features (ablation)READ · HDTFFID: 15.617 -> 15.073Improved
add asynchronous noise scheduler (ANS) instead of synchronous noise and clip concatenation (ablation)READ · two consecutive 121-frame clipstemporal consistency (qualitative)Improved
extend generated video length from 121 to 457 and 1017 frames (ablation)READ with ANS · HDTFSync-C: 8.658 -> 8.767 -> 8.677No clear effect
extend generated video length from 121 to 1017 frames (ablation)READ with ANS · HDTFFID: 15.073 -> 15.241 -> 15.195No clear effect
use Split-CFG instead of Joint-CFG (ablation)READ · HDTFlip-sync and runtime: runtime increased almost by 50%Mixed
reduce inference steps below 5 (ablation)READ · HDTFFIDHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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