AI Paper Atlas

Research map / Video / Video generation

REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation

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

ICML 2026 · Video › Video generation · approach: Talking face generation · 0 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 ID-Sink to the context cache (ablation)REST ID-Context Cache · HDTFFID: 19.362 -> 14.597Improved
add ID-Sink to the context cache (ablation)REST ID-Context Cache · HDTFFVD: 294.692 -> 219.870Improved
add ID-Sink to the context cache (ablation)REST ID-Context Cache · HDTFSync-C: 8.345 -> 8.335No clear effect
add Context-Cache to ID-Sink (ablation)REST ID-Context Cache · HDTFSync-C: 6.909 -> 8.335Improved
add Context-Cache to ID-Sink (ablation)REST ID-Context Cache · HDTFFID: 19.656 -> 14.597Improved
add Context-Cache to ID-Sink (ablation)REST ID-Context Cache · HDTFFVD: 271.508 -> 219.870Improved
add Smooth loss to ASD (ablation)REST ASD · HDTFFVD: 221.525 -> 219.870Improved
add Smooth loss to ASD (ablation)REST ASD · HDTFFID: 14.646 -> 14.597No clear effect
add Contrastive loss to ASD (ablation)REST ASD · HDTFFID: 15.278 -> 14.597Improved
add Contrastive loss to ASD (ablation)REST ASD · HDTFSync-C: 8.190 -> 8.335Improved
add Contrastive loss to ASD (ablation)REST ASD · HDTFFVD: 219.881 -> 219.870No clear effect
add ASD distillation (ablation)REST streaming student · HDTFFID: 15.950 -> 14.597Improved

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