AI Paper Atlas

Research map / Video / Video generation

ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA

Aviad Dahan, Moran Yanuka, Noa Kraicer, Lior Wolf, RAJA GIRYES

ECCV 2026 · Video › Video generation · approach: Talking face generation · 5 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 identity guidance (ablation)ID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: 0.438 -> 0.477Improved
add negative temporal positions instead of standard PEs (ablation)ID-LoRA · CelebV-HQ hard (cross-video)WER: 0.252 -> 0.113Improved
add negative temporal positions instead of standard PEs (ablation)ID-LoRA · CelebV-HQ hard (cross-video)LSE-D: 9.02 -> 8.50Improved
add negative temporal positions instead of standard PEs (ablation)ID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: 0.441 -> 0.477Improved
raise identity guidance scale from 2 to 4 (ablation)ID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: 0.459 -> 0.477Improved
raise identity guidance scale from 4 to 10 (ablation)ID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: 0.477 -> 0.485Mixed
raise identity guidance scale from 4 to 16 (ablation)ID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: 0.477 -> 0.470Hurt
unified joint generation instead of cascaded TTS + WAN2.2ID-LoRA vs CosyVoice 3.0 + WAN2.2 · CelebV-HQ hard (cross-video)speaker similarity: 0.391 -> 0.477Improved
gap over best cascaded baseline widens from same-video to cross-videoID-LoRA · CelebV-HQ hard (cross-video)speaker similarity: +0.063 (easy) to +0.086 (hard)Improved
apply CelebV-HQ checkpoint to TalkVid without fine-tuningID-LoRA · TalkVidspeaker similarity: 0.599 -> 0.595No clear effect
apply CelebV-HQ checkpoint to TalkVid without fine-tuningID-LoRA · TalkVidCLAP: 0.385 -> 0.412Improved
ID-LoRA vs Kling 2.6 Pro in human preference, voice similarityID-LoRA · CelebV-HQ hard (cross-video)A/B preference: 73.1% vs. 20.0%Improved

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