AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

EchoMimicV3: 1.3B Parameters Are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Rang Meng, Yan Wang, Weipeng Wu, Ruobing Zheng, Yuming Li, Chenguang Ma

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 18 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 hard-to-easy task schedule instead of easy-to-hard (ablation)EchoMimicV3 · Ablation (Table 2)Sync-C: 5.40 -> 5.49Improved
use hard-to-easy schedule instead of uniform random sampling (ablation)EchoMimicV3 · Ablation (Table 2)Sync-C: 4.98 -> 5.49Improved
add inter-task EMA (ablation)EchoMimicV3 · Ablation (Table 2)FVD: 508.82 -> 496.76Improved
allocate audio in early timestep phase (ablation)EchoMimicV3 · Ablation (Table 2)Sync-C: 4.76 -> 5.49Improved
include text in early/mid phases (ablation)EchoMimicV3 · Ablation (Table 2)HA: 0.81 -> 0.95Improved
include image in early phases (ablation)EchoMimicV3 · Ablation (Table 2)FVD: 540.80 -> 496.76Improved
use Negative DPO-SFT cycle instead of SFT only (ablation)EchoMimicV3 · Ablation (Table 2)FVD: 540.30 -> 496.76Improved
use Negative DPO instead of paired DPO (ablation)EchoMimicV3 · Ablation (Table 2)ID: 0.93 -> 1.00Improved
use paired DPO instead of Negative DPO (ablation)EchoMimicV3 · Ablation (Table 2)FVD: 480.98 vs 496.76Mixed
add Phase-aware Negative CFG (ablation)EchoMimicV3 · Ablation (Table 2)HA: 0.89 -> 0.95Improved
add Long Video CFG (ablation)EchoMimicV3 · Ablation (Table 2)FVD: 530.21 -> 496.76Improved
use 1.3B model with 5 steps instead of 14B modelsEchoMimicV3 · Table 1inference speed: 18x speedupImproved

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