cs.CVNov 13, 2026

LongCat-Video-Avatar 1.6 Technical Report

Authors: Meituan LongCat Team, Xunliang Cai, Yiqi Chen, Feng Gao, Xiaoyu Kong, Le Li, Hongyu Liu, Xiaoming Wei, 

Abstract

Recent advances in audio-driven avatar video generation have enabled increasingly realistic synthesis, yet achieving precise lip-audio synchronization, natural, human-like motion, and visual consistency over long sequences remains challenging. We present LongCat-Video-Avatar 1.6, which builds on LongCat-Video-Avatar 1.5 to improve expressive naturalness and reduce error accumulation during extended generation, e.g., exaggerated lip movements and overly red, temporally unstable lip coloration, enhance the naturalness of facial expressions and coordinated head and body movements. These improvements are driven by a refined post-training pipeline that integrates reinforcement learning, improved classifier-free guidance strategies for DMD-based few-step distillation, long-video rollouts, and on-policy distillation. Together, these refinements improve expressive realism and enable the generation of videos exceeding 10 minutes while maintaining visual quality and temporal consistency. Arena evaluations show that LongCat-Video-Avatar 1.6 outperforms its predecessor and competing commercial audio-driven avatar models, demonstrating the effectiveness of the improved post-training pipeline.

Figures & tables

Explore similar work

CardsList
  1. LongCat-Video-Avatar 1.5 Technical Report

    May 26, 2026Meituan LongCat Team, Xunliang Cai, Meng Cheng +10Audio-Video GenerationLong Video Generation