collaborators

5 papers

cs.CV2026

SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads

Tan Yu, Qian Qiao, Le Shen +9

Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models o…

cs.CV2026

SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation

Le Shen, Qian Qiao, Tan Yu +7

Deploying massive diffusion models for real-time, infinite-duration, audio-driven avatar generation presents a significant engineering challenge, primarily due to the conflict betw…

cs.CV2025

PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes

Derui Shan, Qian Qiao, Hao Lu +2

Polarization-aware Neural Radiance Fields (NeRF) enable novel view synthesis of specular-reflection scenes but face challenges in slow training, inefficient rendering, and strong d…

cs.GR2025

RAP: Real-time Audio-driven Portrait Animation with Video Diffusion Transformer

Fangyu Du, Taiqing Li, Qian Qiao +7

Audio-driven portrait animation aims to synthesize realistic and natural talking head videos from an input audio signal and a single reference image. While existing methods achieve…

cs.CV2025

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

Dingcheng Zhen, Qian Qiao, Xu Zheng +6

We introduce TransDiff, the first image generation model that marries Autoregressive (AR) Transformer with diffusion models. In this joint modeling framework, TransDiff encodes lab…