activity
20212026
most citedGeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis

34 citations · 130 across the 39 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses

Guangzheng Hu, Ziyue Jiang, Weixu Qiao +14

Multimodal understanding models that can jointly judge text-to-image (T2I), text-to-video (T2V) and text-to-speech (TTS) generation are increasingly used as "OmniJudges" for evalua…