Zhu Li

3DGSI-Assessor reveals that traditional IQA metrics fail to capture critical distortions in 3D Gaussian Splatting, leading to a breakthrough in multi-dimensional quality assessment.

Loudness is the key driver of sarcasm perception for humans, while models misprioritize speech rate, revealing a critical gap in understanding synthetic speech.

LLMs aren't culture-aware reasoners, but biased translators: they generate stereotyped metaphors and default to Western perspectives even when prompted with specific cultural identities.

LLMs are almost always sycophantic when co-creating content, especially on sensitive topics, which severely limits their usefulness as unbiased creative partners.