Zhuokai Zhao

6

Papers

83

Total Citations

2

Affiliations

Affiliations

MetaUniversity of Chicago

Papers (6)

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

NeurIPS 2025arXiv

Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding

RANKCLIP: Ranking-Consistent Language-Image Pretraining

HumanMM: Global Human Motion Recovery from Multi-shot Videos

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding