Wei Chow

EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis