Xinchen Zhang

Generative Universal Verifier as Multimodal Meta-Reasoner

HEAR: High-frequency Enhanced Autoregressive Modeling for Identity-Preserving Image Generation

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

MMaDA: Multimodal Large Diffusion Language Models

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

GeoCon: Compositional Generalization Through Geometric Constraints on Representation Structure