Ying Ba

Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction

Masked AutoRegressive Detokenization with Semantic Visual Tokens for High-fidelity Image Synthesis

PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation

Mitigating Reward Hacking in Multi-Reward Optimization for Text-to-Image Generation

Learning User Preferences for Image Generation Models