Chenhui Gou

UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

Sparsity Forcing: Reinforcing Token Sparsity of MLLMs

Bagel-World: Towards High-Quality Visual Question-Visual Answering

LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding

EZIGen: Enhancing zero-shot subject-driven image generation with precise subject encoding and decoupled guidance