Jiaming Han

Growing Visual Generative Capacity for Pre-Trained MLLMs

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents

AV-Odyssey Bench: From Fundamental Audio Perception to Audio-Visual Understanding

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

VideoShield: A Unified Framework for Multimodal Risk Detection and Control in Video Generative Models

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant

Towards Continual Domain Adaptation of Vision-language Models

Mitigating Generative Privacy Risks of Diffusion Models via Mixed Self-Synthesized Data Fine-tuning