Yunlong Lin

One Graph Can Generalize: Graph-guided Structural Transfer for Source-free Open-set Domain-adaptive Object Detection

PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

FuseAgent: A VLM-driven Agent for Unified In-the-Wild Image Fusion

InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework

Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models

ILVS\(^2\)Net: Illumination-Driven Non-Local Visual State Space Unfolding Network for Low-Light Enhancement

Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling