Dongmei Jiang

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes

FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

Flowing with Precision: Rectified Flow Image Editing with Trajectory and Frequency Guidance

PolaFormer: Polarity-aware Linear Attention for Vision Transformers

CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models

MeMAD: Structured Memory of Debates for Enhanced Multi-Agent Reasoning

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Open-Det: An Efficient Learning Framework for Open-Ended Detection

QFree-Det: Query-Free Detector with Transformer and Sequential Matching