Wanrong Zhu

Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations

Towards Visual Text Grounding of Multimodal Large Language Model

MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing

GUI‑AIMA: Aligning Intrinsic Multi-Modal Attention with a Context Anchor for GUI Grounding

MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

ADOPD-Instruct: A Large-Scale Multimodal Dataset for Document Editing

OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Document Archive