Xiaorui Wang

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Test-Time Scaling with Reflective Generative Model

Visual Feedback for Self-Improving Text Layout with MLLM via Reinforcement Learning

SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion Classifier

GRIP: A Graph-Based Reasoning Instruction Producer

A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Data