Shiqing Ma

EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs

Domain-Specialized Tree of Thought through Plug-and-Play Predictors

MCP-Radar: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models

LLMs as Reverse Engineers? Not Yet on Types and Names

STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning

Continuous Concepts Removal in Text-to-image Diffusion Models

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification