Shuo Zhang

This paper introduces TwoHamsters, a new benchmark that rigorously tests Multi-Concept Compositional Unsafety (MCCU) in text-to-image models, demonstrating that current state-of-the-art models and safety defenses are highly vulnerable to subtle, compositionally unsafe prompts.

DPDSyn improves differentially private dataset synthesis by training a differentially private AI model on the original private data, which is then used to generate synthetic datasets that maintain high utility for downstream tasks.

The paper introduces HomeFlow, a verifiable data flywheel that procedurally generates high-quality, multi-turn training data for smart home agents, achieving state-of-the-art performance on smart home tasks.

The paper proposes Self-Adaptive Monotonic Normalization (SAMN), a hyperparameter-friendly method that improves long-tailed recognition by enforcing monotonicity on per-class weight norms without requiring parameter regularization.

The paper introduces SMH-Bench, a comprehensive benchmark built on a simulator to rigorously test LLM agents' ability to perform complex, environment-grounded reasoning and actions in realistic smart-home scenarios.