shiwen cui

Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs

UpSafe℃: Upcycling for Controllable Safety in Large Language Models

INPO: Image-based Negative Preference Optimization for Concept Erasure in Text-to-Image Diffusion Models

Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination

SEM: Reinforcement Learning For Search-Efficient Large Language Models

On the Robustness of Latent Diffusion Models

Multi-modality Adversarial Attacks on Latent Diffusion Models