Kai Hu

LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models

LLM-based Multi-Agents System Attack via Continuous Optimization with Discrete Efficient Search

Learning Graph Invariance by Harnessing Spuriosity

StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models

ControlVAR: Exploring Controllable Visual Autoregressive Modeling

Transferable Adversarial Attack on Vision-enabled Large Language Models

Combating inherent noise for direct preference optimization