Jun Sun

7

Papers

20

Total Citations

Papers (7)

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

LLMScan: Causal Scan for LLM Misbehavior Detection

Unleashing the Power of Visual Foundation Models for Generalizable Semantic Segmentation

Democratic Training Against Universal Adversarial Perturbations

RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

Multi-Region Text-Driven Manipulation of Diffusion Imagery