Jinghui Chen

Stragglers Can Contribute More: Uncertainty-Aware Distillation for Asynchronous Federated Learning

AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections

TruthFlow: Truthful LLM Generation via Representation Flow Correction

JoPA: Explaining Large Language Model's Generation via Joint Prompt Attribution

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models

Securing Multimodal Large Language Models: Defending Against Jailbreak Attacks with Adversarial Tuning

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models

Your Agent Can Defend Itself against Backdoor Attacks