Jianzhong Qi

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language Model

Parameter-wise Weighted Model Editing for Efficient and Retentive LLM Unlearning

Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts

Attribute-based Visual Reprogramming for Vision-Language Models

CARPRT: Class-Aware Prompt Reweighting for Pre-Trained Vision-Language Models