AI.info

Qifan Wang

Explore Qifan Wang on AI.info.

• TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
• TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
• Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence
• All You Need is One: Capsule Prompt Tuning with a Single Vector
• Prompt-based Adaptation in Large-scale Vision Models: A Survey