Steve Wu PRO

wangzhang

AI & ML interests

LLM Abliteration & Weight-Space Attacks, Refusal Direction Analysis, LoRA Reverse Engineering, TPE Hyperparameter Optimization, Mixture-of-Experts Abliteration, SSM/Hybrid Architecture Research, Activation Engineering, Vision-Language Models, Representation Engineering

Recent Activity

updated a collection about 3 hours ago
GPT-Abliterated
updated a collection about 3 hours ago
GPT-Abliterated
upvoted a collection about 3 hours ago
GPT-Abliterated
View all activity

Organizations

None yet