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 model about 9 hours ago
wangzhang/Mistral-7B-Instruct-RR-Abliterated
liked a model about 10 hours ago
wangzhang/Llama-3-8B-Instruct-RR-Abliterated
updated a model about 10 hours ago
wangzhang/Llama-3-8B-Instruct-RR-Abliterated
View all activity

Organizations

None yet