Xu Zhihao
naiweizi
AI & ML interests
Trustworthy AI
Recent Activity
authored
a paper
about 5 hours ago
Uncovering Safety Risks of Large Language Models through Concept
Activation Vector
authored
a paper
about 5 hours ago
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training
and Deployment
authored
a paper
about 5 hours ago
Internal Value Alignment in Large Language Models through Controlled
Value Vector Activation
Organizations
None yet
models
12
naiweizi/r1-qwen-7b-sft_meta
8B
•
Updated
naiweizi/R1-Qwen-7B-SFT-Meta
Updated
naiweizi/R1-Qwen-1_5B-Cold_Start-OpenR1_Math-priority
2B
•
Updated
naiweizi/dpo-harmless_saferlhf
Updated
•
1
naiweizi/mistral-dpo-helpful-vanilla-1e-4
Updated
naiweizi/mistral-dpo-harmless-vanilla-2e-4
Updated
naiweizi/test
Text Generation
•
8B
•
Updated
•
2
naiweizi/dpo-harmless_helpful-vanilla
Updated
naiweizi/dpo-harmless_helpful-rc_armo
Updated
naiweizi/dpo-harmless_helpful-mixed
Updated