Difan Jiao
difanjiao
AI & ML interests
Generative Models & Mech Interp
Recent Activity
submitted a paper 3 days ago
LLM Safety From Within: Detecting Harmful Content with Internal Representations upvoted a paper 4 days ago
LLM Safety From Within: Detecting Harmful Content with Internal Representations updated a model 4 days ago
UofTCSSLab/SIREN-Llama-3.1-8BOrganizations
models 6
difanjiao/vanilla_grpo_math_Qwen3-4B
4B • Updated • 19
difanjiao/ThinkTwice-Olmo3-7B-Instruct
7B • Updated • 37
difanjiao/ThinkTwice-Qwen3-4B-Instruct
4B • Updated • 77 • 2
difanjiao/OpenCharacter-Qwen3-4B-Instruct-2507
Updated • 5
difanjiao/chessllm-qwen3-0.6b-sft-only
0.6B • Updated • 3
difanjiao/chessllm-qwen3-0.6b
0.8B • Updated • 3