The models trained with EVOL-RL
Yujun Zhou
yujunzhou
AI & ML interests
None yet
Recent Activity
new activity 13 days ago
yujunzhou/AIME-TTT-OctoThinker-8B-Hybrid-Base-TTRL:Running in MSTY Studio submitted a paper 3 months ago
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM ReasoningOrganizations
None yet
models 251
yujunzhou/SFT_Advanced_Risk_Self_Grading_Qwen3-4B
Text Generation • 4B • Updated • 2
yujunzhou/SFT_Advanced_Risk_Self_Grading_llama
Text Generation • 8B • Updated • 9
yujunzhou/SFT_Advanced_Risk_Self_Grading_Qwen3-4B-Base
Text Generation • 4B • Updated • 5
yujunzhou/SFT_Advanced_Risk_Reward_Tampering_Qwen3-4B
Text Generation • 4B • Updated • 1
yujunzhou/Advanced_Risk_Self_Grading_llama
8B • Updated
yujunzhou/SFT_Advanced_Risk_Reward_Tampering_Qwen3-4B-Base
Text Generation • 4B • Updated • 3
yujunzhou/SFT_Advanced_Risk_Reward_Tampering_llama
Text Generation • 8B • Updated
yujunzhou/SFT_Advanced_Risk_Situation_Aware_Qwen3-4B-Base
Text Generation • 4B • Updated • 1
yujunzhou/SFT_Advanced_Risk_Situation_Aware_Qwen3-4B
Text Generation • 4B • Updated
yujunzhou/SFT_Advanced_Risk_Situation_Aware_llama
Text Generation • 8B • Updated • 8