arxiv:2605.18747
Zihao Li
Violet24K
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories authored a paper about 23 hours ago
Code as Agent Harness upvoted a paper 2 days ago
Code as Agent HarnessOrganizations
None yet
models 24
Violet24K/RM-Gemma-2B_reg_0.8
Updated
Violet24K/RM-Gemma-2B_reg_0.6
Updated
Violet24K/RM-Gemma-2B_reg_0.4
Updated
Violet24K/RM-Gemma-2B_reg_0.2
Updated
Violet24K/Llama-2-7b-pg19-mixed-65536
7B • Updated • 1
Violet24K/Llama-2-7b-pg19-mixed-63488
7B • Updated • 2
Violet24K/Llama-2-7b-pg19-mixed-61440
7B • Updated • 1
Violet24K/Llama-2-7b-pg19-mixed-59392
7B • Updated • 1
Violet24K/Llama-2-7b-pg19-mixed-55296
7B • Updated • 1
Violet24K/Llama-2-7b-pg19-mixed-57344
7B • Updated