arxiv:2602.04145
Jinyuan Li
jinyuan222
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories upvoted a paper 4 days ago
Process Rewards with Learned Reliability submitted a paper 4 days ago
Process Rewards with Learned ReliabilityOrganizations
models 10
jinyuan222/visualprm400K-all-soft-vanillaprm-internvl3-8b
8B • Updated • 4
jinyuan222/visualprm400K-all-soft-vanillaprm-internvl3-14b
15B • Updated • 2
jinyuan222/visualprm400K-beta-binom-internvl3-14b
15B • Updated • 3
jinyuan222/visualprm400K-beta-binom-internvl3-8b
8B • Updated • 4
jinyuan222/visualprm400K-random8
8B • Updated • 4
jinyuan222/visualprm400K-lowmc8
8B • Updated • 3
jinyuan222/visualprm400K-mix8
8B • Updated • 3
jinyuan222/visualprm400K-reliable_only25-1-epochonly
Updated • 1
jinyuan222/MM-PRM-train-usage-internvl
Updated
jinyuan222/MM-PRM-train-usage
Updated
datasets 0
None public yet