arxiv:2605.07865
Minjae Oh
Riasok
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
Human Psychometric Questionnaires Mischaracterize LLM Behavior authored a paper 6 days ago
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding authored a paper 6 days ago
KL for a KL: On-Policy Distillation with Control Variate BaselineOrganizations
models 34
Riasok/kaana-if-opd
Text Generation • 2B • Updated • 4 • 1
Riasok/Qwen3_4b_TB
Updated • 1
Riasok/aioyfbqwen7bfpa55e6
Updated
Riasok/fnliniqwen7bfpa105e6
Updated
Riasok/qwugpvqwen7bapo15e6binary
Updated • 2
Riasok/pfgfcyqwen4bdponll25e6
Updated • 2
Riasok/isgyhrqwen4bbsimkl25e6betaepoch4005kl
Updated • 1
Riasok/nryajnqwen4bfpapos25e6epoch4
Updated • 2
Riasok/drcagnqwen4bfpaneg25e6epoch4
Updated • 3
Riasok/elsckaqwen4bfpa55e6
Updated • 2
datasets 0
None public yet