arxiv:2610.19159
Seungone Kim PRO
seungone
AI & ML interests
Large Language Models, LLM-as-a-Judge, Reward Model Overoptimization, Personalized Alignment
Recent Activity
updated a model 7 days ago
seungone/scottyrl-a3-p5_textcraft_grpo published a model 7 days ago
seungone/scottyrl-a3-p5_textcraft_grpo new activity 15 days ago
prometheus-eval/into-the-unknown:Add task category and sample usageOrganizations
arxiv:2610.02202
arxiv:2609.04141
arxiv:2608.19197
arxiv:2607.04412
arxiv:2606.29082
arxiv:2606.02404
arxiv:2605.26457
arxiv:2605.20668
arxiv:2605.09063
arxiv:2603.18886
arxiv:2511.22173
arxiv:2510.24684
arxiv:2509.21451
arxiv:2508.13141
arxiv:2507.00432
arxiv:2506.01789
arxiv:2505.23840
arxiv:2505.22202
arxiv:2505.16409
arxiv:2505.15277
arxiv:2505.14489
arxiv:2505.10185
arxiv:2504.04953
arxiv:2503.19877
arxiv:2412.17847
arxiv:2412.10424
arxiv:2412.03679
arxiv:2410.17578
arxiv:2410.16153
arxiv:2410.02902
arxiv:2407.17022
arxiv:2407.14933
arxiv:2406.05761
arxiv:2405.17977
arxiv:2405.01535
arxiv:2404.10346
arxiv:2404.02575
arxiv:2402.11597
arxiv:2402.11548
arxiv:2401.10695
arxiv:2401.06591
arxiv:2310.11564
arxiv:2310.08491
arxiv:2307.10928
arxiv:2305.14045
arxiv:2303.03628
arxiv:2302.03202
arxiv:2209.00930
