arxiv:2605.17873
Yumin Choi
YuminChoi
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents upvoted a paper 10 days ago
Zone of Proximal Policy Optimization: Teacher in Prompts, Not GradientsOrganizations
models 23
YuminChoi/Thinksafe-8B-olmo-filtered-40k
Updated
YuminChoi/Thinksafe-4B-olmo-filtered-40k
Updated
YuminChoi/Thinksafe-1.7B-olmo-filtered-40k
Updated
YuminChoi/Thinksafe-0.6B-olmo-filtered-40k
Updated
YuminChoi/Thinksafe-8B-olmo-filtered-1k
Updated
YuminChoi/Thinksafe-4B-olmo-filtered-1k
Updated
YuminChoi/Thinksafe-1.7B-olmo-filtered-1k
Updated
YuminChoi/Thinksafe-0.6B-olmo-filtered-1k
Updated
YuminChoi/thinksafe-8B-ablation-prompt-intent
Updated
YuminChoi/thinksafe-8B-ablation-prompt-risk
Updated
datasets 45
YuminChoi/SL-sft-training-dataset
Viewer • Updated • 32.1k • 21
YuminChoi/ThinkSafe-r1-8B-star41k
Viewer • Updated • 61.4k • 10
YuminChoi/ThinkSafe-r1-7B-star41k
Viewer • Updated • 60.1k • 9
YuminChoi/ThinkSafe-r1-1.5B-star41k
Viewer • Updated • 55.2k • 6
YuminChoi/ThinkSafe-8B-star-benign20k-LG-filtered
Viewer • Updated • 31.7k • 58
YuminChoi/ThinkSafe-4B-star-benign20k-LG-filtered
Viewer • Updated • 31.7k • 9
YuminChoi/ThinkSafe-1.7B-star-benign20k-LG-filtered
Viewer • Updated • 31.6k • 9
YuminChoi/ThinkSafe-0.6B-star-benign20k-LG-filtered
Viewer • Updated • 31.4k • 8
YuminChoi/SafeChain-benign-20k-Star-harm-LG-filtered
Viewer • Updated • 31.7k • 6
YuminChoi/ThinkSafe-8B-star-benign-LG-filtered
Viewer • Updated • 23.4k • 5