Qwen technical report about long-horizon agentic tasks
Xinjie Shen
Frinkleko
AI & ML interests
Inference-free, Human AI collaboration
Recent Activity
updated a collection about 15 hours ago
Long-Horizon Agents submitted a paper about 15 hours ago
Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning upvoted a paper about 15 hours ago
Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety LearningOrganizations
models 21
Frinkleko/agentic-boundary-study-checkpoints
Updated
Frinkleko/agentic-boundary-study-portable
Updated
Frinkleko/zs-sftv2-36k
0.8B • Updated
Frinkleko/full_rl_2.165
4B • Updated • 4
Frinkleko/conversation-level-best
4B • Updated
Frinkleko/ood_cyber_rl_0.6590
4B • Updated • 6
Frinkleko/ood_cyber_sft_0.6581
4B • Updated
Frinkleko/ood_chem_rl_0.6553
4B • Updated
Frinkleko/ood_chem_sft_0.6538
4B • Updated
Frinkleko/naive_sft
4B • Updated