qihoo360/RevealLayer-100K
Viewer • Updated • 1.06M • 451 • 4
北京奇虎科技有限公司
company
AI & ML interests
None defined yet.
Papers
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning
qihoo360/InduOCRBench
Viewer • Updated • 2.07k • 319 • 1
qihoo360/VRF-datasets
Viewer • Updated • 658k • 27
qihoo360/DOCCI-CN
Viewer • Updated • 5k • 34 • 1
qihoo360/DCI-CN
Viewer • Updated • 7.81k • 77
qihoo360/LIT-CN
Preview • Updated • 39 • 1
qihoo360/BoxClass-CN
Updated • 43 • 1
qihoo360/FineHARD
Preview • Updated • 58 • 11
qihoo360/Light-IF-SFTData
Viewer • Updated • 2k • 22 • 5
qihoo360/Light-IF-cold-start-datasets.json
Updated • 6
qihoo360/WISA-80K
Viewer • Updated • 79.5k • 1.75k • 13
qihoo360/TinyR1-32B-Preview-datasets
Preview • Updated • 60 • 4
qihoo360/Light-R1-SFTData
Viewer • Updated • 79.4k • 527 • 61
qihoo360/Light-R1-DPOData
Viewer • Updated • 2.97k • 123 • 29
qihoo360/PlanGen_data
Preview • Updated • 12