Learning from Motion to Segment Anything Without Supervision
北京奇虎科技有限公司
company
AI & ML interests
None defined yet.
Recent Activity
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
End-to-End Try on
360Zhinao language model, include both base and chat model
Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
We propose FLUX-Makeup, a high-fidelity, identityconsistent, and robust makeup transfer framework that eliminates the need for any auxiliary face-cont
FG-CLIP 2 is the foundation model for fine-grained vision-language understanding in both English and Chinese.
-
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Paper • 2510.10921 • Published • 12 -
qihoo360/FineHARD-CN
Viewer • Updated • 27.6M • 645 -
qihoo360/fg-clip2-base
Zero-Shot Image Classification • 0.4B • Updated • 2.49k • 28 -
qihoo360/fg-clip2-large
Zero-Shot Image Classification • 0.9B • Updated • 614 • 13
New generation of CLIP with strong fine grained discrimination capability
360Zhinao2 language model, include both base and chat model
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
Learning from Motion to Segment Anything Without Supervision
We propose FLUX-Makeup, a high-fidelity, identityconsistent, and robust makeup transfer framework that eliminates the need for any auxiliary face-cont
End-to-End Try on
FG-CLIP 2 is the foundation model for fine-grained vision-language understanding in both English and Chinese.
-
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Paper • 2510.10921 • Published • 12 -
qihoo360/FineHARD-CN
Viewer • Updated • 27.6M • 645 -
qihoo360/fg-clip2-base
Zero-Shot Image Classification • 0.4B • Updated • 2.49k • 28 -
qihoo360/fg-clip2-large
Zero-Shot Image Classification • 0.9B • Updated • 614 • 13
New generation of CLIP with strong fine grained discrimination capability
360Zhinao language model, include both base and chat model
360Zhinao2 language model, include both base and chat model
Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following