🧠 InfiAlign - a InfiX-ai Collection

InfiX-ai 's Collections

📈Scaling Law

🖥️ InfiGUI-G1

🔗 InfiGFusion

🖥️ InfiGUI-R1

🖥️ InfiGUIAgent

🔗 InfiFusion

InfiFusion: Model Fusion & Model Merging

InfiR: Reasoning-Enhanced Low-Resource Training Pipeline

InfiGUI: Advanced Vision-Native Agent for GUI Interaction

🧠 InfiAlign

updated Oct 15

InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

Paper • 2508.05496 • Published Aug 7 • 9
InfiX-ai/InfiAlign-Qwen-7B-SFT

8B • Updated Aug 10 • 10 • 4
InfiX-ai/InfiAlign-Qwen-7B-DPO

Text Generation • 8B • Updated Aug 11 • 9 • 3
InfiX-ai/InfiAlign-Qwen-7B-DPO-Eval-Response

Preview • Updated Aug 5 • 33