AQ-MedAI/Kimi-K25-eagle3
1B • Updated • 13.3k • 10
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning
AQ-MedAI/ClinAlign-30B-A3B
31B • Updated • 2
AQ-MedAI/ClinAlign-4B
4B • Updated • 9 • 3
AQ-MedAI/PulseMind-72B
Image-Text-to-Text • 73B • Updated • 41 • 1
AQ-MedAI/Qwen3-VL-235B-A22B-Instruct-eagle3
Updated • 14
AQ-MedAI/Diver-Retriever-4B
Text Ranking • 4B • Updated • 607 • 23
AQ-MedAI/Qwen3-VL-8B-Instruct-eagle3
0.4B • Updated • 53
AQ-MedAI/Qwen2.5-VL-72B-Instruct-eagle3
1B • Updated • 8 • 1
AQ-MedAI/Ling-Flash-2.0-eagle3
0.4B • Updated • 8 • 3
AQ-MedAI/Kimi-K2-Instruct-eagle3
1B • Updated • 16 • 11
AQ-MedAI/Diver-GroupRank-7B
Text Ranking • 8B • Updated • 30 • 7
AQ-MedAI/Diver-GroupRank-32B
Text Ranking • 33B • Updated • 8 • 3
AQ-MedAI/Diver-Retriever-4B-1020
Text Ranking • 4B • Updated • 2.98k • 4
AQ-MedAI/Diver-Retriever-0.6B
Text Ranking • 0.6B • Updated • 268 • 6
AQ-MedAI/Diver-Retriever-1.7B
Text Ranking • 2B • Updated • 20 • 2
AQ-MedAI/MedResearcher-R1-32B
Text Generation • 33B • Updated • 53 • 32