AQ-MedAI/Qwen3-4B-DSpark
0.6B β’ Updated β’ 43 β’ 1
AI & ML interests
None defined yet.
Recent Activity
Papers
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning
AQ-MedAI/Qwen3-4B-DFlash2
0.6B β’ Updated β’ 56 β’ 1
AQ-MedAI/DeepSeek-V4-Flash-0731-eagle3
0.7B β’ Updated β’ 59
AQ-MedAI/Kimi-K25-eagle3
1B β’ Updated β’ 934 β’ 10
AQ-MedAI/Kimi-K2.7-Code-eagle3
2B β’ Updated β’ 31 β’ 2
AQ-MedAI/Kimi-K26-eagle3
2B β’ Updated β’ 18
AQ-MedAI/GLM-5.1-eagle3
1B β’ Updated β’ 28 β’ 1
AQ-MedAI/Qwen3.5-397B-A17B-eagle3
0.6B β’ Updated β’ 33 β’ 2
AQ-MedAI/ClinAlign-30B-A3B
31B β’ Updated β’ 19
AQ-MedAI/ClinAlign-4B
4B β’ Updated β’ 22 β’ 3
AQ-MedAI/PulseMind-72B
Image-Text-to-Text β’ 73B β’ Updated β’ 141 β’ 2
AQ-MedAI/Qwen3-VL-235B-A22B-Instruct-eagle3
1B β’ Updated β’ 22
AQ-MedAI/Diver-Retriever-4B
Text Ranking β’ 4B β’ Updated β’ 707 β’ 24
AQ-MedAI/Qwen3-VL-8B-Instruct-eagle3
0.4B β’ Updated β’ 92
AQ-MedAI/Qwen2.5-VL-72B-Instruct-eagle3
1B β’ Updated β’ 22 β’ 1
AQ-MedAI/Ling-Flash-2.0-eagle3
0.4B β’ Updated β’ 22 β’ 3
AQ-MedAI/Kimi-K2-Instruct-eagle3
1B β’ Updated β’ 81 β’ 11
AQ-MedAI/Diver-GroupRank-7B
Text Ranking β’ 8B β’ Updated β’ 67 β’ 7
AQ-MedAI/Diver-GroupRank-32B
Text Ranking β’ 33B β’ Updated β’ 152 β’ 3
AQ-MedAI/Diver-Retriever-4B-1020
Text Ranking β’ 4B β’ Updated β’ 361 β’ 6
AQ-MedAI/Diver-Retriever-0.6B
Text Ranking β’ 0.6B β’ Updated β’ 328 β’ 7
AQ-MedAI/Diver-Retriever-1.7B
Text Ranking β’ 2B β’ Updated β’ 52 β’ 2
AQ-MedAI/MedResearcher-R1-32B
Text Generation β’ 33B β’ Updated β’ 69 β’ β’ 32