AQ-MedAI/PulseMind-72B
Updated
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/Diver-Retriever-4B
Text Ranking
•
4B
•
Updated
•
3.5k
•
22
AQ-MedAI/Qwen3-VL-8B-Instruct-eagle3
0.4B
•
Updated
•
21
AQ-MedAI/Qwen2.5-VL-72B-Instruct-eagle3
1B
•
Updated
•
19
•
1
AQ-MedAI/Ling-Flash-2.0-eagle3
0.4B
•
Updated
•
2
•
3
AQ-MedAI/Kimi-K2-Instruct-eagle3
1B
•
Updated
•
72
•
9
AQ-MedAI/Diver-GroupRank-7B
Text Ranking
•
8B
•
Updated
•
18
•
7
AQ-MedAI/Diver-GroupRank-32B
Text Ranking
•
33B
•
Updated
•
212
•
3
AQ-MedAI/Diver-Retriever-4B-1020
Text Ranking
•
4B
•
Updated
•
493
•
3
AQ-MedAI/Diver-Retriever-0.6B
Text Ranking
•
0.6B
•
Updated
•
440
•
6
AQ-MedAI/Diver-Retriever-1.7B
Text Ranking
•
2B
•
Updated
•
222
•
2
AQ-MedAI/MedResearcher-R1-32B
Text Generation
•
33B
•
Updated
•
16
•
32