-
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 660 -
All is Not Lost: LLM Recovery without Checkpoints
Paper • 2506.15461 • Published • 37 -
NoLoCo: No-all-reduce Low Communication Training Method for Large Models
Paper • 2506.10911 • Published • 7 -
Verde: Verification via Refereed Delegation for Machine Learning Programs
Paper • 2502.19405 • Published • 7
AI & ML interests
We network together the core resource for machine intelligence to flourish alongside human intelligence https://www.gensyn.ai/research
Recent Activity
View all activity
Papers
Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
-
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 660 -
All is Not Lost: LLM Recovery without Checkpoints
Paper • 2506.15461 • Published • 37 -
NoLoCo: No-all-reduce Low Communication Training Method for Large Models
Paper • 2506.10911 • Published • 7 -
Verde: Verification via Refereed Delegation for Machine Learning Programs
Paper • 2502.19405 • Published • 7
RL Swarm is an open source system for peer-to-peer gossip-based reinforcement learning over the internet.
models
6
Gensyn/testing
Updated
•
1.48k
Gensyn/Qwen2.5-7B-Instruct
Text Generation
•
8B
•
Updated
•
48
•
•
7
Gensyn/Qwen2.5-72B-Instruct-bnb-4bit
Text Generation
•
39B
•
Updated
•
6
Gensyn/Qwen2.5-32B-Instruct-bnb-4bit
Text Generation
•
18B
•
Updated
•
5
Gensyn/Qwen2.5-1.5B-Instruct
Text Generation
•
2B
•
Updated
•
16k
•
•
14
Gensyn/Qwen2.5-0.5B-Instruct
Text Generation
•
0.5B
•
Updated
•
2.11M
•
29
datasets
0
None public yet