-
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 661 -
All is Not Lost: LLM Recovery without Checkpoints
Paper • 2506.15461 • Published • 38 -
NoLoCo: No-all-reduce Low Communication Training Method for Large Models
Paper • 2506.10911 • Published • 8 -
Verde: Verification via Refereed Delegation for Machine Learning Programs
Paper • 2502.19405 • Published • 8
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 • 661 -
All is Not Lost: LLM Recovery without Checkpoints
Paper • 2506.15461 • Published • 38 -
NoLoCo: No-all-reduce Low Communication Training Method for Large Models
Paper • 2506.10911 • Published • 8 -
Verde: Verification via Refereed Delegation for Machine Learning Programs
Paper • 2502.19405 • Published • 8
RL Swarm is an open source system for peer-to-peer gossip-based reinforcement learning over the internet.