Ben

benfielding's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Paper • 2511.09780 • Published 4 days ago • 25

upvoted a paper 2 months ago

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Paper • 2509.08721 • Published Sep 10 • 673

upvoted 2 collections 5 months ago

RL Swarm

Collection

RL Swarm is an open source system for peer-to-peer gossip-based reinforcement learning over the internet. • 5 items • Updated Apr 30 • 7

Gensyn Papers

Collection

7 items • Updated 3 days ago • 6

upvoted 5 papers 5 months ago

All is Not Lost: LLM Recovery without Checkpoints

Paper • 2506.15461 • Published Jun 18 • 37

SkipPipe: Partial and Reordered Pipelining Framework for Training LLMs in Heterogeneous Networks

Paper • 2502.19913 • Published Feb 27 • 4

Verde: Verification via Refereed Delegation for Machine Learning Programs

Paper • 2502.19405 • Published Feb 26 • 7

HDEE: Heterogeneous Domain Expert Ensemble

Paper • 2502.19385 • Published Feb 26 • 3

NoLoCo: No-all-reduce Low Communication Training Method for Large Models

Paper • 2506.10911 • Published Jun 12 • 8