Ben

benfielding's activity

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

commented 3 papers about 2 months ago

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

Paper • 2509.08721 • Published Sep 10 • 672 •

53

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

Paper • 2509.08721 • Published Sep 10 • 672 •

53

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

Paper • 2509.08721 • Published Sep 10 • 672 •

53

authored a paper about 2 months ago

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

Paper • 2509.08721 • Published Sep 10 • 672

updated a collection 2 months ago

Papers

Collection

6 items • Updated Sep 11 • 6

upvoted a paper 2 months ago

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

Paper • 2509.08721 • Published Sep 10 • 672

commented a paper 2 months ago

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

Paper • 2509.08721 • Published Sep 10 • 672 •

53

updated a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754521334

Updated Aug 6 • 1

published a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754521334

Updated Aug 6 • 1

updated a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754503572

Updated Aug 6

published a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754503572

Updated Aug 6

updated a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754495991

Updated Aug 6

published a model 3 months ago

benfielding/blockassist-bc-whiskered_howling_kiwi_1754495991

Updated Aug 6

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

Papers

Collection

6 items • Updated Sep 11 • 6

upvoted a paper 5 months ago

All is Not Lost: LLM Recovery without Checkpoints

Paper • 2506.15461 • Published Jun 18 • 37

updated a collection 5 months ago

Papers

Collection

6 items • Updated Sep 11 • 6

commented a paper 5 months ago

All is Not Lost: LLM Recovery without Checkpoints

Paper • 2506.15461 • Published Jun 18 • 37 •

2

liked a model 5 months ago

Gensyn/Qwen2.5-1.5B-Instruct

Text Generation • 2B • Updated Apr 4 • 37.7k • • 13

upvoted a paper 5 months ago

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

Paper • 2502.19913 • Published Feb 27 • 4