Samuel Lewis-Lim PRO

Samll's activity

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

updated a collection 11 days ago

efficient-reasoning

Collection

Models from "Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability". • 10 items • Updated 11 days ago • 2

submitted a paper to Daily Papers 11 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Paper • 2610.03509 • Published 14 days ago • 21

upvoted a paper 14 days ago

Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior

Paper • 2609.39827 • Published 16 days ago • 13

updated a collection 14 days ago

efficient-reasoning

Collection

Models from "Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability". • 10 items • Updated 11 days ago • 2

updated 2 models 14 days ago

Samll/olmo3-7b-think-l1

Updated 14 days ago • 15

Samll/olmo3-7b-think-glp

Updated 14 days ago • 16

published a model 14 days ago

Samll/olmo3-7b-think-thinkprune-b4000

Text Generation • 7B • Updated 14 days ago • 173

updated 3 models 14 days ago

Samll/olmo3-7b-think-thinkprune-b4000

Text Generation • 7B • Updated 14 days ago • 173

Samll/qwen3-8b-l1

Updated 14 days ago • 18

Samll/qwen3-8b-glp

Updated 14 days ago • 22

published a model 14 days ago

Samll/qwen3-8b-thinkprune-b3000

Text Generation • 8B • Updated 14 days ago • 157

updated a model 14 days ago

Samll/qwen3-8b-thinkprune-b3000

Text Generation • 8B • Updated 14 days ago • 157