Samuel Lewis-Lim PRO

Samll's activity

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

updated a collection 4 days ago

efficient-reasoning

Collection

Models from "Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability". • 10 items • Updated 4 days ago • 2

submitted a paper to Daily Papers 4 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Paper • 2610.03509 • Published 7 days ago • 17

upvoted a paper 7 days ago

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

Paper • 2609.39827 • Published 9 days ago • 13

updated a collection 7 days ago

efficient-reasoning

Collection

Models from "Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability". • 10 items • Updated 4 days ago • 2

updated 2 models 7 days ago

Samll/olmo3-7b-think-l1

Updated 7 days ago • 13

Samll/olmo3-7b-think-glp

Updated 7 days ago • 13

published a model 7 days ago

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

Text Generation • 7B • Updated 7 days ago • 169

updated 3 models 7 days ago

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

Text Generation • 7B • Updated 7 days ago • 169

Samll/qwen3-8b-l1

Updated 7 days ago • 9

Samll/qwen3-8b-glp

Updated 7 days ago • 11

published a model 7 days ago

Samll/qwen3-8b-thinkprune-b3000

Text Generation • 8B • Updated 7 days ago • 172

updated a model 7 days ago

Samll/qwen3-8b-thinkprune-b3000

Text Generation • 8B • Updated 7 days ago • 172