Samuel Lewis-Lim PRO

Samll's activity

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

upvoted a paper about 5 hours ago

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

Paper • 2609.39827 • Published 1 day ago • 5

published 4 models 7 days ago

Samll/olmo3-7b-lcpo-exact-step250

Updated 19 days ago

Samll/qwen3-4b-lcpo-exact-2gpu-step200

Updated 17 days ago

Samll/qwen3-4b-kimi-length-2gpu-step150

Updated 17 days ago

Samll/qwen3-8b-kimi-length-step200

Updated 22 days ago

published a model 8 days ago

Samll/qwen3-8b-lcpo-exact-step300

Updated 22 days ago

published 2 models 9 days ago

Samll/qwen3-4b-thinkprune-2gpu-step200-merged

Text Generation • 4B • Updated 16 days ago • 131

Samll/olmo3-7b-kimi-length-step100

Updated 9 days ago

updated a model 9 days ago

Samll/olmo3-7b-kimi-length-step100

Updated 9 days ago

updated a model 16 days ago

Samll/qwen3-4b-thinkprune-2gpu-step200-merged

Text Generation • 4B • Updated 16 days ago • 131

updated 2 models 17 days ago

Samll/qwen3-4b-lcpo-exact-2gpu-step200

Updated 17 days ago

Samll/qwen3-4b-kimi-length-2gpu-step150

Updated 17 days ago

updated a model 19 days ago

Samll/olmo3-7b-lcpo-exact-step250

Updated 19 days ago

updated 2 models 22 days ago

Samll/qwen3-8b-lcpo-exact-step300

Updated 22 days ago

Samll/qwen3-8b-kimi-length-step200

Updated 22 days ago

upvoted a paper 28 days ago

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

Paper • 2608.29464 • Published Aug 29 • 15

upvoted a paper about 2 months ago

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility

Paper • 2608.03930 • Published Aug 4 • 10

upvoted a paper 3 months ago

MultiHashFormer: Hash-based Generative Language Models

Paper • 2606.28057 • Published Jun 26 • 23

upvoted a paper 5 months ago

Where does output diversity collapse in post-training?

Paper • 2604.16027 • Published Apr 17 • 21

upvoted a paper 8 months ago

Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

Paper • 2602.08658 • Published Feb 9 • 13