arxiv:2508.19827
Samuel Lewis-Lim PRO
Samll
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior published a model 7 days ago
Samll/olmo3-7b-lcpo-exact-step250 published a model 7 days ago
Samll/qwen3-4b-lcpo-exact-2gpu-step200Organizations
None yet
models 9
Samll/olmo3-7b-kimi-length-step100
Updated
Samll/qwen3-4b-thinkprune-2gpu-step200-merged
Text Generation • 4B • Updated • 131
Samll/qwen3-4b-lcpo-exact-2gpu-step200
Updated
Samll/qwen3-4b-kimi-length-2gpu-step150
Updated
Samll/olmo3-7b-lcpo-exact-step250
Updated
Samll/qwen3-8b-lcpo-exact-step300
Updated
Samll/qwen3-8b-kimi-length-step200
Updated
Samll/wild_hallu_v3-3b
Text Generation • 3B • Updated • 9
Samll/amazon_reviews_v2_llama3-3b
Text Generation • 3B • Updated • 10
datasets 20
Samll/wild_hallucinations_deepseek_factscore_chat_v2
Viewer • Updated • 3.65k • 34
Samll/wild_hallucinations_deepseek_factscore_chat
Viewer • Updated • 3.38k • 27
Samll/hotpotqa_inference_llama3-8b
Viewer • Updated • 20k • 10
Samll/wild_hallucinations_deepseek_factscore
Viewer • Updated • 1k • 30
Samll/wild_hallucinations_with_responses
Viewer • Updated • 7.92k • 38
Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions_v1
Viewer • Updated • 5.77k • 33
Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions
Viewer • Updated • 15.1k • 22
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_attn_test
Viewer • Updated • 210 • 16
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_v1
Viewer • Updated • 13.3k • 43
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances
Viewer • Updated • 22.4k • 32