Matteo Santelmo's picture

2 1 10

Matteo Santelmo

matsant01

·

AI & ML interests

LLM self-improvement, reasoning, AI4Science

Recent Activity

updated a dataset about 16 hours ago

matsant01/blind-spots-bench

published a dataset about 17 hours ago

matsant01/blind-spots-bench

updated a dataset 3 months ago

matsant01/countdown-v2

View all activity

Organizations

spaces 1

DiT-Edit User Study

Collect human preferences on image composition

models 9

matsant01/STEMerald-2b-4bit

Text Generation • 3B • Updated Jun 14, 2024 • 9 • 1

matsant01/STEMerald-2b

Text Generation • 3B • Updated Jun 14, 2024 • 6 • 3

matsant01/m3_sft_orca_it_base

Text Generation • 3B • Updated Jun 14, 2024 • 5

matsant01/m3_sft_it_dpo_4bit

Text Generation • 3B • Updated Jun 13, 2024 • 4

matsant01/orca_gemma_it_dpo

Text Generation • 3B • Updated Jun 13, 2024 • 2

matsant01/m3_sft_dpo

Text Generation • 3B • Updated Jun 12, 2024 • 3

matsant01/m3_sft_gemma_it

Text Generation • 3B • Updated Jun 12, 2024 • 4

matsant01/m3_sft_gemma

Text Generation • 3B • Updated Jun 12, 2024 • 2

matsant01/m3_sft_it_dpo

Text Generation • 3B • Updated Jun 12, 2024 • 2

datasets 9

matsant01/blind-spots-bench

Viewer • Updated about 16 hours ago • 245

matsant01/countdown-v2

Viewer • Updated Oct 14, 2025 • 480 • 14

matsant01/countdown

Viewer • Updated Oct 3, 2025 • 480 • 27

matsant01/sudoku-llm-eval

Viewer • Updated Oct 2, 2025 • 498 • 11

matsant01/omni-MATH-hard

Viewer • Updated Sep 19, 2025 • 173 • 7

matsant01/omni-MATH-500

Viewer • Updated Sep 18, 2025 • 500 • 7

matsant01/aime2425

Viewer • Updated Sep 4, 2025 • 60 • 17

matsant01/prime-factorization-llm

Viewer • Updated Jul 25, 2025 • 500 • 8

matsant01/llm-compression-2025-04

Viewer • Updated May 2, 2025 • 34.1k • 12