Samuel Simko PRO

samuelsimko

·

AI & ML interests

AI Alignment, AI Safety

Recent Activity

published a model 3 days ago

samuelsimko/apertus-v1.5-8b-triplet-kl5-ck900

updated a model 3 days ago

samuelsimko/apertus-v1.5-8b-triplet-kl5-ck900

liked a Space 4 days ago

OPTML-Group/UnlearnCanvas-Benchmark

View all activity

Organizations

upvoted a collection 21 days ago

🇨🇭 Apertus 1.5

Fully open fused multimodal reasoning models • 2 items • Updated 22 days ago • 1

upvoted a collection 7 months ago

Tamper-Resistant Safeguards for Open-Weight LLMs

Models & datasets from the paper "Tamper-Resistant Safeguards for Open-Weight LLMs" (https://arxiv.org/pdf/2408.00761) • 9 items • Updated Feb 15, 2025 • 5

upvoted a paper 10 months ago

A Synthetic Dataset for Personal Attribute Inference

Paper • 2406.07217 • Published Jun 11, 2024 • 2

upvoted an article 11 months ago

Article

Jupyter Agents: training LLMs to reason with notebooks

+1

baptistecolle, hannayukhymenko, lvwerra

•

Sep 10, 2025

• 67

upvoted an article over 1 year ago

Article

Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM

INSAIT-Institute

•

Apr 23, 2025

• 65