Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
AI Safety Research's picture
23 44 287

AI Safety Research

AISafety
t-edward's profile picture Architectures's profile picture Viewegger's profile picture
·
https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

liked a model 2 days ago
stepfun-ai/Step-3.5-Flash
upvoted a collection 2 days ago
Step-3.5-Flash
liked a dataset 6 days ago
angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
View all activity

Organizations

Hugging Face Discord Community's profile picture ML intern explorers's profile picture

AISafety 's collections 3

Model building
  • Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

    Paper • 2511.06221 • Published Nov 9, 2025 • 134
Inference efficiency
  • The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

    Paper • 2402.17764 • Published Feb 27, 2024 • 629
Safety and transparency
  • OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

    Paper • 2504.07096 • Published Apr 9, 2025 • 77
Model building
  • Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

    Paper • 2511.06221 • Published Nov 9, 2025 • 134
Safety and transparency
  • OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

    Paper • 2504.07096 • Published Apr 9, 2025 • 77
Inference efficiency
  • The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

    Paper • 2402.17764 • Published Feb 27, 2024 • 629
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs