AI Safety - a PeppePasti Collection

PeppePasti 's Collections

LLMs

Multimodal LLMs

RAG

Agents

Reinforcement learning (RL)

Liquid Neural Networks

Diffusion Models

Text Embedding & Rankers

Computer Vision

Multi-lingual Training Language Models

NLP (no LLM related)

Interesting Stuffs

AI Safety

updated Sep 4, 2024

Improving Alignment and Robustness with Short Circuiting

Paper • 2406.04313 • Published Jun 6, 2024 • 1
Efficient Detection of Toxic Prompts in Large Language Models

Paper • 2408.11727 • Published Aug 21, 2024 • 12
Diffusion Policy Policy Optimization

Paper • 2409.00588 • Published Sep 1, 2024 • 20