LLM-Security - a admarcosai Collection

admarcosai 's Collections

Function Calling Datasets

HCI

Position Papers

Coding

Reasoning | Planning

Alignment: FineTuning-Preference

Data Efficiency

Survey

Efficient Inference

Libraries and Framworks

Preference Dataset

Function Calling Dataset

Model Architectures

Serving

LMMM

LLM Pretraining

Models

Self-Learning AI

XAI

Efficient-Continuous Training

ParadigmShift-Inquiry

AI UX

InContext Learning

Efficient Training

LLM x Symbolics

Tool Use | Function Calling

Quantization | Compression

Math

LLM x Animation

Memory

Modality: Video

3D - AI

Mambas and LLM-AltArch

LLM-Security

updated Jan 13, 2024

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Paper • 2401.05566 • Published Jan 10, 2024 • 30