Inversion Lab for AI Safety

AI & ML interests

Interpretability of Language Models and Multi-Agent Safety

Recent Activity

lgalke  authored a paper 7 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

lgalke  authored a paper 7 months ago

Guarded Query Routing for Large Language Models

lgalke  authored a paper 10 months ago

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

View all activity

Team members 1