Tatiana Gaintseva
PulseAugur coverage of Tatiana Gaintseva — every cluster mentioning Tatiana Gaintseva across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI interpretability tools develop concept-specific blind spots
Researchers have identified a phenomenon where 'Activation Oracles' (AOs), models designed to interpret the internal states of other AI models, can develop concept-specific blind spots. Despite being trained on data whe…
-
New SV-Detect method accurately identifies AI-generated text
Researchers have developed a new method called SV-Detect for identifying AI-generated text, even when the text has been altered or comes from different sources. The technique utilizes "steering vectors" derived from a f…
-
MidSteer framework offers optimal affine control for generative models
Researchers have introduced MidSteer, a novel theoretical framework for concept steering in generative models. This framework builds upon the concept of affine erasure, demonstrating that existing methods for removing u…