1 citations · 1 across the 13 of their papers we have counts for
4 papers · 1 filter
Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering
Narmeen Oozeer, Shivam Raval, Philip Quirke +4
Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as…
MoE Lens -- An Expert Is All You Need
Marmik Chaudhari, Idhant Gulati, Nishkal Hundia +2
Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to lim…
DreamReader: An Interpretability Toolkit for Text-to-Image Models
Nirmalendu Prakash, Narmeen Oozeer, Michael Lan +6
Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques.…
Spectral Superposition: A Theory of Feature Geometry
Georgi Ivanov, Narmeen Oozeer, Shivam Raval +3
Neural networks represent more features than they have dimensions via superposition, forcing features to share representational space. Current methods decompose activations into sp…