activity
20242026
collaborators

7 papers

cs.LG2026

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…

cs.AI2025

Approximating Human Preferences Using a Multi-Judge Learned System

Eitán Sprejer, Fernando Avalos, Augusto Bernardi +3

Aligning LLM-based judges with human preferences is a significant challenge, as they are difficult to calibrate and often suffer from rubric sensitivity, bias, and instability. Ove…

cs.AI2025

Position: Require Frontier AI Labs To Release Small "Analog" Models

Shriyash Upadhyay, Chaithanya Bandi, Narmeen Oozeer +1

Recent proposals for regulating frontier AI models have sparked concerns about the cost of safety regulation, and most such regulations have been shelved due to the safety-innovati…

cs.LG2025

Distribution-Aware Feature Selection for SAEs

Narmeen Oozeer, Nirmalendu Prakash, Michael Lan +2

Sparse autoencoders (SAEs) decompose neural activations into interpretable features. A widely adopted variant, the TopK SAE, reconstructs each token from its K most active latents.…

cs.CY2025

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models

Philip Quirke, Narmeen Oozeer, Chaithanya Bandi +8

This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and…

cs.AI2025

Activation Space Interventions Can Be Transferred Between Large Language Models

Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash +3

The study of representation universality in AI models reveals growing convergence across domains, modalities, and architectures. However, the practical applications of representati…