activity
20202026
most citedStructure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families

3 citations · 6 across the 4 of their papers we have counts for

collaborators

8 papers

cs.SE20261 cited

The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes

Redacted by arXiv

This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…

cs.CL2024

Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers

Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +1

Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be eas…

cs.DS2024

Efficient Certificates of Anti-Concentration Beyond Gaussians

Ainesh Bakshi, Pravesh Kothari, Goutham Rajendran +2

A set of high dimensional points in isotropic position is said to be -anti concentrated if for every direction , the fraction of poin…

cs.CL20242 cited

On the Origins of Linear Representations in Large Language Models

Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +2

Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such l…

cs.LG2024

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

Goutham Rajendran, Simon Buchholz, Bryon Aragam +2

To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causa…

cs.LG2023

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis

Goutham Rajendran, Patrik Reizinger, Wieland Brendel +1

We investigate the relationship between system identification and intervention design in dynamical systems. While previous research demonstrated how identifiable representation lea…