activity
20242026
collaborators

12 papers

cs.LG2026

Multi-component Causal Tracing in Large Language Models

Zirui Yan, Dennis Wei, Dmitriy A. Katz +2

Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computa…

cs.RO2025

ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learning

Pranamya Kulkarni, Puranjay Datta, Burak Varıcı +3

Causal representation learning (CRL) has emerged as a powerful unsupervised framework that (i) disentangles the latent generative factors underlying high-dimensional data, and (ii)…

cs.LG2025

Score-based Causal Representation Learning: Linear and General Transformations

Burak Varıcı, Emre Acartürk, Karthikeyan Shanmugam +2

This paper addresses intervention-based causal representation learning (CRL) under a general nonparametric latent causal model and an unknown transformation that maps the latent va…

stat.ML2025

Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms

Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2

The objective of canonical multi-armed bandits is to identify and repeatedly select an arm with the largest reward, often in the form of the expected value of the arm's probability…

cs.LG2025

Real-Time Risky Fault-Chain Search using Time-Varying Graph RNNs

Anmol Dwivedi, Ali Tajer

This paper introduces a data-driven graphical framework for the real-time search of risky cascading fault chains (FCs) in power-grids, crucial for enhancing grid resiliency in the…

stat.ML2025

Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms

Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2

This paper introduces a general framework for risk-sensitive bandits that integrates the notions of risk-sensitive objectives by adopting a rich class of distortion riskmetrics. Th…