Publications

* denotes equal contribution. Also on Google Scholar.

2026

  1. P.3

    CaLM: Causal Language Modeling for Counterfactual World Simulations

    Havaldar, S., Jalaldoust, K., Pan, Y., and Bareinboim, E.

    Coming soon

  2. W.4

    CoBe: A Benchmark For Conversational Counterfactual Text Editing

    Raghavan, A.*, Hwang, I.*, Havaldar, S.*, Lee, K.Z., Maiti, A., Pan, Y., Wu, J., Li, M. and Bareinboim, E.

    Poster at AI4GOOD, TAE @ NeurIPS ’26

2025

  1. P.2

    Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge

    Plecko, D., Okanovic, P., Havaldar, S., Hoefler, T. & Bareinboim, E.

    Under submission at DMLR

  2. C.3

    Learning from Label Proportions and Covariate-shifted Instances

    Singh, S., Sharma, N.*, Havaldar, S.*, Saket, R., & Raghuveer, A.

    Poster at UAI ’25

2024

  1. C.2W.3

    Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

    Havaldar, S.*, Sharma, N.*, Sareen, S., Shanmugam, K., & Raghuveer, A.

    Oral Poster at ICLR ’24 & Oral at Regulatable-ML @ NeurIPS ’23

  2. C.1W.2

    Improving Fairness-Accuracy tradeoff with few Test Samples under Covariate Shift

    Havaldar, S.*, Chauhan, J.*, Shanmugam, K.*, Nandy, J., & Raghuveer, A.

    Spotlight Poster at AAAI ’24 & Spotlight at AFT @ NeurIPS ’23

2023

  1. P.1

    Label Differential Privacy via Aggregation

    Brahmbhatt, A., Saket, R., Havaldar, S., Nasery, A., Makhija, Y. & Raghuveer, A.

    Under submission at TMLR

2021

  1. W.1

    On the Benefits of Defining Vicinal Distributions in Latent Space

    Mangla, P., Singh, V., Havaldar, S., & Balasubramanian, V.

    Best Paper Best Paper @ AML-CV @ CVPR ’21; presented at RobustML and RAI (ICLR ’21)