Hi, I'm Sruthi! I enjoy learning about mathematically motivated ideas. My current research is in reinforcement learning for large language models at Amazon AGI, where I both develop new ideas and turn them into implementations backed by optimal infrastructure. Before that, I did my Ph.D. at IISc Bangalore with Prof. Anand Louis on machine learning algorithms with provable fairness guarantees, supported by the Google PhD Fellowship in Algorithms, Optimizations, and Markets, and the Microsoft Research India PhD Award.

LLM post-trainingreinforcement learningfairnessrankingoptimization
Google Scholar · DBLP · GitHub · LinkedIn
Sruthi Gorantla

News

Publications

LLM Post-Training

  1. SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning.
    Salman Rahman, Sruthi Gorantla, Arpit Gupta, Swastik Roy, Nanyun Peng, Yang Liu.
    Under submission
  2. The Role of Preference Data and Unembeddings in the Convergence Rate of DPO.
    Gayathri Chandran, Sai Soumya Nalli, Sruthi Gorantla, Amit Deshpande, Anand Louis.
    ARLET Workshop, NeurIPS 2025
  3. Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs.
    Sruthi Gorantla, Aditya Rawal, Devamanyu Hazarika, Kaixiang Lin, Mingyi Hong, Mahdi Namazifar.
    EMNLP 2025

Fairness in Ranking

  1. Pairwise Sample Complexity for Fair Active Ranking with Cascaded Norm Objectives.
    Sruthi Gorantla, Sara Ahmadian.
    KDD 2025
  2. Optimizing Group-Fair Plackett-Luce Ranking Models for Relevance and Ex-Post Fairness.
    Sruthi Gorantla, Eshaan Bhansali, Amit Deshpande, Anand Louis.
    SIGIR 2024 · github
  3. Sampling Individually-Fair Rankings that are Always Group-Fair.
    Sruthi Gorantla*, Anay Mehrotra*, Amit Deshpande, Anand Louis (* equal contribution).
    AIES 2023
  4. Sampling Ex-Post Group-Fair Rankings.
    Sruthi Gorantla, Amit Deshpande, Anand Louis.
    IJCAI 2023 · github
  5. On the Problem of Underranking in Group-Fair Ranking.
    Sruthi Gorantla, Amit Deshpande, Anand Louis.
    ICML 2021 · github

Fairness in Clustering

  1. Socially Fair Center-Based and Linear Subspace Clustering.
    Sruthi Gorantla*, Kishen N. Gowda*, Amit Deshpande, Anand Louis (* equal contribution).
    ECML-PKDD 2023 · github

AI for Healthcare

  1. Increasing Impact of Mobile Health Programs: SAHELI for Maternal and Child Care.
    Shresth Verma, Gargi Singh, Aditya Mate, Paritosh Verma, Sruthi Gorantla, Neha Madhiwalla, Aparna Hegde, Divy Thakkar, Manish Jain, Milind Tambe, Aparna Taneja.
    IAAI 2023 (Best Innovative Application Award)
  2. Multi-disease Predictive Analytics: A Clinical Knowledge-aware Approach.
    Lin Qiu, Sruthi Gorantla, Vaibhav Rajan, Bernard C. Y. Tan.
    ACM TMIS 2021

Sentiment Analysis & NLP

  1. CASCADE: Contextual Sarcasm Detection in Online Discussion Forums.
    Devamanyu Hazarika, Soujanya Poria, Sruthi Gorantla, Erik Cambria, Roger Zimmermann, Rada Mihalcea.
    COLING 2018
  2. Self-Attentive Feature-level Fusion for Multimodal Emotion Detection.
    Devamanyu Hazarika, Sruthi Gorantla, Soujanya Poria, Roger Zimmermann.
    MIPR 2018
  3. Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining.
    Devamanyu Hazarika, Rajiv Bajpai, Kunal Singh, Sruthi Gorantla, Erik Cambria, Roger Zimmermann.
    CICLing 2018

Miscellaneous

  1. Biologically Plausible Neural Networks via Evolutionary Dynamics and Dopaminergic Plasticity.
    Sruthi Gorantla, Anand Louis, Christos H. Papadimitriou, Santosh Vempala, Naganand Yadati.
    NeurIPS Workshop 2020

Awards

Education

  • 2020 – 2025 Ph.D., Computer Science, Indian Institute of Science (IISc) Bangalore. Advisor: Prof. Anand Louis.
  • 2017 – 2019 M. Tech., Computer Science, Computer Science and Automation (CSA), IISc Bangalore.
  • 2013 – 2017 B.Tech., Computer Science, NIT Warangal.