Abhinav Gorantla

Abhinav Gorantla

Graduate CS Student at ASU

Abhinav Gorantla

Abhinav Gorantla is currently pursuing a Master of Science degree in Computer Science at Arizona State University, where he works as a Graduate Research and Teaching Assistant in the EMIT Lab. His research interests are machine learning, multi-objective optimization, generative AI (broadly). He also has experience as a full-stack web developer.

Abhinav has contributed to award-winning projects like CausalBench (a flexible benchmarking solution for causal ML algorithms).

Education

Experience

  • August 2024 - Now: Graduate Research Assistant at Emitlab, School of Computing and Augmented Intelligence, ASU
    • Developing an optimized algorithm for efficient Skyline retrieval in relational database systems.
    • Collaborating with researchers at CASCADE Lab to maintain and improve causalbench.org, a platform dedicated to causal discovery benchmarks.
    • Built a causal-analysis recommendation system; led end-to-end integration and serverless deployment on AWS Lambda; published at CIKM 2025.
  • August 2024 - May 2025: Graduate Teaching Assistant at Emitlab, School of Computing and Augmented Intelligence, ASU
    • Assisted in CSE515 and CSE510 graduate-level computer science courses.
  • March 2024 – August 2024: Graduate Services Assistant at Emitlab, School of Computing and Augmented Intelligence, ASU
    • Supported CASCADE Lab researchers in developing the causalbench Python package and website, establishing an end-to-end benchmarking solution for the causal machine learning community.
    • Served as a full stack developer on the CausalBench project, contributing to a comprehensive framework for benchmarking causal machine learning algorithms.
    • Optimized backend architecture for the Skysong project, enhancing data flow efficiency and achieving an 80% improvement in server response time. Reduced deployment costs by 30% by integrating AWS SageMaker.
  • April 2022 – June 2023: SDE Intern at Webknot Technologies Pvt. Ltd.
    • Revamped API endpoints within the Palette project, achieving a notable 30% reduction in response times.
    • Engineered a custom plugin for Sisense BI software, enabling the seamless display of geojson data on a GeoJSON layer atop maps rendered via DeckGL.
    • Fine-tuned data flow for the DeckGL plugin within Sisense by elevating the efficiency of JAQL queries, ensuring a smoother and more responsive user experience.

Publications

  1. [Introducing CausalBench: A Flexible Benchmark Framework for Causal Analysis and Machine Learning] · Paper · Website

Community Service & Outreach

  • Student Volunteer, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025)
  • Tutorial Presenter, KDD 2025 — CausalBench: Causal Learning Research Streamlined · Paper · Video (YouTube)

Projects

  1. Research Publications Analysis tool
    • Proposed an architecture and built a research publications analysis tool for ASU. This tool was built as a web application which could fetch research paper information affiliated with ASU using SCOPUS APIs and perform a text analysis on their abstracts.
    • Reduced the server response time by 80% and improved the user experience by integrating RabbitMQ message queues in the system.
    • Tech stack used: ReactJS, NodeJS, Python-FastAPI, RabbitMQ, MongoDB, AWS S3, AWS Sagemaker, OpenAI APIs.
  2. Multimodal Image Retrieval System using Advanced Feature Analysis and Search Techniques
    • Developed a Python-based image retrieval engine encompassing feature extraction from Caltech101 dataset images, latent semantics computation, clustering, and classification.
    • Employed Locality Sensitive Hashing to index image features, optimizing nearest neighbor searches and ensuring scalability for expansive image datasets.
  3. Enhancing Diversity in the LLM Modulo Framework through Multi-Response Generation
    • Developed the Diversified LLM Modulo framework to address looping and redundancy in the LLM Modulo framework.
    • Improved the performance of the LLM Modulo Framework on Planning tasks. Tested my framework on the Google Deepmind Natural Plan benchmark and achieved a performance improvement of 300% by increasing the diversity of LLM (Large Language Model) Responses.