Parshin Shojaee | Virginia Tech

About Me

I’m a third-year CS PhD student at Virginia Tech, advised by Prof. Chandan Reddy. I am also currently a research intern at Apple. My primary research topic is AI for symbolic generation (code, math, reasoning) and its potential for scientific discovery. I mostly focus on developing better algorithms for language models to handle symbolic reasoning and scientific discovery tasks, while studying their current limitations. During the course of my PhD, I have also pursued summer AI/ML research internships at Adobe (2024) and Gilead Sciences (2022). Prior to starting my PhD, I completed my MS in Operations Research at Virginia Tech, and obtained my BS from Sharif University of Technology.

If you’re interested in my research, would like to discuss relevant topics, or explore potential collaborations, please feel free to get in touch :) - I am best reached by email at parshinshojaee@vt.edu

News

[Feb 2025] Excited to start my research internship at Apple!
[Feb 2025] I’ll be presenting our tutorial of “Symbolic Regression: Towards Interpretability and Automated Scientific Discovery” at AAAI 2025. Looking forward to seeing everyone in Philadelphia!
[Jan 2025] Our LLM-SR paper on LLM agents + evolutionary search for scientific discovery is accepted to ICLR 2025 as Oral!
[Dec 2024] My Adobe internship project Federated RAG for Multi-Source QA is now on arxiv.
[Nov 2024] Our position paper on AI for Scientific Discovery is accepted to AAAI 2025!
[May. 2024] I’m excited to start my internship at Adobe in this summer!
[Jan. 2024] Our SNIP (Symbolic-Numeric Pretraining) paper on mathematical discovery with multi-modal latent reasoning is accepted to ICLR 2024 as Spotlight!
[Dec. 2023] I will be at NeurIPS 2023 in New Orleans, presenting our TPSR paper. Please reach out if you want to chat!
[Sep. 2023] Our paper TPSR on mathematical discovery with language model + MCTS planning is accepted to NeurIPS 2023!

Selected Publications

ICLR 2025

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

Parshin Shojaee*, Kazem Meidani*, Shashank Gupta, Amir Barati Farimani, Chandan K. Reddy (*Equal Contribution)

International Conference on Learning Representations (ICLR 2025).

PDF Code Oral (top 1%)

ICLR 2024

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

Kazem Meidani*, Parshin Shojaee*, Chandan K. Reddy, Amir Barati Farimani (*Equal Contribution)

International Conference on Learning Representations (ICLR 2024).

PDF Code Spotlight (top 5%)

NeurIPS 2023

Transformer-based Planning for Symbolic Regression

Parshin Shojaee*, Kazem Meidani*, Amir Barati Farimani, Chandan K. Reddy (*Equal Contribution)

Advances in Neural Information Processing Systems (NeurIPS 2023).

PDF Video Code

TMLR

Execution-based Code Generation using Deep Reinforcement Learning

Parshin Shojaee, Aneesh Jain, Sindhu Tipirneni, Chandan K. Reddy

Transactions on Machine Learning Research (TMLR), 2023.

PDF Video Code

AAAI 2025

Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges

Chandan K. Reddy, Parshin Shojaee

The Association for the Advancement of Artificial Intelligence (AAAI 2025).

PDF

COLING 2025

Federatd Retrieval Augmented Generation for Multi-Product Question Answering

Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, Yunyao Li

International Conference on Computational Linguistics (COLING 2025, Industry Track)

PDF

Services

Conference Reviewer: ICML 2025, AISTAT 2025, ICLR 2025, NeurIPS 2024 (Top Reviewer both Main & DB Tracks)

Journal Reviewer: Nature, TMLR, npj AI, ACM TIST

Workshop Reviewer: NeurIPS 2024 AI for Math, ICML 2024 AI for Science

A little more about me

When I’m not into AI research, I enjoy exploring all kinds of music and playing Tar and Setar instruments (think Persian guitars with their own unique twist).