I'm a fourth-year undergraduate student in the Computer Science Department at the University of Illinois, Urbana-Champaign (UIUC). I work with Prof. Alex Aiken (Stanford), Prof. Sasa Misailovic (UIUC), and Prof. Gagandeep Singh (UIUC).

Research

My research is at the intersection of Machine Learning (ML), Programming Languages (PL), Formal Methods (FM), and Systems. I am largely interested in:

- Scalable formal tools and learning-based methods for correct and secure ML-driven programming systems

- Machine learning for program synthesis, optimization, verification, and repair

Papers

▼ Scalable Formal Tools for Correct and Secure ML-Driven Programming Systems

DINGO: Constrained Inference for Diffusion LLMs
Tarun Suresh*, Debangshu Banerjee*, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025
pdf

CRANE: Reasoning with Constrained LLM Generation
Debangshu Banerjee*, Tarun Suresh*, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025
pdf

BEAVER: An Efficient Deterministic LLM Verifier
Tarun Suresh*, Nalin Wadhwa*, Debangshu Banerjee, Gagandeep Singh
In Submission
pdf

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
Shubham Ugare, Rohan Gumaste, Tarun Suresh, Gagandeep Singh, Sasa Misailovic
Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
pdf

SynCode: LLM Generation with Grammar Augmentation
Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh
Transactions on Machine Learning Research (TMLR), 2025
pdf| code

▼ Deep Learning for Program Synthesis, Optimization, Verification, and Repair

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
Tarun Suresh*, Revanth Gangi Reddy*, Yifei Xu, Zach Nussbaum, Andriy Mulyar, Brandon Duderstadt, Heng Ji
Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
pdf| blog post| code

SweRank: Software Issue Localization with Code Ranking
Revanth Gangi Reddy*, Tarun Suresh*, JaeHyeok Doo*, Ye Liu, Xuan Phi Nguyen, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Heng Ji, Shafiq Joty
In Submission
pdf| code

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
Anjiang Wei, Tarun Suresh, Jiannan Cao, Naveen Kannan, Yuheng Wu, Kai Yan, Thiago S. F. X. Teixeira, Ke Wang, Alex Aiken
Proceedings of the 2nd Conference on Language Modeling (COLM), 2025
pdf| code

SuperCoder: Assembly Program Superoptimization with Large Language Models
Anjiang Wei, Tarun Suresh, Huanmi Tan, Yinglun Xu, Gagandeep Singh, Ke Wang, Alex Aiken
The 4th Deep Learning for Code Workshop (DL4C) at Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025
pdf

InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?
Anjiang Wei, Tarun Suresh, Tianran Sun, Haoze Wu, Ke Wang, Alex Aiken
In Submission
pdf

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
Anjiang Wei*, Yuheng Wu*, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
pdf

VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
Anjiang Wei, Huanmi Tan, Tarun Suresh, Daniel Mendoza, Thiago S. F. X. Teixeira, Ke Wang, Caroline Trippel, Alex Aiken
The 4th Deep Learning for Code Workshop (DL4C) at Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025
pdf

▼ Robust and Efficient Preference-Based Reinforcement Learning

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
Yinglun Xu, Tarun Suresh, Rohan Gumaste, David Zhu, Ruirui Li, Zhengyang Wang, Haoming Jiang, Xianfeng Tang, Qingyu Yin, Monica Xiao Cheng, Qi Zheng, Chao Zhang, Gagandeep Singh
Transactions on Machine Learning Research (TMLR), 2025
pdf

Learning a Pessimistic Reward Model in RLHF
Yinglun Xu*, Hangoo Kang*, Tarun Suresh, Yuxuan Wan, Gagandeep Singh
Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) Workshop at Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025
pdf

▼ Neural Network Robustness and Verification

Relational Verification Leaps Forward with RABBit
Tarun Suresh*, Debangshu Banerjee*, Gagandeep Singh
Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2024
pdf| code

Tamper-Resistant Safeguards for Open-Weight LLMs
Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti, Tarun Suresh, Maxwell Lin, Justin Wang, Rowan Wang, Ron Arel, Andy Zou, Dawn Song, Bo Li, Dan Hendrycks, Mantas Mazeika
Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
pdf

Incremental Randomized Smoothing Certification
Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Sasa Misailovic, Gagandeep Singh
Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024
pdf| code

Is Watermarking LLM Generated Code Robust?
Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
Tiny Papers Track at Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024 (Oral Presentation)
pdf| code

Towards Continuous Verification of DNNs
Shubham Ugare, Debangshu Banerjee, Tarun Suresh, Gagandeep Singh, Sasa Misailovic
Workshop on Formal Verification and Machine Learning (WFML) at Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
pdf| code