About Me
I’m a senior at UIUC studying Computer Science, and I work on reasoning in Large Language Models. I’m fortunate to be advised by Professor Dilek Hakkani-Tur, and Professor Heng Ji.
I’ve previously interned at Yahoo Research. I’m currently working on some very interesting projects at Rivian.
DM me on X, I’m pretty active there, or drop me an email at sumuk[atsymbol]sumuk.org.
Research
- Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models Paper
- Sumuk Shashidhar, Abhinav Chinta, Vaibhav Sahai, Zhenhailong Wang, and Heng Ji. 2023. Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9070–9084, Singapore. Association for Computational Linguistics.
- [ Under Review ] Unsupervised Human Preference Learning
- [ Under Review ] Token Efficient Deep Conversational Reasoning With ConvoDAGs
- [ Under Review ] Verifiers For Superior Code Generation
- SpaceKraft: A Vision Language Approach For Interior Design Inpainting. Paper
- Ideal Prompt Generation for Text-Conditional Image Synthesis from Large Text Corpora. Paper
- Decentralisation of Election Processes in Developing Nations Paper
Paper Presentations
Work
- Sep 2023 - Present: Rivian
- NDA. New Features.
- May 2023 - Aug 2023: Software Engineering Intern @ Yahoo
- ML pipeline for ad pricing and performance monitoring on demand-side platform
- May 2022 - May 2023: Software Engineering Intern @ AGCO
- Supply chain analytics for risk forecasting
- Jun 2021 - May 2022: Software Engineering Intern @ QuantIllinois
- High frequency trading infrastructure and anomaly detection
- Jun 2020 - Dec 2020: Data Science Intern @ YLAC
- Data based mobilization of advertising funds on instagram to reverse sentiment.
- Jun 2019 - Mar 2020: Software Engineering Intern @ Cisco:
- Internal platform development with microservices and caching