Scholar
Sarkar Snigdha Sarathi Das
Google Scholar ID: V7lBToMAAAAJ
PhD Student at Pennsylvania State University
Citations & Impact
Citations
623
H-index
9
i10-index
9
Publications
19
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- - Our Time-Series Forecasting technique NeXus has topped the GIFT-Eval leaderboard
- - Research on Prompt Optimization and High-Resolution image understanding covered in TechXplore and PSU News
- - Presented our work on Prompt Optimization library - GReaTerPrompt at ACL 2025 Demo
- - Two co-authored papers accepted at ICCV 2025 and COLM 2025
- - Received 2024-25 Vice Provost and Dean of the Graduate School Student Persistence Scholarship
- - One co-authored paper accepted at WOAH @ ACL 2025
- - GReaTerPrompt library accepted at ACL 2025 Demo
- - One co-authored paper on LLM usage for user intent taxonomies accepted at ACM Transactions on the Web 2025
- - Two patents from Microsoft Internship published
- - One paper on Prompt Optimization accepted at ICLR 2025
- - One co-authored paper on LLM error detection accepted at COLM 2024
- - One paper from Microsoft Research Internship on Joint Dialogue Segmentation and State Tracking accepted at ACL Findings 2024
- - One paper on Low Resource Sequence Labeling accepted at EMNLP 2023
- - One co-authored paper on Network Protocol Analysis with NLP accepted at USENIX Security ‘24
- - One co-authored paper on Few shot NER accepted at ACL 2022 Main Conference
- - One paper on AF Detection from PPG Signals accepted at IMWUT (UbiComp) 2022
- - One paper on Geo-Spatial Embedding for Housing Pricing accepted at Data Mining and Knowledge Discovery
Research Experience
- - PhD Student at Pennsylvania State University
- - Student Researcher at Google Research, working with LLM agents
- - Research Intern at Microsoft Research
- - Research Intern at Amazon Science
Education
- PhD Student at Pennsylvania State University, advised by Dr. Rui Zhang.
Background
- Research Interests: Investigating novel techniques for stronger and data-efficient Natural Language Processing, with a focus on Multi-Agent LLM, Time-Series Agents, Strategy and Prompt Optimization, Data and Parameter Efficient Fine Tuning, Zero/Few-Shot Learning.
