Aman Gupta

Hi! I am a Machine Learning Master's student in the School of Computer Science at Carnegie Mellon University. I am currently advised by Prof. Graham Neubig on research areas related to long-context modeling, personalization, and dialog systems.

Previously, I was an undergraduate student at IIT Delhi, where I completed my Bachelor's in Computer Science and Engineering. I have worked with several research groups at IIT Delhi: the Computer Vision Group with Prof. Chetan Arora, ACT4D with Prof. Aaditeshwar Seth, and the Systems Group with Prof. Abhilash Jindal.

Email  /  CV  /  Bio  /  Google Scholar  /  Twitter  /  Github

profile photo

Research Areas

I am currently interested in research directions related to personalization of long context dialogs. Previously, I have worked on research related to high-resolution computer vision tasks (using satellite and mammography images) and developing efficient ML workflows. I am always excited to exchange research perspectives and hop on to new research endeavors. If you are interested, reach out via email!

Publications

DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems
Aman Gupta, Anirudh Ravichandran, Ziji Zhang, Swair Shah, Anurag Beniwal, Narayanan Sadagopan
NeurIPS - Open World Agents, 2024
Code Coming Soon / bibtex
Reactive Dataflow for Inflight Error Handling in ML Workflows
Abhilash Jindal, Kaustubh Beedkar, Vishal Singh, Jawahar Nausheen Mohammed, Tushar Singla, Aman Gupta, Keerti Choudhary
DEEM Sigmoid, 2024
Code / bibtex
Ultra-high resolution, multi-scale, context-aware approach for detection of small cancers on mammography
Krithika Rangarajan, Aman Gupta, Saptarshi Dasgupta, Uday Marri, Arun Kumar Gupta, Smriti Hari, Subhashis Banerjee, Chetan Arora
Nature Journal, 2022
Code / bibtex
Tracking Socio-economic Development in Rural India Over Two Decades Using Satellite Imagery
Anant Gulgulia, Aman Gupta, Akshay P Sarashetti, Aaditya Sinha, Aaditeshwar Seth,
ACM Compass, 2023
Code / Curated Dataset / Presentation / bibtex

Credits for the source code