Amrit Nagarajan

According to our database, Amrit Nagarajan authored at least 8 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Spyre: An Inference-Optimized Scalable AI Accelerator for Enterprise Workloads.

Matthew Cohen, Monodeep Kar, Swagath Venkataramani, Viji Srinivasan, Brian Veraa, Matthew M. Ziegler, Nianzheng Cao, Ashish Ranjan, Joel Silberman, Michael Guillorn, Sandra Woodward, JohnDavid Lancaster, Josh Hursey, Kyu-Hyoun Kim, Alberto Mannari, Amrit Nagarajan, Ananda Samajdar, Bahman Hekmatshoartabari, Bob Galbraith, Ching Zhou, David L. Satterfield, Gregory S. Still, Gustavo Tellez, Indira Nair, Indu Masilamanai, Jinwook Jung, Kavi Randhawa, Marcel Schaal, Martin Lutz, Paul Crumley, Philip Jacob, Prasanth Chatarasi, Radhika Jain, Sae Kyu Lee, Sanchari Sen, Sarada Krithivasan, Scot Rider, Shubham Jain, Siyu Koswatta, Thomas Roewer, Tom Gooding, Victor Ferrari, Vidhi Zalani, Zhibin Ren, Kevin Reick, Lisa Maurice, Christopher J. Gonzalez, Chris Catalino, Ryan Nett, Pong-Fei Lu, Robert M. Senger, Leland Chang

Proceedings of the IEEE International Solid-State Circuits Conference, 2026

2024

Efficient Batched Inference in Conditional Neural Networks.

Surya Selvam, Amrit Nagarajan, Anand Raghunathan

IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., November, 2024

Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks.

Amrit Nagarajan, Anand Raghunathan

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

2023

FASTRAIN-GNN: Fast and Accurate Self-Training for Graph Neural Networks.

Amrit Nagarajan, Anand Raghunathan

Trans. Mach. Learn. Res., 2023

TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models.

Amrit Nagarajan, Anand Raghunathan

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

2022

AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models.

Amrit Nagarajan, Sanchari Sen, Jacob R. Stevens, Anand Raghunathan

Proceedings of the International Joint Conference on Neural Networks, 2022

Efficient ensembles of graph neural networks.

Amrit Nagarajan, Jacob R. Stevens, Anand Raghunathan

Proceedings of the DAC '22: 59th ACM/IEEE Design Automation Conference, San Francisco, California, USA, July 10, 2022

2020

Optimizing Transformers with Approximate Computing for Faster, Smaller and more Accurate NLP Models.

Amrit Nagarajan, Sanchari Sen, Jacob R. Stevens, Anand Raghunathan

CoRR, 2020