| AxFormer: Accuracy-driven approximation of transformers for faster, smaller and more accurate NLP models A Nagarajan, S Sen, JR Stevens, A Raghunathan 2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022 | 9* | 2022 |
| Efficient ensembles of graph neural networks A Nagarajan, JR Stevens, A Raghunathan Proceedings of the 59th ACM/IEEE Design Automation Conference, 187-192, 2022 | 8 | 2022 |
| FASTRAIN-GNN: Fast and Accurate Self-Training for Graph Neural Networks A Nagarajan, A Raghunathan Transactions on Machine Learning Research, 2023 | 2 | 2023 |
| TokenDrop+ BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models A Nagarajan, A Raghunathan Findings of the Association for Computational Linguistics: EMNLP 2023, 11682 …, 2023 | 1 | 2023 |
| GENERATING PROGRAM BINARIES FOR A TRANSFORMER TO PROCESS SEQUENCE CONCATENATIONS HAVING DIFFERENT INPUT LENGTHS S Venkataramani, S Sen, A Nagarajan, V Srinivasan, S Krithivasan US Patent App. 18/344,487, 2025 | | 2025 |
| REUSING WEIGHTS AND BIASES IN AN ARTIFICIAL INTELLIGENCE ACCELERATOR FOR A NEURAL NETWORK FOR DIFFERENT MINIBATCH SIZES OF INFERENCES S Venkataramani, M Schaal, S Sen, A Nagarajan, V Srinivasan, S Ramji US Patent App. 18/344,491, 2025 | | 2025 |
| Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks A Nagarajan, A Raghunathan Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024 | | 2024 |
| Efficient Batched Inference in Conditional Neural Networks S Selvam, A Nagarajan, A Raghunathan IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024 | | 2024 |
| Optimizing Accuracy-Efficiency Tradeoffs in Emerging Neural Workloads A Nagarajan Purdue University Graduate School, 2023 | | 2023 |
Anand RaghunathanSilicon Valley Chair Professor of Electrical and Computer Engineering, Purdue UniversityAdresse e-mail validée de purdue.edu