| Stance detection in web and social media: a comparative study S Ghosh, P Singhania, S Singh, K Rudra, S Ghosh Experimental IR Meets Multilinguality, Multimodality, and Interaction: 10th …, 2019 | 107 | 2019 |
| A hybrid tensor-expert-data parallelism approach to optimize mixture-of-experts training S Singh, O Ruwase, AA Awan, S Rajbhandari, Y He, A Bhatele Proceedings of the 37th International Conference on Supercomputing, 203-214, 2023 | 21 | 2023 |
| Be like a goldfish, don't memorize! mitigating memorization in generative llms A Hans, J Kirchenbauer, Y Wen, N Jain, H Kazemi, P Singhania, S Singh, ... Advances in Neural Information Processing Systems 37, 24022-24045, 2025 | 16 | 2025 |
| AxoNN: An asynchronous, message-driven parallel framework for extreme-scale deep learning S Singh, A Bhatele 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS …, 2022 | 16 | 2022 |
| Loki: Low-rank keys for efficient sparse attention P Singhania, S Singh, S He, S Feizi, A Bhatele Advances in Neural Information Processing Systems 37, 16692-16723, 2025 | 14 | 2025 |
| A survey and empirical evaluation of parallel deep learning frameworks D Nichols, S Singh, SH Lin, A Bhatele arXiv preprint arXiv:2111.04949, 2021 | 10* | 2021 |
| Inducing Cooperation in Multi-Agent Games Through Status-Quo Loss P Badjatiya, M Sarkar, A Sinha, S Singh, N Puri, B Krishnamurthy arXiv preprint, 2020 | 9* | 2020 |
| Exploiting sparsity in pruned neural networks to optimize large model training S Singh, A Bhatele 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS …, 2023 | 8 | 2023 |
| PySchedCL: Leveraging Concurrency in Heterogeneous Data-Parallel Systems A Ghose, S Singh, V Kulaharia, L Dokara, S Maity, S Dey IEEE Transactions on Computers 71 (9), 2234-2247, 2021 | 4 | 2021 |
| Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach J Geiping, S McLeish, N Jain, J Kirchenbauer, S Singh, BR Bartoldson, ... arXiv preprint arXiv:2502.05171, 2025 | 3 | 2025 |
| A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs arXiv preprint arXiv:2305.13525, 2023 | 3* | 2023 |
| HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages A Chaturvedi, D Nichols, S Singh, A Bhatele arXiv preprint arXiv:2412.15178, 2024 | 1 | 2024 |
| Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers S Singh, P Singhania, A Ranjan, J Kirchenbauer, J Geiping, Y Wen, ... SC24: International Conference for High Performance Computing, Networking …, 2024 | 1 | 2024 |
| Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization S Singh, Z Sating, A Bhatele arXiv preprint arXiv:2310.12298, 2023 | 1 | 2023 |
| Gemstones: A Model Suite for Multi-Faceted Scaling Laws S McLeish, J Kirchenbauer, DY Miller, S Singh, A Bhatele, M Goldblum, ... arXiv preprint arXiv:2502.06857, 2025 | | 2025 |
| Eve: Less Memory, Same Might A Tomar, S Singh, T Goldstein, A Bhatele | | 2024 |
| Creating Code LLMs for HPC: It’s LLMs All the Way Down A Chaturvedi, D Nichols, S Singh, A Bhatele Memory (MB) 4011 (7228), 14927, 0 | | |
Abhinav BhateleAssociate Professor of Computer Science, University of Maryland, College ParkПотвърден имейл адрес: cs.umd.edu
