| Equivariant contrastive learning R Dangovski, L Jing, C Loh, S Han, A Srivastava, B Cheung, P Agrawal, ... arXiv preprint arXiv:2111.00899, 2021 | 139 | 2021 |
| Compositional foundation models for hierarchical planning A Ajay, S Han, Y Du, S Li, A Gupta, T Jaakkola, J Tenenbaum, L Kaelbling, ... Advances in Neural Information Processing Systems 36, 22304-22325, 2023 | 33 | 2023 |
| Yilun Du, Shuang Li, Abhi Gupta, Tommi Jaakkola, Josh Tenenbaum, Leslie Kaelbling, Akash Srivastava, and Pulkit Agrawal. Compositional foundation models for hierarchical planning A Ajay, S Han arXiv preprint arXiv:2309.08587 7, 2023 | 31 | 2023 |
| Estimating the density ratio between distributions with high discrepancy using multinomial logistic regression A Srivastava, S Han, K Xu, B Rhodes, MU Gutmann arXiv preprint arXiv:2305.00869, 2023 | 16 | 2023 |
| Gage MPC: bypassing residual function leakage for non-interactive MPC G Almashaqbeh, F Benhamouda, S Han, D Jaroslawicz, T Malkin, A Nicita, ... Cryptology ePrint Archive, 2021 | 16 | 2021 |
| Value augmented sampling for language model alignment and personalization S Han, I Shenfeld, A Srivastava, Y Kim, P Agrawal arXiv preprint arXiv:2405.06639, 2024 | 13 | 2024 |
| not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution S Han, A Srivastava, C Hurwitz, P Sattigeri, DD Cox arXiv preprint arXiv:2009.04433, 2020 | 9 | 2020 |
| On the importance of calibration in semi-supervised learning C Loh, R Dangovski, S Sudalairaj, S Han, L Han, L Karlinsky, M Soljacic, ... arXiv preprint arXiv:2210.04783, 2022 | 8 | 2022 |
| Multi-symmetry ensembles: improving diversity and generalization via opposing symmetries C Loh, S Han, S Sudalairaj, R Dangovski, K Xu, F Wenzel, M Soljacic, ... International Conference on Machine Learning, 22614-22630, 2023 | 6 | 2023 |
| Predicting the accuracy of neural networks from final and intermediate layer outputs C DeChant, S Han, H Lipson ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena, 2019 | 6 | 2019 |
| Constructive assimilation: Boosting contrastive learning performance through view generation strategies L Han, S Han, S Sudalairaj, C Loh, R Dangovski, F Deng, P Agrawal, ... arXiv preprint arXiv:2304.00601, 2023 | 4 | 2023 |
| 3D distributed deep learning framework for prediction of human intelligence from brain MRI S Han, Y Zhang, Y Ren, J Posner, S Yoo, J Cha Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and …, 2020 | 2 | 2020 |
| Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs A Pareja, NS Nayak, H Wang, K Killamsetty, S Sudalairaj, W Zhao, S Han, ... arXiv preprint arXiv:2412.13337, 2024 | 1 | 2024 |
| Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers S Han, J Song, J Gore, P Agrawal arXiv preprint arXiv:2412.12276, 2024 | | 2024 |
| Training a Large-Scale 3D Convolutional Neural Network Predicting Human Intelligence in Adolescent Brain Cognitive Development Study S Han, Y Zhang, Y Ren, S Yoo, J Cha | | 2022 |
| Education Massachusetts Institute of Technology September 2019-Present Ph. D. in Electrical Engineering and Computer Science GPA: 5.00/5.00 MIT Presidential fellowship A Majumdar, A Ajay, X Zhang, P Putta, S Yenamandra, M Henaff, S Silwal, ... University of California, Berkeley 2017, 2013 | | 2013 |
| Training Mice to Compete with Elephants: A Guide for Customizing Small-Sized LLMs on Knowledge and Skills Data A Pareja, NS Nayak, H Wang, K Killamsetty, S Sudalairaj, W Zhao, S Han, ... The Thirteenth International Conference on Learning Representations, 0 | | |
| Value Augmented Sampling: Predict Your Rewards To Align Language Models S Han, I Shenfeld, A Srivastava, Y Kim, P Agrawal ICLR 2024 Workshop on Reliable and Responsible Foundation Models, 0 | | |
| On Assimilating Learned Views in Contrastive Learning L Han, S Han, S Sudalairaj, C Loh, R Dangovski, P Agrawal, DN Metaxas, ... | | |
| Scaling Densities For Improved Density Ratio Estimation A Srivastava, S Han, B Rhodes, K Xu, MU Gutmann | | |
Akash SrivastavaMIT, IBM Research, University of Edinburghmit.edu의 이메일 확인됨
