| Why m heads are better than one: Training a diverse ensemble of deep networks S Lee, S Purushwalkam, M Cogswell, D Crandall, D Batra arXiv preprint arXiv:1511.06314, 2015 | 378 | 2015 |
| Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases S Purushwalkam, A Gupta Advances in Neural Information Processing Systems 33, 3407-3418, 2020 | 254 | 2020 |
| Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles S Lee, S Purushwalkam, M Cogswell, V Ranjan, D Crandall, D Batra Advances In Neural Information Processing Systems, 2119-2127, 2016 | 222 | 2016 |
| Task-driven modular networks for zero-shot compositional learning S Purushwalkam, M Nickel, A Gupta, MA Ranzato Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 201 | 2019 |
| The unsurprising effectiveness of pre-trained vision models for control S Parisi, A Rajeswaran, S Purushwalkam, A Gupta international conference on machine learning, 17359-17371, 2022 | 194 | 2022 |
| Diffusion model alignment using direct preference optimization B Wallace, M Dang, R Rafailov, L Zhou, A Lou, S Purushwalkam, S Ermon, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 143 | 2024 |
| Applying machine learning to identify autistic adults using imitation: An exploratory study B Li, A Sharma, J Meng, S Purushwalkam, E Gowen PloS one 12 (8), e0182652, 2017 | 106 | 2017 |
| Audio-visual floorplan reconstruction S Purushwalkam, SVA Gari, VK Ithapu, C Schissler, P Robinson, A Gupta, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 56 | 2021 |
| The challenges of continuous self-supervised learning S Purushwalkam, P Morgado, A Gupta European conference on computer vision, 702-721, 2022 | 52 | 2022 |
| xgen-mm (blip-3): A family of open large multimodal models L Xue, M Shu, A Awadalla, J Wang, A Yan, S Purushwalkam, H Zhou, ... arXiv preprint arXiv:2408.08872, 2024 | 50 | 2024 |
| Pose from action: Unsupervised learning of pose features based on motion S Purushwalkam, A Gupta arXiv preprint arXiv:1609.05420, 2016 | 32 | 2016 |
| Xgen-7b technical report E Nijkamp, T Xie, H Hayashi, B Pang, C Xia, C Xing, J Vig, S Yavuz, ... arXiv preprint arXiv:2309.03450, 2023 | 30 | 2023 |
| Aligning videos in space and time S Purushwalkam, T Ye, S Gupta, A Gupta Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 28 | 2020 |
| Bounce and learn: Modeling scene dynamics with real-world bounces S Purushwalkam, A Gupta, DM Kaufman, B Russell arXiv preprint arXiv:1904.06827, 2019 | 26 | 2019 |
| Combining the best of graphical models and convnets for semantic segmentation M Cogswell, X Lin, S Purushwalkam, D Batra arXiv preprint arXiv:1412.4313, 2014 | 22 | 2014 |
| Long sequence modeling with xgen: A 7b llm trained on 8k input sequence length E Nijkamp, T Xie, H Hayashi, B Pang, C Xia, C Xing, J Vig, S Yavuz, ... Salesforce AI Research Blog, 2023 | 15 | 2023 |
| The functional correspondence problem Z Lai, S Purushwalkam, A Gupta Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 15 | 2021 |
| Bootpig: Bootstrapping zero-shot personalized image generation capabilities in pretrained diffusion models S Purushwalkam, A Gokul, S Joty, N Naik arXiv preprint arXiv:2401.13974, 2024 | 10 | 2024 |
| Automatic segmentation of adipose tissue from thigh magnetic resonance images S Purushwalkam, B Li, Q Meng, J McPhee Image Analysis and Recognition: 10th International Conference, ICIAR 2013 …, 2013 | 7 | 2013 |
| FaithEval: Can Your Language Model Stay Faithful to Context, Even If" The Moon is Made of Marshmallows" Y Ming, S Purushwalkam, S Pandit, Z Ke, XP Nguyen, C Xiong, S Joty arXiv preprint arXiv:2410.03727, 2024 | 6 | 2024 |
Abhinav GuptaProfessor, Robotics Institute, Carnegie Mellon UniversityEmail được xác minh tại cs.cmu.edu
