Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 1092 | 2023 |
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 182 | 2024 |
learn2learn: A library for meta-learning research SMR Arnold, P Mahajan, D Datta, I Bunner, KS Zarkias arXiv preprint arXiv:2008.12284, 2020 | 79 | 2020 |
When maml can adapt fast and how to assist when it cannot S Arnold, S Iqbal, F Sha International conference on artificial intelligence and statistics, 244-252, 2021 | 28 | 2021 |
Reducing the variance in online optimization by transporting past gradients S Arnold, PA Manzagol, R Babanezhad Harikandeh, I Mitliagkas, ... Advances in Neural Information Processing Systems 32, 2019 | 23 | 2019 |
Roboclip: One demonstration is enough to learn robot policies S Sontakke, J Zhang, S Arnold, K Pertsch, E Bıyık, D Sadigh, C Finn, L Itti Advances in Neural Information Processing Systems 36, 2024 | 19 | 2024 |
A domain-agnostic approach for characterization of lifelong learning systems MM Baker, A New, M Aguilar-Simon, Z Al-Halah, SMR Arnold, ... Neural Networks 160, 274-296, 2023 | 19 | 2023 |
Uniform sampling over episode difficulty S Arnold, G Dhillon, A Ravichandran, S Soatto Advances in Neural Information Processing Systems 34, 1481-1493, 2021 | 9 | 2021 |
learn2learn, 2019 SM Arnold, P Mahajan, D Datta, I Bunner | 8 | |
Analyzing the variance of policy gradient estimators for the linear-quadratic regulator JA Preiss, SMR Arnold, CY Wei, M Kloft arXiv preprint arXiv:1910.01249, 2019 | 7 | 2019 |
Can an LLM-powered socially assistive robot effectively and safely deliver cognitive behavioral therapy? A study with university students MJ Kian, M Zong, K Fischer, A Singh, AM Velentza, P Sang, S Upadhyay, ... arXiv preprint arXiv:2402.17937, 2024 | 6 | 2024 |
Policy learning and evaluation with randomized quasi-Monte Carlo SMR Arnold, P L'Ecuyer, L Chen, Y Chen, F Sha arXiv preprint arXiv:2202.07808, 2022 | 6 | 2022 |
Embedding adaptation is still needed for few-shot learning SMR Arnold, F Sha arXiv preprint arXiv:2104.07255, 2021 | 6* | 2021 |
Decoupling adaptation from modeling with meta-optimizers for meta learning SMR Arnold, S Iqbal, F Sha | 5* | 2019 |
Writing distributed applications with PyTorch S Arnold | 3 | 2017 |
An Introduction to Distributed Deep Learning S Arnold | 2 | 2016 |
Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? J Lee, A Chen, Z Dai, D Dua, DS Sachan, M Boratko, Y Luan, SMR Arnold, ... arXiv preprint arXiv:2406.13121, 2024 | | 2024 |
Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL SMR Arnold, F Sha arXiv preprint arXiv:2302.06009, 2023 | | 2023 |
Accelerating SGD for Distributed Deep-Learning Using Approximated Hessian Matrix SMR Arnold, C Wang arXiv preprint arXiv:1709.05069, 2017 | | 2017 |
Shapechanger: Environments for Transfer Learning SMR Arnold, TK Pun, TTJ Denisart, FJ Valero-Cuevas arXiv preprint arXiv:1709.05070, 2017 | | 2017 |