| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... Google DeepMind Technical Report, 2024 | 3439 | 2024 |
| Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... Google DeepMind Technical Report, 2025 | 1378 | 2025 |
| Gemma 3 technical report G Team, A Kamath, J Ferret, S Pathak, N Vieillard, R Merhej, S Perrin, ... arXiv preprint arXiv:2503.19786, 2025 | 899 | 2025 |
| Objaverse-xl: A universe of 10m+ 3d objects M Deitke, R Liu, M Wallingford, H Ngo, O Michel, A Kusupati, A Fan, ... NeurIPS Datasets & Benchmarks 2023, 2023 | 667 | 2023 |
| Matryoshka Representation Learning A Kusupati*, G Bhatt*, A Rege*, M Wallingford, A Sinha, V Ramanujan, ... NeurIPS 2022, 2022 | 355 | 2022 |
| MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound R Zellers, J Lu, X Lu, Y Yu, Y Zhao, M Salehi, A Kusupati, J Hessel, ... CVPR 2022, 2022 | 332 | 2022 |
| Soft Threshold Weight Reparameterization for Learnable Sparsity A Kusupati, V Ramanujan, R Somani, M Wortsman, P Jain, S Kakade, ... ICML 2020, 2020 | 303 | 2020 |
| FastGRNN: A Fast, accurate, stable & tiny kilobyte sized Gated Recurrent Neural Network A Kusupati, M Singh, K Bhatia, A Kumar, P Jain, M Varma NeurIPS 2018, 2018 | 266 | 2018 |
| MADLAD-400: A Multilingual And Document-Level Large Audited Dataset S Kudugunta, I Caswell, B Zhang, X Garcia, CA Choquette-Choo, K Lee, ... NeurIPS Datasets & Benchmarks 2023, 2023 | 219 | 2023 |
| Gecko: Versatile text embeddings distilled from large language models J Lee, Z Dai, X Ren, B Chen, D Cer, JR Cole, K Hui, M Boratko, ... Google DeepMind Technical Report, 2024 | 178* | 2024 |
| MatFormer: Nested Transformer for Elastic Inference D Khatri*, S Kudugunta*, A Kusupati*, T Dettmers, K Chen, I Dhillon, ... NeurIPS 2024, 2023 | 66* | 2023 |
| RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference O Saha, A Kusupati, HV Simhadri, M Varma, P Jain NeurIPS 2020, 2020 | 65 | 2020 |
| EdgeML: Machine Learning for resource-constrained edge devices DK Dennis, Y Gaurkar, S Gopinath, S Goyal, C Gupta, M Jain, A Kumar, ... https://github.com/microsoft/EdgeML, 2017 | 54* | 2017 |
| ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard of Hearing Users D Jain, KHA Nguyen, S Goodman, R Grossman-Kahn, H Ngo, A Kusupati, ... CHI 2022, 2022 | 50 | 2022 |
| One size does not fit all: Multi-scale, cascaded RNNs for radar classification D Roy, S Srivastava, A Kusupati, P Jain, M Varma, A Arora BuildSys 2019 (Best Paper Runner-Up), 2019 | 30* | 2019 |
| Extreme Regression for Dynamic Search Advertising Y Prabhu, A Kusupati, N Gupta, M Varma WSDM 2020, 2020 | 24 | 2020 |
| Neural Priming for Sample-Efficient Adaptation M Wallingford, V Ramanujan, A Fang, A Kusupati, R Mottaghi, ... NeurIPS 2023, 2023 | 20 | 2023 |
| Mixture of Nested Experts: Adaptive Processing of Visual Tokens G Jain, N Hegde, A Kusupati, A Nagrani, S Buch, P Jain, A Arnab, S Paul NeurIPS 2024, 2024 | 17 | 2024 |
| FLUID: A Unified Evaluation Framework for Flexible Sequential Data. M Wallingford, A Kusupati, K Alizadeh-Vahid, A Walsman, A Kembhavi, ... TMLR 2023, 2023 | 15* | 2023 |
| Disrupting Model Training with Adversarial Shortcuts I Evtimov, I Covert, A Kusupati, T Kohno Workshop on Adversarial Machine Learning @ ICML 2021, 2021 | 14 | 2021 |
Ali FarhadiProfessor, Computer Science and Engineering, University of WashingtonVerified email at cs.uw.edu
