Sachin Mehta
University of Washington
H-index: 21
North America-United States
Top articles of Sachin Mehta
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7 x Faster Pre-training on Web-scale Image-Text Data | arXiv preprint arXiv:2404.15653 | Sachin Mehta Maxwell Horton Fartash Faghri Mohammad Hossein Sekhavat Mahyar Najibi | 2024/4/24 |
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework | arXiv preprint arXiv:2404.14619 | Sachin Mehta Mohammad Hossein Sekhavat Qingqing Cao Maxwell Horton Yanzi Jin | 2024/4/22 |
Weight subcloning: direct initialization of transformers using larger pretrained ones | arXiv preprint arXiv:2312.09299 | Mohammad Samragh Mehrdad Farajtabar Sachin Mehta Raviteja Vemulapalli Fartash Faghri | 2023/12/14 |
Relu strikes back: Exploiting activation sparsity in large language models | arXiv preprint arXiv:2310.04564 | Iman Mirzadeh Keivan Alizadeh Sachin Mehta Carlo C Del Mundo Oncel Tuzel | 2023/10/6 |
APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks | arXiv preprint arXiv:2303.02323 | Yuxiang Zhang Nicholas Bolten Sachin Mehta Anat Caspi | 2023/3/4 |
Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models | arXiv preprint arXiv:2311.18237 | Raviteja Vemulapalli Hadi Pouransari Fartash Faghri Sachin Mehta Mehrdad Farajtabar | 2023/11/30 |
Reinforce data, multiply impact: Improved model accuracy and robustness with dataset reinforcement | Fartash Faghri Hadi Pouransari Sachin Mehta Mehrdad Farajtabar Ali Farhadi | 2023/10 | |
Diffusion Models as Masked Audio-Video Learners | arXiv preprint arXiv:2310.03937 | Elvis Nunez Yanzi Jin Mohammad Rastegari Sachin Mehta Maxwell Horton | 2023/10/5 |
Tic-clip: Continual training of clip models | arXiv preprint arXiv:2310.16226 | Saurabh Garg Mehrdad Farajtabar Hadi Pouransari Raviteja Vemulapalli Sachin Mehta | 2023/10/24 |
On the Efficacy of Multi-scale Data Samplers for Vision Applications | arXiv preprint arXiv:2309.04502 | Elvis Nunez Thomas Merth Anish Prabhu Mehrdad Farajtabar Mohammad Rastegari | 2023/9/8 |
Sam-clip: Merging vision foundation models towards semantic and spatial understanding | arXiv preprint arXiv:2310.15308 | Haoxiang Wang Pavan Kumar Anasosalu Vasu Fartash Faghri Raviteja Vemulapalli Mehrdad Farajtabar | 2023/10/23 |
AB0818 SCLERODERMA RENAL CRISIS TREATMENT WITH C5 INHIBITOR ECULIZUMAB–A REVIEW OF LITERATURE | L Farrukh HH Waqar S Mehta L Shapiro | 2023/6/1 | |
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement | arXiv preprint arXiv:2310.14108 | Mohammadreza Salehi Mehrdad Farajtabar Maxwell Horton Fartash Faghri Hadi Pouransari | 2023/10/21 |
Sharcs: Efficient transformers through routing with dynamic width sub-networks | EMNLP Findings 2023 | Mohammadreza Salehi Sachin Mehta Aditya Kusupati Ali Farhadi Hanna Hajishirzi | 2023/10/18 |
OASIS: Automated Assessment of Urban Pedestrian Paths at Scale | arXiv preprint arXiv:2303.02287 | Yuxiang Zhang Suresh Devalapalli Sachin Mehta Anat Caspi | 2023/3/4 |
Segmenting skin biopsy images with coarse and sparse annotations using U-Net | Journal of digital imaging | Shima Nofallah Mojgan Mokhtari Wenjun Wu Sachin Mehta Stevan Knezevich | 2022/10 |
P11. 45. B Improved overall survival following Stereotactic Radiosurgery for brain metastases-a single institution experience | Neuro-Oncology | C May M Forshaw H Wong R Brass A Corns | 2022/9/1 |
End-to-end diagnosis of breast biopsy images with transformers | Medical image analysis | Sachin Mehta Ximing Lu Wenjun Wu Donald Weaver Hannaneh Hajishirzi | 2022/7/1 |
Rangeaugment: Efficient online augmentation with range learning | arXiv preprint arXiv:2212.10553 | Sachin Mehta Saeid Naderiparizi Fartash Faghri Maxwell Horton Lailin Chen | 2022/12/20 |
Calibration error prediction: ensuring high-quality mobile eye-tracking | Beibin Li James C Snider Quan Wang Sachin Mehta Claire Foster | 2022/6/8 |
Co-Authors
