Sachin Mehta

1. Bytes Are All You Need: Transformers Operating Directly On File Bytes
   2023/05/31 by Maxwell Horton, Sachin Mehta, Ali Farhadi +1 · 4 voices · 1 citation
   #cs.CV
2. OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
   2024/04/22 by Sachin Mehta, Mehta, Sachin, Mohammad Hossein Sekhavat +19 · 5 voices · 9 citations
   #cs.CL #cs.AI #cs.LG
3. MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
   2021/10/05 by Sachin Mehta, Mehta, Sachin, Mohammad Rastegari +1 · 73 citations
   Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Advanced Image and Video Retrieval Techniques
4. Separable Self-attention for Mobile Vision Transformers
   2022/06/06 by Sachin Mehta, Mehta, Sachin, Mohammad Rastegari +1 · 20 citations
   Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Solar Radiation and Photovoltaics
5. CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
   2024/04/24 by Sachin Mehta, Maxwell Horton, Mehta, Sachin +13 · 1 voice · 2 citations
   Computer Science · #Handwritten Text Recognition Techniques
6. SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
   2023/10/23 by Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Wang, Haoxiang +15 · 20 citations
   Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics and Sensor-Based Localization
7. LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
   2024/07/19 by Qichen Fu, Fu, Qichen, Minsik Cho +9 · 14 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis
8. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
   2023/10/06 by Iman Mirzadeh, Keivan Alizadeh, Mirzadeh, Iman +13 · 10 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Machine Learning and Data Classification
9. ESPNetv2: A Light-weight, Power Efficient, and General Purpose\n Convolutional Neural Network
   2018/11/28 by Sachin Mehta, Mohammad Rastegari, Mehta, Sachin +5 · 4 citations
   Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications
10. TiC-CLIP: Continual Training of CLIP Models
    2023/10/24 by Saurabh Garg, Mehrdad Farajtabar, Garg, Saurabh +13 · 4 citations
    Computer Science · #Multimodal Machine Learning Applications #Domain Adaptation and Few-Shot Learning #Topic Modeling
11. KV Prediction for Improved Time to First Token
    2024/10/10 by Maxwell Horton, Horton, Maxwell, Qingqing Cao +11 · 3 citations
    Engineering · Computer Science · #Tunneling and Rock Mechanics #Image and Object Detection Techniques
12. RangeAugment: Efficient Online Augmentation with Range Learning
    2022/12/20 by Sachin Mehta, Mehta, Sachin, Saeid Naderiparizi +13 · 1 citation
    Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Advanced Neural Network Applications
13. CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
    2024/10/15 by Qingqing Cao, Mahyar Najibi, Cao, Qingqing +3 · 1 citation
    Computer Science · #Multimodal Machine Learning Applications #Image Retrieval and Classification Techniques #Handwritten Text Recognition Techniques
14. TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
    2025/04/02 by Jeffrey Li, Li, Jeffrey, Mohammadreza Armandpour +19 · 2 citations
    Engineering · #Metallurgy and Material Forming #Advanced Surface Polishing Techniques
15. SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
    2024/10/14 by Rasoul Shafipour, David Harrison, Shafipour, Rasoul +15 · 1 citation
    Computer Science · #Neural Networks and Applications