sanketvmehta
PhD student at SCS, CMU. Previously worked with Adobe Research Lab, India.
Carnegie Mellon UniversityPittsburgh, PA
Pinned Repositories
AdaBound
An optimizer that trains as fast as Adam and as good as SGD.
ai-deadlines
:alarm_clock: AI conference deadline countdowns
allennlp
An open-source NLP research library, built on PyTorch.
awesome-2vec
Curated list of 2vec-type embedding models
colab
A ContinualAI repository for tutorials and demo running on Google Colaboratory.
gradient-based-inference
Code for "Lee, J. Y., Mehta, S. V., Wick, M., Tristan, J. B., & Carbonell, J. (2019, July). Gradient-based inference for networks with output constraints. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, pp. 4147-4154)."
lifelong-learning-pretraining-and-sam
Code for the paper "Mehta, S. V., Patil, D., Chandar, S., & Strubell, E. (2023). An Empirical Investigation of the Role of Pre-training in Lifelong Learning. The Journal of Machine Learning Research 24 (2023)"
NLP-PyTorch
ssl-deep-srl
Code for "Mehta, S. V.*, Lee, J. Y.*, and Carbonell, J. (2018). Towards Semi-Supervised Learning for Deep Semantic Role Labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 4958-4963).
Structured-Adversary
"Learning Rhyming Constraints using Structured Adversaries. Jhamtani H., Mehta S., Carbonell J., Berg-Kirkpatrick T. EMNLP-IJCNLP (Short paper) 2019"
sanketvmehta's Repositories
sanketvmehta/lifelong-learning-pretraining-and-sam
Code for the paper "Mehta, S. V., Patil, D., Chandar, S., & Strubell, E. (2023). An Empirical Investigation of the Role of Pre-training in Lifelong Learning. The Journal of Machine Learning Research 24 (2023)"
sanketvmehta/gradient-based-inference
Code for "Lee, J. Y., Mehta, S. V., Wick, M., Tristan, J. B., & Carbonell, J. (2019, July). Gradient-based inference for networks with output constraints. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, pp. 4147-4154)."
sanketvmehta/ssl-deep-srl
Code for "Mehta, S. V.*, Lee, J. Y.*, and Carbonell, J. (2018). Towards Semi-Supervised Learning for Deep Semantic Role Labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 4958-4963).
sanketvmehta/AdaBound
An optimizer that trains as fast as Adam and as good as SGD.
sanketvmehta/ai-deadlines
:alarm_clock: AI conference deadline countdowns
sanketvmehta/awesome-2vec
Curated list of 2vec-type embedding models
sanketvmehta/colab
A ContinualAI repository for tutorials and demo running on Google Colaboratory.
sanketvmehta/Structured-Adversary
"Learning Rhyming Constraints using Structured Adversaries. Jhamtani H., Mehta S., Carbonell J., Berg-Kirkpatrick T. EMNLP-IJCNLP (Short paper) 2019"
sanketvmehta/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, DGR, DGR+distill, RtF, iCaRL).
sanketvmehta/cramming
Cramming the training of a (BERT-type) language model into limited compute.
sanketvmehta/cvpr_clvision_challenge
CVPR 2020 Continual Learning Challenge - Submit your CL algorithm today!
sanketvmehta/HowToTrainYourMAMLPytorch
The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
sanketvmehta/indic_nlp_library
Resources and tools for Indian language Natural Language Processing
sanketvmehta/learn2learn
PyTorch Meta-learning Framework for Researchers
sanketvmehta/maml
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
sanketvmehta/MAML-Pytorch
Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)
sanketvmehta/Matterport
Matterport3D is a pretty awesome dataset for RGB-D machine learning tasks :)
sanketvmehta/nanoT5
Fast & Simple repository for pre-training and fine-tuning T5-style models
sanketvmehta/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
sanketvmehta/pointer-generator
Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"
sanketvmehta/pythia
sanketvmehta/pytorch-hessian-eigenthings
Efficient PyTorch Hessian eigendecomposition tools!
sanketvmehta/sanketvmehta.github.io
sanketvmehta/schema-guided-dialogue
sanketvmehta/spatium-v1
Spatial Co-location Pattern Mining using Graph Database
sanketvmehta/speaker_follower
Code release for Fried et al., Speaker-Follower Models for Vision-and-Language Navigation. in NeurIPS, 2018.
sanketvmehta/tensorboard-pytorch
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
sanketvmehta/transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
sanketvmehta/TreeNLG
A novel method of constrained decoding for neural NLG (NNLG) models
sanketvmehta/visdom
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.