← Authors

Ashish Vaswani

30 papers · 2010–2022 · 10 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (29) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (10) πŸƒ Academic Marathon (12) 🧭 Keyword Pioneer πŸ—ƒοΈ Keyword Collector (63) πŸ’Ž Century Club (30) πŸ”₯ Unstoppable (10) πŸ“ˆ Trend Setter ⚑ Prolific Year (5)

Conferences

ACL (7) NAACL (6) EMNLP (4) ICLR (3) NIPS (3) CVPR (2) ICML (2) COLING (1) ICCV (1) IJCNLP (1)

Top co-authors

Niki Parmar (9) Kevin Knight (7) David Chiang (7) Jakob Uszkoreit (6) Noam Shazeer (6) LUKASZ KAISER (3) Qing Dou (3) Jonathon Shlens (3) Chris Dyer (2) Dirk Hovy (2)

Keywords

object detection (4) image classification (4) transformer architecture (3) convolutional neural network (3) machine translation (2) neural machine translation (2) transformer model (2) neural network (2) instance segmentation (2) autoregressive model (2) vision-language navigation (1) self-attention mechanism (1) passage retrieval (1) visual navigation (1) attention mechanism (1) model parallelism (1) image generation (1) deep learning (1) instruction following (1) transfer learning (1)

Papers

Scale Efficiently: Insights from Pretraining and Finetuning Transformers ICLR 2022
The Efficiency Misnomer ICLR 2022
Simple and Efficient ways to Improve REALM EMNLP 2021
Bottleneck Transformers for Visual Recognition CVPR 2021
Scaling Local Self-Attention for Parameter Efficient Visual Backbones CVPR 2021
Music Transformer: Generating Music with Long-Term Structure ICLR 2019
Attention Augmented Convolutional Networks ICCV 2019
Stand-Alone Self-Attention in Vision Models NIPS 2019
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation ACL 2019
Fast Decoding in Sequence Models Using Discrete Latent Variables ICML 2018
Image Transformer ICML 2018
Mesh-TensorFlow: Deep Learning for Supercomputers NIPS 2018
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation ACL 2018
Self-Attention with Relative Position Representations NAACL 2018
Attention is All you Need NIPS 2017
Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies NAACL 2016
Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning NAACL 2016
Supertagging With LSTMs NAACL 2016
Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data NAACL 2015
Unifying Bayesian Inference and Vector Space Models for Improved Decipherment ACL 2015
Unifying Bayesian Inference and Vector Space Models for Improved Decipherment IJCNLP 2015
Aligning context-based statistical models of language with brain activity during reading EMNLP 2014
Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation EMNLP 2014
Decoding with Large-Scale Neural Language Models Improves Translation EMNLP 2013
Learning Whom to Trust with MACE NAACL 2013
Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm ACL 2012
Rule Markov Models for Fast Tree-to-String Translation ACL 2011
Models and Training for Unsupervised Preposition Sense Disambiguation ACL 2011
Fast, Greedy Model Minimization for Unsupervised Tagging COLING 2010
Efficient Optimization of an MDL-Inspired Objective Function for Unsupervised Part-Of-Speech Tagging ACL 2010