• Publications
  • Influence
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
Current end-to-end machine reading and question answering (Q\&A) models are primarily based on recurrent neural networks (RNNs) with attention. Despite their success, these models are often slow forExpand
  • 442
  • 89
  • PDF
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data whereExpand
  • 726
  • 72
  • PDF
Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution
Current end-to-end machine reading and question answering (Q\&A) models are primarily based on recurrent neural networks (RNNs) with attention. Despite their success, these models are often slow forExpand
  • 42
  • 9
Learning Hierarchical Semantic Segmentations of LIDAR Data
This paper investigates a method for semantic segmentation of small objects in terrestrial LIDAR scans in urban environments. The core research contribution is a hierarchical segmentation algorithmExpand
  • 29
  • 2
  • PDF
Model-based reinforcement learning for biological sequence design
The ability to design biological structures such as DNA or proteins would have considerable medical and industrial impact. Doing so presents a challenging black-box optimization problem characterizedExpand
  • 6
  • 2
K-median Algorithms: Theory in Practice
We define the distance metric as dij for i ∈ {1, . . . , n}, j ∈ {1, . . . , n}, such that dij is the distance between points i and j in the metric space X. Kariv and Hakim [1] proved that findingExpand
  • 8
  • PDF
Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers
Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies betweenExpand
  • 3
  • PDF
EXPLORING NEURAL ARCHITECTURE SEARCH FOR LANGUAGE TASKS
Neural architecture search (NAS), the task of finding neural architectures automatically, has recently emerged as a promising approach for unveiling better models over human-designed ones. However,Expand
  • 3
Biological Sequence Design using Batched Bayesian Optimization
Being able to effectively design biological molecules like DNA and proteins to desired specifications would have a transformative effect on science. Currently, the most popular design method inExpand
  • 2
  • PDF
Population-Based Black-Box Optimization for Biological Sequence Design
The use of black-box optimization for the design of new biological sequences is an emerging research area with potentially revolutionary impact. The cost and latency of wet-lab experiments requiresExpand
  • 2
  • PDF