Search Results for author:
Found 41 papers, 16 papers with code
CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling
Terrestrial carbon fluxes provide vital information about our biosphere's health and its capacity to absorb anthropogenic CO$_2$ emissions.
LLMs can learn self-restraint through iterative self-reflection
This utility function can be used to score generation of different length and abstention.
Language Models Can Reduce Asymmetry in Information Markets
This work addresses the buyer's inspection paradox for information markets.
ArK: Augmented Reality with Knowledge Interactive Emergent Ability
In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e. g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world.
A General Purpose Neural Architecture for Geospatial Systems
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications.
Implicit Offline Reinforcement Learning via Supervised Learning
Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models.
Neural Attentive Circuits
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities.
Workflow Discovery from Dialogues in the Low Data Regime
We propose and evaluate an approach that conditions models on the set of possible actions, and we show that using this strategy, we can improve WD performance.
Ranked #1 on
Workflow Discovery
on ABCD
Learned Image Compression for Machine Perception
Compression that ensures high accuracy on computer vision tasks such as image segmentation, classification, and detection therefore has the potential for significant impact across a wide variety of settings.
Learning Multi-Objective Curricula for Robotic Policy Learning
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL).
Accounting for Variance in Machine Learning Benchmarks
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices.
Predicting Infectiousness for Proactive Contact Tracing
Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).
DuoRAT: Towards Simpler Text-to-SQL Models
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases.
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences
Understanding human preferences, along with cultural and social nuances, lives at the heart of natural language understanding.
Medical Imaging with Deep Learning: MIDL 2020 -- Short Paper Track
This compendium gathers all the accepted extended abstracts from the Third International Conference on Medical Imaging with Deep Learning (MIDL 2020), held in Montreal, Canada, 6-9 July 2020.
Role-Wise Data Augmentation for Knowledge Distillation
To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated.
Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments
In our endeavor to create a navigation assistant for the BVI, we found that existing Reinforcement Learning (RL) environments were unsuitable for the task.
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
Batch normalization has been widely used to improve optimization in deep neural networks.
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
We propose a new framework that utilizes the gradients to revise the sentence in a continuous space during inference to achieve text style transfer.
Probabilistic Planning with Sequential Monte Carlo methods
In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories.
Towards Standardization of Data Licenses: The Montreal Data License
This paper provides a taxonomy for the licensing of data in the fields of artificial intelligence and machine learning.
Towards Deep Conversational Recommendations
There has been growing interest in using neural networks and deep learning techniques to create dialogue systems.
Towards Text Generation with Adversarially Learned Neural Outlines
We generate outlines with an adversarial model trained to approximate the distribution of sentences in a latent space induced by general-purpose sentence encoders.
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state.
A Survey of Mobile Computing for the Visually Impaired
The number of visually impaired or blind (VIB) people in the world is estimated at several hundred million.
Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding
We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state.
Fashion-Gen: The Generative Fashion Dataset and Challenge
We introduce a new dataset of 293, 008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists.
Focused Hierarchical RNNs for Conditional Sequence Processing
We evaluate this method on several types of tasks with different attributes.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
(Unigram Acc metric)
ACtuAL: Actor-Critic Under Adversarial Learning
This makes it fundamentally difficult to train GANs with discrete data, as generation in this case typically involves a non-differentiable function.
Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation.
Twin Networks: Matching the Future for Sequence Generation
We propose a simple technique for encouraging generative RNNs to plan ahead.
On orthogonality and learning RNNs with long term dependencies
We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance.
Liver lesion segmentation informed by joint liver segmentation
We propose a model for the joint segmentation of the liver and liver lesions in computed tomography (CT) volumes.
Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods.
On orthogonality and learning recurrent networks with long term dependencies
We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance.
The Importance of Skip Connections in Biomedical Image Segmentation
In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation.
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
We propose zoneout, a novel method for regularizing RNNs.
Improving Facial Analysis and Performance Driven Animation through Disentangling Identity and Expression
We use a weakly-supervised approach in which identity labels are used to learn the different factors of variation linked to identity separately from factors related to expression.
Delving Deeper into Convolutional Networks for Learning Video Representations
We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs). Our method relies on percepts that are extracted from all level of a deep convolutional network trained on the large ImageNet dataset.
Brain Tumor Segmentation with Deep Neural Networks
Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2013 leaderboard
