Chris Pal
YOU?
Author Swipe
Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments Open
Image-based personalized medicine has the potential to transform healthcare, particularly for diseases that exhibit heterogeneous progression such as Multiple Sclerosis (MS). In this work, we introduce the first treatment-aware spatio-temp…
View article: The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages
The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages Open
The development of high-performing, robust, and reliable speech technologies depends on large, high-quality datasets. However, African languages -- including our focus, Igbo, Hausa, and Yoruba -- remain under-represented due to insufficien…
CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling Open
Terrestrial carbon fluxes provide vital information about our biosphere's health and its capacity to absorb anthropogenic CO$_2$ emissions. The importance of predicting carbon fluxes has led to the emerging field of data-driven carbon flux…
LLMs can learn self-restraint through iterative self-reflection Open
In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer t…
Language Models Can Reduce Asymmetry in Information Markets Open
This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limit access to prevent theft. To study this, we introduce an o…
ArK: Augmented Reality with Knowledge Interactive Emergent Ability Open
Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2D/3D scenes in unseen environments. The common practice requires deploying an AI agent to collect l…
A General Purpose Neural Architecture for Geospatial Systems Open
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications. However, collaboration between these actors is difficult due…
View article: Implicit Offline Reinforcement Learning via Supervised Learning
Implicit Offline Reinforcement Learning via Supervised Learning Open
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. It is as simple as supervised learning and Behavior Cloni…
Neural Attentive Circuits Open
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities. General purpose models typically make few assumptions about the underlying data-structure and…
Workflow Discovery from Dialogues in the Low Data Regime Open
Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans or artificial agents through the task of he…
View article: Learned Image Compression for Machine Perception
Learned Image Compression for Machine Perception Open
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing applicat…
Learning Multi-Objective Curricula for Robotic Policy Learning Open
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL). They are designed to control how a DRL agent collects data, which is inspir…
Learning Multi-Objective Curricula for Deep Reinforcement Learning Open
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL). They are designed to control how a DRL agent collects data, which is inspir…
Structural Inductive Biases in Emergent Communication Open
In order to communicate, humans flatten complex ideas and their attributes into a sequence of words. Humans can use this ability to express and understand complex hierarchical and relational concepts, such as kinship relations and logical …
Predicting Infectiousness for Proactive Contact Tracing Open
The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential…
Medical Imaging with Deep Learning: MIDL 2020 -- Short Paper Track Open
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. Note that only accepted extended abstracts are …
Role-Wise Data Augmentation for Knowledge Distillation Open
Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{student}), where typically, the teacher has a greater capacity (…
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning Open
Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither…
Interactive Machine Comprehension with Information Seeking Agents Open
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue that this stems from the nature of MRC datasets: most of the…
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences Open
Understanding human preferences, along with cultural and social nuances, lives at the heart of natural language understanding. Concretely, we present a new task and corpus for learning alignments between machine and human preferences. Our …
View article: On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models Open
We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarization. We perform a simple extractive step before generating a summary, which is then used to conditio…
View article: Sidewalk Environment for Visual Navigation
Sidewalk Environment for Visual Navigation Open
This dataset contains low and high resolution panoramic images, coordinates, labels and a connectivity graph. In order to run this simulated environment, you will need at least one copy of the panoramic images, which are available in low (…
View article: Sidewalk Environment for Visual Navigation
Sidewalk Environment for Visual Navigation Open
This dataset contains low and high resolution panoramic images, coordinates, labels and a connectivity graph. In order to run this simulated environment, you will need at least one copy of the panoramic images, which are available in low (…
View article: Navigation Agents for the Visually Impaired: A Sidewalk Simulator and\n Experiments
Navigation Agents for the Visually Impaired: A Sidewalk Simulator and\n Experiments Open
Millions of blind and visually-impaired (BVI) people navigate urban\nenvironments every day, using smartphones for high-level path-planning and\nwhite canes or guide dogs for local information. However, many BVI people still\nstruggle to t…
View article: Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments
Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments Open
Millions of blind and visually-impaired (BVI) people navigate urban environments every day, using smartphones for high-level path-planning and white canes or guide dogs for local information. However, many BVI people still struggle to trav…
Learning Neural Causal Models from Unknown Interventions Open
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data. However, there are theoretical limitations on the identifiability of underlying st…
An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation Open
Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalizatio…
Revision in Continuous Space: Fine-Grained Control of Text Style Transfer. Open
Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither…
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning Open
Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither…