In Person Conference

Event Sponsors

About Event

Welcome to Applied Research in Action Showcase! Join us for an unforgettable experience filled with excitement, inspiration, and connection. Our event brings together [industry/community] leaders, experts, and enthusiasts to share knowledge, engage in meaningful discussions, and foster valuable connections. Explore innovative ideas, discover new opportunities, and be a part of this vibrant gathering. Whether you’re a seasoned professional or a curious newcomer, there’s something for everyone at Applied Research in Action Showcase. Get ready for a day of learning, networking, and fun. See you there!

Agenda

On-Demand

-

AI-Based Saliency Prediction for Better Perceptual Quality in Display and Video Compression

-

Revolutionizing Healthcare application Deployment: A Kubernetes-Driven Approach

-

Analysis of Single Cells in Pediatric Brain Tumours with Transfer Learning and a Pre-trained Transformer Model

-

High-Fidelity Human Avatars from Laptop Webcams using Edge Compute

-

Content-Aware Video Encoder Optimization

-

JITServer: Disaggregated JIT Compiler for the JVM

-

Exploring Graph Neural Network Methods on the Analyst Network Graph

-

Automatically Parallelizing C/C++ code with Large Language Models

-

A Machine Learning Framework for Exploring Mortality in Developing Countries with Verbal Autopsies

-

Automatic Detection of Service Center Locations from Vehicle Data

-

Abstract Syntax Tree Coarsening via Deep Attention-Based Node Pooling Auto-Encoders

-

Prospect Recommendations with Integrated LLM Features

-

DataStats: An Automated Framework Supporting the Design and Development of Recommender Systems

-

TabPFGen - Tabular Data Generation with TabPFN

-

OmniRuntime: Squeezing Every Last Drop of Performance for In-Memory Data Analytics

-

Early Septic Shock Detection Using Vital Signs Forecasting and Classification

-

Closeness to Pathway: Clustering Patient Electronic Medical Records for Drug Repurposing

-

A Machine Learning Approach to Retail Sales Forecasting Using Localized Weather Features

-

Project Li-Tooth: Scalable, High-Bandwidth Optical Information Broadcast for Spatial Computing

-

Pytheas: Pattern-Based Table Discovery in CSV Files

-

Headshift

-

Query Broker: An Efficient Cybersecurity Data Access Platform

-

Speech Generation for Indigenous Language Education

-

MABS: Make All Batteries Smart

-

IOMemTable - Memory-Optimized Index-Organized Table for LSM-Tree Storage

-

Enhancing Forecasting Performance of LightGBM through Feature Screening

-

Task Grouping for Multi-Task Reinforcement Learning

-

Revitalizing Retail: Edge-Driven Computer Vision for Real-Time Analytics

-

Visual Perception of Walking Environments using Deep Learning and Large Language Models

-

Explaining the Out-of-Distribution Detection Paradox through Likelihood Peaks

-

Generative Al for Product Listing and Conditional Infographic Generation

-

Unsupervised Data Extraction from Radiology Reports with LLMs

-

Explore New Initiatives on RIM Submissions Archive's Support of eSTAR FDA Medical Device Submission Format

-

Anomaly Detection for Automated English Language Test Scoring Improvement

-

Enhancing Document Retrieval with Large Language Models and Human Feedback

-

Machine Learning for Vehicle Diagnostics Automation

-

Image Captions Are Worth a Thousand Words: Enhancing Search in Conversational

-

Cracking the Code: Gherkin Test Prioritization for Improved CI/CD Efficiency

-

Reactive-Proactive Obstacle Avoidance for Autonomous UAVs in Dynamic Indoor Environments

-

GNNs with Protein Dynamics for Enhanced Drug Targeting

-

Efficient Embedding-Based Item Identification for Robotic Pick and Place Applications

-

Smartphone Indoor Localization: A Sensor Fusion Approach

-

Analyzing Sales Cannibalization Through Utility Theory to Improve Accuracy of Predicting POS

-

Visual Blocks for ML

-

Visualizing Al-Powered Patient Insights

-

Transforming Learning Through Al-Enhanced Online Discussions: Collaboration, Equity, and Assessment

-

Al-driven Web Payment Automation

-

Object Tracking for High-Speed Pick-and-Place Robot

-

Automating Rotoscoping in Videos with NeRF Priors

-

Towards Intelligent Edge Computing

-

Enabling Large Language Models at Vanguard

-

SCE-MAE: Selective Correspondence Enhancement with MAE for Self-Supervised Landmark Estimation

-

Advancements in Multi-Objective Optimization Algorithms to Trade Promotion Strategy

-

MultiResFormer: Transformer with Adaptive Multi-Resolution Analysis for Long-Term Time Series Forecasting

-

Exact Geometry Processing Kernel using Integer Barycentric Coordinates

-

Real-time Camera Tracking for Gameplay Automation in Video Games

-

Sound Event Localization

-

Advancing the Security of Commercial Quantum-Key-Distribution Systems

-

DORA: DevOps Research and Assessment

-

A Global Surveillance System for Infectious Diseases and Bio-Security Threats

-

Driver Behavior Analysis Using Sensor Data On Android Devices

-

Detecting Malicious DNS Traffic Using Neural Networks

-

Accurate and Precise Force Estimation Algorithm for Robot Manipulation

-

Data Communication Optimization Between Mobile Devices and Servers

-

Leveraging LLMs for Operations Research Problems

-

Learning GPU Code Structure Using Large Language Models

-

Prediction of Genetic Mutations in Pediatric Brain Tumors Using Pathology Images

-

Multi-Regional Salary Prediction Model

-

Using Multi-Modal Data and Self-Supervised Approaches for Deep Learning in Healthcare

-

MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network

-

Hardware Accelerated Collision Checking

-

LayoutDM: A Discrete Diffusion Approach for Optimal Smartphone Widget Layout Generation

-

Towards Optimized E-Commerce: Examining Performance-Affecting Factors for Online Retail Platforms

-

Unsupervised Real Image Denoising

-

Efficiently Training Large Language Models with Advanced Distributed Training Techniques

-

Two-Stage Deep-Learning Framework for Understanding Scanned Documents

-

Facial Landmark Detection with Synthetic Data

-

LUTFlow: Conditionally Bijective Implicit 3D Lookup Tables

-

CAPP: Conditional Variational Auto-Encoder Accelerated Path Planner

-

Vision-Based Analysis of Gait in Older Adults with Dementia

-

Automatic Gameplay Highlight Reel Generation Using Multimodal Learning

-

Towards Broadcast-Quality Audio: Enhancement of Conference Microphones and Exploration of Objective Evaluation Techniques

-

Simulation of Device Location

-

Identifying Causal Risk Factors for Hazardous Driving and Accident Propensity for Safer Fleets and Smart Cities

-

Data Quality Detection and Improvement for Al Dashcam Models

-

Detailed Cross-Attention Control in Image Editing

-

Network Traffic Anomaly Detection by Clustering with Autoencoder Ensembling

-

Learning Unrestricted Facial Geometry from Lightstage Images

-

Benchmark Performance of Remote Control Operations Across Varied Mobile Device in Different Environments

-

3D Image Representation for Gameplay Automation

-

Cross-Account and Cross-Platform Cloud Cost Optimization: An Integrated Management for AWS and Azure

-

Latent DeepFakes: Fast High-Resolution Face Swap

-

Project Sonata: Al-Driven Recommendation & Consumer Segementation Platform of Unilever NA

-

Video Based Animation Retrieval

-

Image Caption Generation with Machine Learning for AR Wearable Devices

-

Enhancement of IP Wizard in Power and Thermal Calculator

-

Real-Time 3D Landmark Regression from Monocular Image Input on Mobile GPUs with Synthetic 3D Face Data

-

Broca: a Multimodal Language Model to Draft Radiology Reports for X-rays

-

Model Compression for Unmanned Aerial Vehicle's Companion Computer

-

Enhancing Image Composition Control with Loss-Guided Diffusion Models

-

From ML Model to Production: Streaming Data Analytics Infrastructure for loT Big Data

-

Machine Learning for Pattern-Matching Optimization in GPU Compilers

-

DynaCOMP: Bringing ML to the Transplantation Clinic

-

EarSteth: Cardiac Auscultation Audio Reconstruction Using Earbuds

-

"WaM" Cognitive Assessment in VR

-

Pre-Consultation Medical Chatbot

-

Moral Norm Variation in Large Language Models

-

Playing Various Strategies in Dominion using Deep Reinforcement Learning

-

NebulaSuit: An Upper-Body High- Density Vibrotactile Suit Built With Scalable Hardware Solutions

-

Interactive Zoetrope with a Strobing Flashlight

-

Hierarchical Data Management for Edge-Cloud Infrastructure

-

Multi-platform Autonomous Surgical Robotics From Simulation Using Reinforcement Learning

-

The Moon Man

-

Triple Point

-

3D Perspectives in Gaming: Exploring its Mechanics and Level Design Applications

-

Meow Tunes

Day - 01

15:30

ARIA Doors Open

View Info

Hide Info

Location: Reception Hall 104CD

Start your showcase journey by checking-in and selecting your seat for our showstopping keynotes from our guest speakers. 

15:45

ARIA Opening Kickoff

View Info

Hide Info

Location: Reception Hall 104CD

We’re kicking off ARIA 2023 with a warm welcome from Eyal de Lara and Arvind Gupta who will introduce our guest speakers who are at the forefront of tech innovation.

Eyal de Lara

Chair, Department of Computer Science

Arvind Gupta

Academic Director, MScAC

16:00

Alex Mariakakis Takes the Stage

View Info

Hide Info

Location: Reception Hall 104CD

Hear from the Department of Computer Science at the University of Toronto’s very own Alex Marakakis – a trailblazed in the mobile health space whose work is changing lives everywhere. 

Alex Mariakakis

Assistant Professor in the Department of Computer Science at the University of Toronto and an Affiliate Scientist at Techna.

Alex Mariakakis is an Assistant Professor in the Department of Computer Science at the University of Toronto and an Affiliate Scientist at Techna. He runs the Computational Health and Interaction (CHAI) lab, which leverages ubiquitous and emergent technologies to address problems related to people’s health and wellbeing. His research not only creates new sensing technologies for measuring physiological, behavioral, and contextual health indicators, but also examines the implications of these technologies in people’s hands. Alex and his research group deliver innovative solutions using expertise in multiple subareas of computer science, particularly machine learning, signal processing, computer vision, and human-computer interaction.

Alex received his Ph.D. from the School of Computer Science and Engineering at the University of Washington. As a student, he received the National Science Foundation Graduate Research Fellowship, the Qualcomm Innovation Fellowship, and the Gaetano Borriello Outstanding Student Award at UbiComp 2018. His work has garnered multiple Best Paper Awards at ACM venues (CHI, COMPASS) and significant attention from media outlets ranging from the BBC to National Geographic.

16:10

Raquel Urtasun Takes the Stage

View Info

Hide Info

Location: Reception Hall 104CD

Recently named one of Time Magazine’s 100 Most Influential People in AI, Raquel Urtasun takes us to the future of autonomous driving solutions.  

Raquel Urtasun

Founder and CEO of Waabi

Raquel Urtasun is Founder and CEO of Waabi, an AI company building the next generation of self-driving technology. Waabi is the culmination of Raquel’s 20 year career in AI and 10 years of experience building self-driving solutions. Raquel is also a Full Professor in the Department of Computer Science at the University of Toronto, a co-founder of the Vector Institute for AI, and the recipient of several high profile awards including a Longuet-Higgins Prize, an Everingham Prize, an NSERC EWR Steacie Award, and more.

In 2021, Raquel was named as 100 Women of Impact by Entrepreneur Magazine, 100 People Transforming Business by Business Insider and Toronto’s Most Influential Torontonians according to Toronto Life Magazine. She was also named Chatelaine 2018 Woman of the year and 2018 Toronto's top influencers by Adweek magazine.

Sergio Casas

Technical Lead Manager at Waabi

16:20

ARIA Award Ceremony

View Info

Hide Info

Location: Reception Hall 104CD

Celebrating our talented and innovative students and industry-academic collaborators who continue to push the boundaries to solve the world’s complexities. 

16:30

Step Forward into the ARIA Showcase

View Info

Hide Info

Location: Constitution Hall 

Toronto, it’s time to explore over 100 graduate student-led applied R&D projects, network with industry leading partners, and experience live demonstrations of cutting-edge research in industry and our departmental research labs. 

This is your chance to witness ground-breaking technologies of tomorrow, today. 

FAQs


Yes, you’ll need to fill out our registration form to gain access to the event. Please fill in the registration form with some basic information to get started.

The information you provide upon registration will only be used to establish you as a user on the platform and to create your login credentials. It will not be used for any other purposes.

Yes, the vFairs platform is compatible with any computer or mobile device and any browser.

Yes, this event is completely free to attend. We encourage you to login and have a look around at your convenience.

The event will be on demand indefinitely, however we may make updates and changes to the platform periodically. Make sure to keep checking back in to see our newest features in action!