Angus Fung

I am a Ph.D candidate at the University of Toronto, Robotics Institute, where I am advised by Goldie Nejat. My research is at the intersection of robotics, machine learning, and computer vision, where I am develop perception algorithms that are robust under challenging human-centered environments.

During my undergraduate, in Engineering Science, I worked on distributed learning algorithms at the Vector Institute where I was advised by Jimmy Ba. I also worked on autonomous drone tracking and landing at the Toronto Robotics and AI Lab where I was advised by Steven Waslander.

1. I founded ONE800 (with Aaron Tan), a personal companion that leverages multimodal LLM agents.
2. I founded Scholarply (with Aaron Tan), which automates the scholarship application process through LLM agents.
3. I worked with 2x Grammy Award recipient Sean Leon to build AI technology for their Herd Immunity and God's Algorithm Project.
4. I am active as a church organist having held positions at the Metropolitan United Church (under Dr. Patricia Wright) and St. Michael's Cathedral Basilica. I received my ARCT Diploma in Piano and Organ Performance in 2013 at the Royal Conservatory of Music.
5. I am building a patient screen tool using LLM agents with Dr. Edward Margolin.
   
6. I am a hobbyist game developer with experience at deploying games at scale, specifically in game design, load balancing, DDoS mitigation, cloud-based and firewall security measures, and anti-cheat mechanisms.

Email  /  CV  /  Google Scholar  /  Github

We present a novel people tracking architecture for mobile service robots using conditional latent diffusion models, which we name Latent Diffusion Track (LDTrack), to solve the robotic problem of tracking multiple dynamic people under intraclass variations.

We present a novel multimodal person detection architecture to address the mobile robot problem of person detection under intraclass variations (e.g. partial occlusion, varying illumination, pose deformation) by introducing our Temporal Invariant Multimodal Contrastive Learning (TimCLR) method.

We present a novel multi-robot person search system to generate search plans for multi-robot teams to find multiple dynamic users before a deadline.

We present the novel Weakly Supervised Mask Data Distillation (WeSuperMaDD) architecture for autonomously generating pseudo segmentation labels.

We present a method to calibrate the time-varying extrinsic transformation between any number of cameras and achieves measurement excitation over the entire configuration space of the mechanism resulting in a more accurate calibration.

We investigate the first use of deep networks for victim identification in Urban Search and Rescue, for cases of partial occlusions and varying illumination, on a RGB-D dataset obtained by a mobile robot navigating cluttered USAR-like environments.

• Accelerating the scholarship application process via LLM agents to help students secure funding while focusing on their studies.
• Selected by Microsoft Startup Hub Program, receiving grants worth $150k.

• An all-in-one service built in to iMessage aimed at lowering the barrier of entry for LLMs and Generative AI.
• Launched multi-modal conversations with proprietary model 4 months before GPT-4V.
• Gained significant traction with thousands of monthly active users.