Anthony Lem

Hello! I completed my M.Sc. in Computer Science at the Robot Vision & Learning (RVL) Lab at the University of Toronto under the supervision of Professor Florian Shkurti. My research focused on generative AI for robot perception. Before that, I received my BASc. in Engineering Science at the University of Toronto, where I was fortunate to research at the Multimedia Laboratory under the supervision of Professor Konstantinos Plataniotis. I also had an internship at Qualcomm.

Publications

Projects

teaser for Animated Wallpaper Generation

Animated Wallpaper Generation

Personal Project,

Generated animated desktop wallpapers with open-source state-of-the-art AI models. Used AI software and compute infrastructure including ComfyUI, Hugging Face, and Modal.

teaser for Compositional Premise Retrieval

Compositional Premise Retrieval

Group Course Project,

Developed a novel method for training Transformer models for retrieving premises for Automatic Theorem Proving. Benchmarked baseline retrieval methods: TF-IDF, BM25, and Sentence-BERT.

teaser for Cloud Database System

Cloud Database System

Group Course Project,

Built a distributed database system inspired by Amazon’s Dynamo in Java with multiple servers that could be dynamically removed or added. System featured data replication across servers, heart beat for server failure detection, and gossiping to achieve eventual consistency.

teaser for Multimodal Content Moderation

Multimodal Content Moderation

Group Course Project,

Developed a state-of-the-art multimodal (image and text) content moderation model that performed well on Meta’s Hateful Memes Challenge for the company Clarifai. Built a computation pipeline to augment and generate synthetic text and image data samples using Stable Diffusion for training neural networks.