Projects

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA

We learn to generate text-conditioned images of new concepts in a sequential manner (i.e., continual learning) without forgetting.

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

We learn decomposed prompts for rehearsal-free continual learning.

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

We continuously adapt BLIP to new VL concepts.

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

Data-Free Class-Incremental Learning, where an agent must learn new concepts over time without storing generators or training data from past tasks

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

Realistic Semi-Supervised Continual Learning, where data distributions reflect object class correlations between, and among, the labeled and unlabeled data distributions

Unsupervised Progressive Learning and the STAM Architecture

Learning data representations from a non-stationary stream of unlabeled data for downstream classification tasks

Selected Publications

. CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

PDF Project

. ConStruct-VL: Data-Free Continual Structured VL Concepts Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

PDF Project

. Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning. International Conference on Computer Vision (ICCV), 2021.

PDF Project

. Unsupervised Progressive Learning and the STAM Architecture. International Joint Conference on Artificial Intelligent (IJCAI), 2021.

PDF Project

. Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer. International Joint Conference on Neural Networks (IJCNN), 2021.

PDF Project

Teaching

I was a Teaching Assistant for the following courses:

Georgia Tech

Auburn University

  • ELEC 2110: Electric Circuit Analysis (Summer 2017)
  • ELEC 2210: Digital Electronics (Fall 2017, Spring 2018)
  • ENG 1110: Introduction to Electrical Engineering (Fall 2017)

Recent Posts

I was a recent student spotlight for ML@GT

CONTINUE READING

James Smith, graduate student in electrical and computer engineering, will be presented with the Alton B. Zerby and Carl T. Koerner Outstanding Student Award from IEEE-Eta Kappa Nu at an awards ceremony in March 2018.

CONTINUE READING

James Smith, senior in electrical engineering, was chosen as the Auburn Department of Electrical and Computer Engineering’s outstanding student for 2017.

CONTINUE READING