Bayesian Adaptation of Network Depth and Width for Continual Learning

J. Thapa, R. Li · International Conference on Machine Learning · 2024

Bayesian structure inference framework using beta process and conjugate Bernoulli process for continual network depth and width adaptation

Paper

BibTeX
@inproceedings{thapa2024bayesian,
  title     = {Bayesian Adaptation of Network Depth and Width for Continual Learning},
  author    = {Thapa, Jeevan and Li, Rui},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  year      = {2024}
}

Evolving Mixture of Low-Rank Experts for Continual User Modeling

J. Thapa, S. Zhao, K. Shindo · European Conference on Information Retrieval · 2026

Architecture of continual SVD-LoRA and experimental results on continual user modeling

Paper

BibTeX
@inproceedings{thapa2026evolving,
  title     = {Evolving Mixture of Low-Rank Experts for Continual User Modeling},
  author    = {Thapa, Jeevan and Zhao, S. and Shindo, K.},
  booktitle = {Proceedings of the European Conference on Information Retrieval},
  year      = {2026}
}

Under Review

Cross-Task Representation Alignment for Exemplar-Free Class-Incremental Learning

J. Thapa, R. Li · Manuscript under review