Your representations are in the network: composable and parallel adaptation for large scale models
Yonatan Dukler, Alessandro Achille, Hao Yang, Benjamin Bowman, Varsha Vivek, Luca Zancato, Avinash Ravichandran, Charless Fowlkes, Ashwin Swaminathan, Stefano Soatto. Accepted to NeurIPS 2023. Preprint: arXiv:2303.04105

SAFE: Machine Unlearning With Shard Graphs
Yonatan Dukler*, Benjamin Bowman*, Alessandro Achille*, Aditya Golatkar, Ashwin Swaminathan, Stefano Soatto (*Equal contribution). The IEEE/CVF International Conference on Computer Vision (ICCV 2023). Preprint: arXiv:2304.13169.

À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023). Preprint: arXiv:2302.07994. Video: CVPR 2023.

Characterizing the Spectrum of the NTK via a Power Series Expansion
Michael Murray*, Hui Jin*, Benjamin Bowman*, Guido Montúfar (*Equal contribution). The Eleventh International Conference on Learning Representations (ICLR 2023). Preprint: arXiv:2211.07844. Virtual Poster: ICLR 2023.

Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
Benjamin Bowman and Guido Montúfar. 2022 Conference on Neural Information Processing Systems (NeurIPS 2022). Preprint: arXiv:2206.02927. Virtual Poster: NeurIPS 2022.

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks
Benjamin Bowman and Guido Montúfar. The Tenth International Conference on Learning Representations (ICLR 2022). Preprint: arXiv:2201.04738. Virtual Poster: ICLR 2022.