Publications

2024

  1. Transformers Can Do Arithmetic with the Right Embeddings
    McLeish, Sean Michael,  Bansal, Arpit, Stein, Alex, Jain, Neel, Kirchenbauer, John, Bartoldson, Brian R., Kailkhura, Bhavya, Bhatele, Abhinav, Geiping, Jonas, Schwarzschild, Avi, and Goldstein, Tom
    In ICML 2024 Workshop on LLMs and Cognition 2024
  2. Just How Flexible are Neural Networks in Practice?
    Shwartz-Ziv, Ravid, Goldblum, Micah,  Bansal, Arpit, Bruss, C Bayan, LeCun, Yann, and Wilson, Andrew Gordon
    arXiv preprint arXiv:2406.11463 2024
  3. Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
    Souri, Hossein,  Bansal, Arpit, Kazemi, Hamid, Fowl, Liam H, Saha, Aniruddha, Geiping, Jonas, Wilson, Andrew Gordon, Chellappa, Rama, Goldstein, Tom, and Goldblum, Micah
    In ICML 2024 Next Generation of AI Safety Workshop 2024
  4. Universal Guidance for Diffusion Models
    Bansal, Arpit, Chu, Hong-Min, Schwarzschild, Avi, Sengupta, Soumyadip, Goldblum, Micah, Geiping, Jonas, and Goldstein, Tom
    In The Twelfth International Conference on Learning Representations 2024

2023

  1. Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
    Bansal, Arpit, Borgnia, Eitan, Chu, Hong-Min, Li, Jie S., Kazemi, Hamid, Huang, Furong, Goldblum, Micah, Geiping, Jonas, and Goldstein, Tom
    In Thirty-seventh Conference on Neural Information Processing Systems 2023
  2. Transfer Learning with Deep Tabular Models
    Levin, Roman, Cherepanova, Valeriia, Schwarzschild, Avi,  Bansal, Arpit, Bruss, C. Bayan, Goldstein, Tom, Wilson, Andrew Gordon, and Goldblum, Micah
    In International Conference on Learning Representations 2023
  3. Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
    Wen, Yuxin,  Bansal, Arpit, Kazemi, Hamid, Borgnia, Eitan, Goldblum, Micah, Geiping, Jonas, and Goldstein, Tom
    In International Conference on Learning Representations 2023
  4. Gradient-based optimization is not necessary for generalization in neural networks
    Chiang, Ping-yeh, Ni, Renkun, Miller, David Yu,  Bansal, Arpit, Geiping, Jonas, Goldblum, Micah, and Goldstein, Tom
    In International Conference on Learning Representations 2023

2022

  1. End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking
    Bansal, Arpit, Schwarzschild, Avi, Borgnia, Eitan, Emam, Zeyad, Huang, Furong, Goldblum, Micah, and Goldstein, Tom
    In Advances in Neural Information Processing Systems 2022
  2. Certified Neural Network Watermarks with Randomized Smoothing
    Bansal, Arpit, Chiang, Ping-Yeh, Curry, Michael J, Jain, Rajiv, Wigington, Curtis, Manjunatha, Varun, Dickerson, John P, and Goldstein, Tom
    In International Conference on Machine Learning 2022
  3. Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
    Somepalli, Gowthami, Fowl, Liam,  Bansal, Arpit, Yeh-Chiang, Ping, Dar, Yehuda, Baraniuk, Richard, Goldblum, Micah, and Goldstein, Tom
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022

2021

  1. Preventing unauthorized use of proprietary data: Poisoning for secure dataset release
    Fowl, Liam, Chiang, Ping-yeh, Goldblum, Micah, Geiping, Jonas,  Bansal, Arpit, Czaja, Wojtek, and Goldstein, Tom
    arXiv preprint arXiv:2103.02683 2021
  2. MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
    Bansal, Arpit, Goldblum, Micah, Cherepanova, Valeriia, Schwarzschild, Avi, Bruss, C Bayan, and Goldstein, Tom
    arXiv preprint arXiv:2106.09643 2021

2019

  1. Pag-net: Progressive attention guided depth super-resolution network
    Bansal, Arpit, Jonna, Sankaraganesh, and Sahay, Rajiv R
    arXiv preprint arXiv:1911.09878 2019