Ankit Vani
E-mail: [firstname][lastname]@gmail.com
Github: ankitkv
I am a Senior Machine Learning Researcher at RBC Borealis, leading the research and development of new foundation models to power a broad range of financial use cases.
I completed my PhD at Mila, Université de Montréal, under the supervision of Aaron Courville in 2024 [PhD defense slides].
Education
- Ph.D., Machine Learning, Université de Montréal, 2024
- M.S., Computer Science, New York University, 2017
- B.E., Computer Engineering, University of Pune, 2013
Research Interests
- Out-of-distribution generalization
- Foundation models
- Self-supervised learning
- Compositionality
Publications and Preprints
- Ankit Vani, Bac Nguyen, Samuel Lavoie, Ranjay Krishna, Aaron Courville. SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision. European Conference on Computer Vision (ECCV), 2024. [pdf]
- Ankit Vani, Frederick Tung, Gabriel L. Oliveira, Hossein Sharifi-Noghabi Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics. International Conference on Machine Learning (ICML), 2024. [pdf]
- Samuel Lavoie, Christos Tsirigotis, Max Schwarzer, Ankit Vani, Michael Noukhovitch, Kenji Kawaguchi, Aaron Courville. Simplicial Embeddings in Self-Supervised Learning and Downstream Classification. International Conference on Learning Representations (ICLR), 2023. [pdf]
- Arian Hosseini, Ankit Vani, Dzmitry Bahdanau, Alessandro Sordoni, Aaron Courville. On the Compositional Generalization Gap of In-Context Learning. BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022. [pdf]
- Hattie Zhou, Ankit Vani, Hugo Larochelle, Aaron Courville. Fortuitous Forgetting in Connectionist Networks. International Conference on Learning Representations (ICLR), 2022. [pdf]
- Ankit Vani, Max Schwarzer, Yuchen Lu, Eeshan Dhekane, Aaron Courville. Iterated learning for emergent systematicity in VQA. International Conference on Learning Representations (ICLR), 2021. [pdf]
- Jose Gallego, Ankit Vani, Max Schwarzer, Simon Lacoste-Julien. GAIT: A Geometric Approach to Information Theory. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. [pdf]
- Ankit Vani, Yacine Jernite, David Sontag. Grounded Recurrent Neural Networks. arXiv:1705.08557 Preprint, 2017. [pdf]
- Ramakrishna B Bairi, Ankit Vani, Pooja Ahuja, Ganesh Ramakrishnan. Categorising videos using a personalised category catalogue. IKDD Conference on Data Sciences (CODS), 2015. [pdf]
Research Reports
- Ankit Vani. Adversarial Discrete Sequence Generation. November 2017. [pdf] (advisor: Rob Fergus)
- Ankit Vani. Adversarial Objectives for Text Generation. December 2016. [pdf] (advisor: Kyunghyun Cho)
- Ankit Vani and Vighnesh Birodkar. Challenges with Variational Autoencoders for Text. December 2016. [pdf] (advisor: David Sontag)
double l[]={2.237245047823e-312,3.01793166842199e-307};main(){(1[l]+=*l)?printf(l+1),1[l]=-*l,main():puts(l);}