19 citations · 33 across the 9 of their papers we have counts for
9 papers
Thinking Costs Tokens: When More Structure is Worth the Price
Thomas Nolasque, John Grey, Calista Pham +1
Adding inference structure to a language model lets it search, verify, and revise, but these actions consume the very budget they are supposed to use well. In this paper, we invest…
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
Ankit Vani, Frederick Tung, Gabriel L. Oliveira +1
Despite attaining high empirical generalization, the sharpness of models trained with sharpness-aware minimization (SAM) do not always correlate with generalization error. Instead…
SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
Ankit Vani, Bac Nguyen, Samuel Lavoie +2
Selective attention helps us focus on task-relevant aspects in the constant flood of our sensory input. This constraint in our perception allows us to robustly generalize under dis…
On the Compositional Generalization Gap of In-Context Learning
Arian Hosseini, Ankit Vani, Dzmitry Bahdanau +2
Pretrained large generative language models have shown great performance on many tasks, but exhibit low compositional generalization abilities. Scaling such models has been shown t…
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Samuel Lavoie, Christos Tsirigotis, Max Schwarzer +4
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into simplices of dimensions each usin…
Fortuitous Forgetting in Connectionist Networks
Hattie Zhou, Ankit Vani, Hugo Larochelle +1
Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "f…
Iterated learning for emergent systematicity in VQA
Ankit Vani, Max Schwarzer, Yuchen Lu +2
Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice. When instead learn…
GAIT: A Geometric Approach to Information Theory
Jose Gallego-Posada, Ankit Vani, Max Schwarzer +1
We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities between them. This concept was originall…
Grounded Recurrent Neural Networks
Ankit Vani, Yacine Jernite, David Sontag
In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific d…