◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Ankit Vani

Mila

7 papers hereh-index 6175 citations14 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author4
  • middle author2
  • last author1

Across the 7 of 7 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.AI1
  • cs.CL1
  • cs.CV1
  • stat.ML1
affiliations
  • Mila
  • Université de Montréal
Homepage

identity via Semantic Scholar / OpenAlex

activity
20172026
most citedGrounded Recurrent Neural Networks

19 citations · 25 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

3 papers · 1 filter

cs.LG2024

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…

cs.LG2022★ 5 cited

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…

cs.LG2021

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…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.