Ankit Vani
7 papers · 2020–2024 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🌱 Topic Pioneer 🔥 Unstoppable · Bronze
📈
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(4)
Artificial Intelligence
(3)
Learning Types · Machine Learning
(3)
Optimization & Theory · Machine Learning
(3)
Core AI
(2)
Learning Paradigms
(2)
Natural Language Processing
(1)
Applications
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Understanding
(1)
Keywords
information theory
(1)
wasserstein distance
(1)
representation learning
(1)
image classification
(1)
continual learning
(1)
feature learning
(1)
information bottleneck
(1)
embedding learning
(1)
visual question answering
(1)
self-supervised learning
(1)
in-context learning
(1)
semantic parsing
(1)
neural network optimization
(1)
out-of-distribution generalization
(1)
group sparsity
(1)
compositional generalization
(1)
generalization
(1)
generative model
(1)
systematic generalization
(1)
model scaling
(1)
Papers
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
ICML 2024
SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
ECCV 2024
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
ICLR 2023
Fortuitous Forgetting in Connectionist Networks
ICLR 2022
On the Compositional Generalization Gap of In-Context Learning
EMNLP 2022
Iterated learning for emergent systematicity in VQA
ICLR 2021
GAIT: A Geometric Approach to Information Theory
AISTATS 2020