Sotabase

Career

· University of Tübingen

Publications (40)

GDumb: A Simple Approach that Questions Our Progress in Continual Learning
European Conference on Computer Vision · 2020
694
cited
Humanity's Last Exam
Robotics · 2025
284
cited
Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
International Conference on Computational Linguistics · 2016
208
cited
Inverse Scaling: When Bigger Isn't Better
Trans. Mach. Learn. Res. · 2023
185
cited
Simple Unsupervised Multi-Object Tracking
arXiv.org · 2020
86
cited
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Neural Information Processing Systems · 2024
82
cited
Computationally Budgeted Continual Learning: What Does Matter?
Computer Vision and Pattern Recognition · 2023
79
cited
Towards Adversarial Evaluations for Inexact Machine Unlearning
2022
78
cited
Deep Expander Networks: Efficient Deep Networks from Graph Theory
European Conference on Computer Vision · 2017
76
cited
Sampling Bias in Deep Active Classification: An Empirical Study
Conference on Empirical Methods in Natural Language Processing · 2019
66
cited
Real-Time Evaluation in Online Continual Learning: A New Hope
Computer Vision and Pattern Recognition · 2023
59
cited
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity
ICON · 2016
45
cited
Open Problems in Machine Unlearning for AI Safety
arXiv.org · 2025
41
cited
Online Continual Learning Without the Storage Constraint
arXiv.org · 2023
40
cited
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
International Conference on Learning Representations · 2021
25
cited
Corrective Machine Unlearning
Trans. Mach. Learn. Res. · 2024
21
cited
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
IEEE International Conference on Computer Vision · 2023
21
cited
Great Models Think Alike and this Undermines AI Oversight
International Conference on Machine Learning · 2025
20
cited
Evaluating Inexact Unlearning Requires Revisiting Forgetting
arXiv.org · 2022
18
cited
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2018
18
cited
Sotabase
Ameya Prabhu | Researcher Profile | Sotabase | Sotabase