Ameya Prabhu

75 papers A* 12A 3B 1Journal 50Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Delta-Influence: Identifying Poisons via Influence Functions.
Trans. Mach. Learn. Res.
Wenjie Li, Jiawei Li, Pengcheng Zeng, Christian Schroeder de Witt, Ameya Prabhu, Amartya Sanyal
2026 J jnl
Intrinsic Credit Assignment for Long Horizon Interaction.
CoRR
Ilze Amanda Auzina, Joschka Strüber, Sergio Hernández-Gutiérrez, Shashwat Goel, Ameya Prabhu, Matthias Bethge
2026 J jnl
Modular Memory is the Key to Continual Learning Agents.
CoRR
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, Barbara Hammer, Tyler L. Hayes, Timm Hess, Christopher Kanan, Dhireesha Kudithipudi, Xialei Liu, Vincenzo Lomonaco, Jorge Mendez-Mendez, Darshan Patil, Ameya Prabhu, Elisa Ricci, Tinne Tuytelaars, Gido M. van de Ven, Liyuan Wang, Joost van de Weijer, Jonghyun Choi, Martin Mundt, Rahaf Aljundi
2026 J jnl
PostTrainBench: Can LLM Agents Automate LLM Post-Training?
CoRR
Ben Rank, Hardik Bhatnagar, Ameya Prabhu, Shira Eisenberg, Karina Nguyen, Matthias Bethge, Maksym Andriushchenko
2025 J jnl
A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility.
CoRR
Andreas Hochlehnert, Hardik Bhatnagar, Vishaal Udandarao, Samuel Albanie, Ameya Prabhu, Matthias Bethge
2025 J jnl
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols.
CoRR
Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping
2025 J jnl
Answer Matching Outperforms Multiple Choice for Language Model Evaluation.
CoRR
Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping
2025 J jnl
Are We Done with Object-Centric Learning?
CoRR
Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Seong Joon Oh
2025 J jnl
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation.
CoRR
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu
2025 A* conf
Great Models Think Alike and this Undermines AI Oversight.
ICML
Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping
2025 J jnl
Great Models Think Alike and this Undermines AI Oversight.
CoRR
Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping
2025 A* conf
How to Merge Your Multimodal Models Over Time?
CVPR
Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth, Ameya Prabhu, Zeynep Akata, Samuel Albanie, Matthias Bethge
2025 J jnl
Mapping Post-Training Forgetting in Language Models at Scale.
CoRR
Jackson Harmon, Andreas Hochlehnert, Matthias Bethge, Ameya Prabhu
2025 — conf
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities.
ACL (1)
Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao, Samuel Albanie, Matthias Bethge
2025 J jnl
Open Problems in Machine Unlearning for AI Safety.
CoRR
Fazl Barez, Tingchen Fu, Ameya Prabhu, Stephen Casper, Amartya Sanyal, Adel Bibi, Aidan O'Gara, Robert Kirk, Ben Bucknall, Timothy Fist, Luke Ong, Philip Torr, Kwok-Yan Lam, Robert Trager, David Krueger, Sören Mindermann, José Hernández-Orallo, Mor Geva, Yarin Gal
2025 J jnl
Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks.
CoRR
Thaddäus Wiedemer, Yash Sharma, Ameya Prabhu, Matthias Bethge, Wieland Brendel
2025 J jnl
Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs.
CoRR
Christoph Schuhmann, Gollam Rabby, Ameya Prabhu, Tawsif Ahmed, Andreas Hochlehnert, Huu Nguyen, Nick Akinci Heidrich, Ludwig Schmidt, Robert Kaczmarczyk, Sören Auer, Jenia Jitsev, Matthias Bethge
2025 J jnl
Scaling Open-Ended Reasoning to Predict the Future.
CoRR
Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping
2025 J jnl
Solving Spatial Supersensing Without Spatial Supersensing.
CoRR
Vishaal Udandarao, Shyamgopal Karthik, Surabhi S. Nath, Andreas Hochlehnert, Matthias Bethge, Ameya Prabhu
2025 J jnl
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs.
CoRR
Alexander Panfilov, Evgenii Kortukov, Kristina Nikolic, Matthias Bethge, Sebastian Lapuschkin, Wojciech Samek, Ameya Prabhu, Maksym Andriushchenko, Jonas Geiping
2025 J jnl
Un-Attributability: Computing Novelty From Retrieval & Semantic Similarity.
CoRR
Philipp Davydov, Ameya Prabhu, Matthias Bethge, Elisa Nguyen, Seong Joon Oh
2025 J jnl
VGGSounder: Audio-Visual Evaluations for Foundation Models.
CoRR
Daniil Zverev, Thaddäus Wiedemer, Ameya Prabhu, Matthias Bethge, Wieland Brendel, A. Sophia Koepke
2024 J jnl
A Practitioner's Guide to Continual Multimodal Pretraining.
CoRR
Karsten Roth, Vishaal Udandarao, Sebastian Dziadzio, Ameya Prabhu, Mehdi Cherti, Oriol Vinyals, Olivier J. Hénaff, Samuel Albanie, Matthias Bethge, Zeynep Akata
2024 A* conf
A Practitioner's Guide to Real-World Continual Multimodal Pretraining.
NeurIPS
Vishaal Udandarao, Karsten Roth, Sebastian Dziadzio, Ameya Prabhu, Mehdi Cherti, Oriol Vinyals, Olivier J. Hénaff, Samuel Albanie, Zeynep Akata, Matthias Bethge
2024 A* conf
CiteME: Can Language Models Accurately Cite Scientific Claims?
NeurIPS
Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, Matthias Bethge
2024 J jnl
CiteME: Can Language Models Accurately Cite Scientific Claims?
CoRR
Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, Matthias Bethge
2024 J jnl
Corrective Machine Unlearning.
CoRR
Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal
2024 J jnl
Corrective Machine Unlearning.
Trans. Mach. Learn. Res.
Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal
2024 — conf
Data Contamination Report from the 2024 CONDA Shared Task.
CONDA
Oscar Sainz, Iker García-Ferrero, Alon Jacovi, Jon Ander Campos, Yanai Elazar, Eneko Agirre, Yoav Goldberg, Wei-Lin Chen, Jenny Chim, Leshem Choshen, Luca D'Amico-Wong, Melissa Dell, Run-Ze Fan, Shahriar Golchin, Yucheng Li, Pengfei Liu, Bhavish Pahwa, Ameya Prabhu, Suryansh Sharma, Emily Silcock, Kateryna Solonko, David Stap, Mihai Surdeanu, Yu-Min Tseng, Vishaal Udandarao, Zengzhi Wang, Ruijie Xu, Jinglin Yang
2024 J jnl
Data Contamination Report from the 2024 CONDA Shared Task.
CoRR
Oscar Sainz, Iker García-Ferrero, Alon Jacovi, Jon Ander Campos, Yanai Elazar, Eneko Agirre, Yoav Goldberg, Wei-Lin Chen, Jenny Chim, Leshem Choshen, Luca D'Amico-Wong, Melissa Dell, Run-Ze Fan, Shahriar Golchin, Yucheng Li, Pengfei Liu, Bhavish Pahwa, Ameya Prabhu, Suryansh Sharma, Emily Silcock, Kateryna Solonko, David Stap, Mihai Surdeanu, Yu-Min Tseng, Vishaal Udandarao, Zengzhi Wang, Ruijie Xu, Jinglin Yang
2024 J jnl
Delta-Influence: Unlearning Poisons via Influence Functions.
CoRR
Wenjie Li, Jiawei Li, Christian Schröder de Witt, Ameya Prabhu, Amartya Sanyal
2024 A* conf
Efficient Lifelong Model Evaluation in an Era of Rapid Progress.
NeurIPS
Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie
2024 — conf
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web.
CoLLAs
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip Torr, Adel Bibi
2024 J jnl
How to Merge Your Multimodal Models Over Time?
CoRR
Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth, Ameya Prabhu, Zeynep Akata, Samuel Albanie, Matthias Bethge
2024 J jnl
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress.
CoRR
Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie
2024 A* conf
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance.
NeurIPS
Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip Torr, Adel Bibi, Samuel Albanie, Matthias Bethge
2024 J jnl
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance.
CoRR
Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip H. S. Torr, Adel Bibi, Samuel Albanie, Matthias Bethge
2024 J jnl
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities.
CoRR
Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao, Samuel Albanie, Matthias Bethge
2024 J jnl
RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning.
CoRR
Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania
2024 A* conf
RanDumb: Random Representations Outperform Online Continually Learned Representations.
NeurIPS
Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip Torr, Ozan Sener, Puneet K. Dokania
2024 J jnl
Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry.
CoRR
Shiven Sinha, Ameya Prabhu, Ponnurangam Kumaraguru, Siddharth Bhat, Matthias Bethge
2024 J jnl
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies.
CoRR
Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr
2024 J jnl
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies.
Trans. Mach. Learn. Res.
Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr
2023 A* conf
Computationally Budgeted Continual Learning: What Does Matter?
CVPR
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi
2023 J jnl
Computationally Budgeted Continual Learning: What Does Matter?
CoRR
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi
2023 J jnl
From Categories to Classifier: Name-Only Continual Learning by Exploring the Web.
CoRR
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip H. S. Torr, Adel Bibi
2023 J jnl
Inverse Scaling: When Bigger Isn't Better.
CoRR
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler, Alicia Parrish, Aaron Mueller, Ameya Prabhu, Euan McLean, Aaron Kirtland, Alexis Ross, Alisa Liu, Andrew Gritsevskiy, Daniel Wurgaft, Derik Kauffman, Gabriel Recchia, Jiacheng Liu, Joe Cavanagh, Max Weiss, Sicong Huang, The Floating Droid, Tom Tseng, Tomasz Korbak, Xudong Shen, Yuhui Zhang, Zhengping Zhou, Najoung Kim, Samuel R. Bowman, Ethan Perez
2023 J jnl
Inverse Scaling: When Bigger Isn't Better.
Trans. Mach. Learn. Res.
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler, Alicia Parrish, Aaron Mueller, Ameya Prabhu, Euan McLean, Aaron Kirtland, Alexis Ross, Alisa Liu, Andrew Gritsevskiy, Daniel Wurgaft, Derik Kauffman, Gabriel Recchia, Jiacheng Liu, Joe Cavanagh, Max Weiss, Sicong Huang, The Floating Droid, Tom Tseng, Tomasz Korbak, Xudong Shen, Yuhui Zhang, Zhengping Zhou, Najoung Kim, Samuel R. Bowman, Ethan Perez
2023 J jnl
Online Continual Learning Without the Storage Constraint.
CoRR
Ameya Prabhu, Zhipeng Cai, Puneet K. Dokania, Philip H. S. Torr, Vladlen Koltun, Ozan Sener
2023 A* conf
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
ICCV
Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem
2023 J jnl
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
CoRR
Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem
2023 A* conf
Real-Time Evaluation in Online Continual Learning: A New Hope.
CVPR
Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem
2023 J jnl
Real-Time Evaluation in Online Continual Learning: A New Paradigm.
CoRR
Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem
2022 — conf
CLActive: Episodic Memories for Rapid Active Learning.
CoLLAs
Sri Aurobindo Munagala, Sidhant Subramanian, Shyamgopal Karthik, Ameya Prabhu, Anoop M. Namboodiri
2022 J jnl
Evaluating Inexact Unlearning Requires Revisiting Forgetting.
CoRR
Shashwat Goel, Ameya Prabhu, Ponnurangam Kumaraguru
2021 A* conf
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks.
ICLR
Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
2021 J jnl
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks.
CoRR
Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
2020 — conf
GDumb: A Simple Approach that Questions Our Progress in Continual Learning.
ECCV (2)
Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania
2020 A conf
STQ-Nets: Unifying Network Binarization and Structured Pruning.
BMVC
Sri Aurobindo Munagala, Ameya Prabhu, Anoop M. Namboodiri
2020 J jnl
Simple Unsupervised Multi-Object Tracking.
CoRR
Shyamgopal Karthik, Ameya Prabhu, Vineet Gandhi
2019 J jnl
"You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets.
CoRR
Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran, Srikanth Tamilselvam, Senthil Mani
2019 — conf
Sampling Bias in Deep Active Classification: An Empirical Study.
EMNLP/IJCNLP (1)
Ameya Prabhu, Charles Dognin, Maneesh Singh
2019 J jnl
Sampling Bias in Deep Active Classification: An Empirical Study.
CoRR
Ameya Prabhu, Charles Dognin, Maneesh Singh
2018 A* conf
Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks.
AAAI
Ameya Prabhu, Harish Krishna, Soham Saha
2018 — conf
Deep Expander Networks: Efficient Deep Networks from Graph Theory.
ECCV (13)
Ameya Prabhu, Girish Varma, Anoop M. Namboodiri
2018 A conf
Distribution-Aware Binarization of Neural Networks for Sketch Recognition.
WACV
Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada, Anoop M. Namboodiri
2018 J jnl
Distribution-Aware Binarization of Neural Networks for Sketch Recognition.
CoRR
Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada, Anoop M. Namboodiri
2018 A conf
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory.
WACV
Ameya Prabhu, Vishal Batchu, Rohit Gajawada, Sri Aurobindo Munagala, Anoop M. Namboodiri
2018 J jnl
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory.
CoRR
Ameya Prabhu, Vishal Batchu, Rohit Gajawada, Sri Aurobindo Munagala, Anoop M. Namboodiri
2017 J jnl
Deep Expander Networks: Efficient Deep Networks from Graph Theory.
CoRR
Ameya Prabhu, Girish Varma, Anoop M. Namboodiri
2016 — conf
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity.
ICON
Vinayak Athavale, Shreenivas Bharadwaj, Monik Pamecha, Ameya Prabhu, Manish Shrivastava
2016 J jnl
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity.
CoRR
Vinayak Athavale, Shreenivas Bharadwaj, Monik Pamecha, Ameya Prabhu, Manish Shrivastava
2016 B conf
Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text.
COLING
Aditya Joshi, Ameya Prabhu, Manish Shrivastava, Vasudeva Varma
2016 J jnl
Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text.
CoRR
Ameya Prabhu, Aditya Joshi, Manish Shrivastava, Vasudeva Varma
2015 — conf
Learning clustered sub-spaces for sketch-based image retrieval.
ACPR
Koustav Ghosal, Ameya Prabhu, Riddhiman Dasgupta, Anoop M. Namboodiri