Delta-Influence: Identifying Poisons via Influence Functions.

Ameya Prabhu

Wenjie Li Jiawei Li Pengcheng Zeng Christian Schroeder de Witt Ameya Prabhu Amartya Sanyal Delta-Influence: Identifying Poisons via Influence Functions. 2026 2026 Trans. Mach. Learn. Res. https://openreview.net/forum?id=4XtcG8NNaG db/journals/tmlr/tmlr2026.html#LiLZWPS26 streams/journals/tmlr

Ilze Amanda Auzina Joschka Strüber Sergio Hernández-Gutiérrez Shashwat Goel Ameya Prabhu Matthias Bethge Intrinsic Credit Assignment for Long Horizon Interaction. 2026 February abs/2602.12342 CoRR https://doi.org/10.48550/arXiv.2602.12342 db/journals/corr/corr2602.html#abs-2602-12342 streams/journals/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 0001 Tinne Tuytelaars Gido M. van de Ven Liyuan Wang Joost van de Weijer 0001 Jonghyun Choi Martin Mundt Rahaf Aljundi Modular Memory is the Key to Continual Learning Agents. 2026 March abs/2603.01761 CoRR https://doi.org/10.48550/arXiv.2603.01761 db/journals/corr/corr2603.html#abs-2603-01761 streams/journals/corr

Ben Rank Hardik Bhatnagar Ameya Prabhu Shira Eisenberg Karina Nguyen Matthias Bethge Maksym Andriushchenko PostTrainBench: Can LLM Agents Automate LLM Post-Training? 2026 March abs/2603.08640 CoRR https://doi.org/10.48550/arXiv.2603.08640 db/journals/corr/corr2603.html#abs-2603-08640 streams/journals/corr

Anne-Sofie Maerten Juliane Verwiebe Shyamgopal Karthik Ameya Prabhu Johan Wagemans Matthias Bethge Personalizing Text-to-Image Generation to Individual Taste. 2026 April abs/2604.07427 CoRR https://doi.org/10.48550/arXiv.2604.07427 db/journals/corr/corr2604.html#abs-2604-07427 streams/journals/corr

Ronald Skorobogat Ameya Prabhu Matthias Bethge Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss. 2026 April abs/2604.12911 CoRR https://doi.org/10.48550/arXiv.2604.12911 db/journals/corr/corr2604.html#abs-2604-12911 streams/journals/corr

Sumeet Ramesh Motwani Daniel Nichols Charles London Peggy Li Fabio Pizzati Acer Blake Hasan Hammoud Tavish McDonald Akshat Naik Alesia Ivanova Vignesh Baskaran Ivan Laptev Ruben Glatt Tal Ben-Nun Philip Torr 0001 Natasha Jaques Ameya Prabhu Brian R. Bartoldson Bhavya Kailkhura Christian Schroeder de Witt LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning. 2026 April abs/2604.14140 CoRR https://doi.org/10.48550/arXiv.2604.14140 db/journals/corr/corr2604.html#abs-2604-14140 streams/journals/corr

Shashwat Goel Nikhil Chandak Arvindh Arun Ameya Prabhu Steffen Staab Moritz Hardt Maksym Andriushchenko Jonas Geiping FutureSim: Replaying World Events to Evaluate Adaptive Agents. 2026 May abs/2605.15188 CoRR https://doi.org/10.48550/arXiv.2605.15188 db/journals/corr/corr2605.html#abs-2605-15188 streams/journals/corr

Adhiraj Ghosh Sebastian Dziadzio Ameya Prabhu Vishaal Udandarao Samuel Albanie Matthias Bethge ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities. 32445-32481 2025 ACL (1) https://doi.org/10.18653/v1/2025.acl-long.1560 https://aclanthology.org/2025.acl-long.1560/ conf/acl/2025-1 db/conf/acl/acl2025-1.html#GhoshDPUAB25 Sebastian Dziadzio Vishaal Udandarao Karsten Roth Ameya Prabhu Zeynep Akata Samuel Albanie Matthias Bethge How to Merge Your Multimodal Models Over Time? 20479-20491 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Dziadzio_How_to_Merge_Your_Multimodal_Models_Over_Time_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.01907 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#DziadzioURPAAB25 Daniil Zverev Thaddäus Wiedemer Ameya Prabhu Matthias Bethge Wieland Brendel A. Sophia Koepke VGGSounder: Audio-Visual Evaluations for Foundation Models. 2025 ICCV 1027-1037 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.00103 db/conf/iccv/iccv2025.html#ZverevWPBBK25 streams/conf/iccv Shashwat Goel Joschka Strüber Ilze Amanda Auzina Karuna K. Chandra Ponnurangam Kumaraguru Douwe Kiela Ameya Prabhu Matthias Bethge Jonas Geiping Great Models Think Alike and this Undermines AI Oversight. 2025 ICML https://proceedings.mlr.press/v267/goel25b.html https://openreview.net/forum?id=3Z827FtMNe conf/icml/2025 db/conf/icml/icml2025.html#GoelSACKKPBG25

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 0001 Kwok-Yan Lam Robert Trager David Krueger 0001 Sören Mindermann José Hernández-Orallo Mor Geva Yarin Gal Open Problems in Machine Unlearning for AI Safety. 2025 January abs/2501.04952 CoRR https://doi.org/10.48550/arXiv.2501.04952 db/journals/corr/corr2501.html#abs-2501-04952 streams/journals/corr

Shashwat Goel Joschka Strüber Ilze Amanda Auzina Karuna K. Chandra Ponnurangam Kumaraguru Douwe Kiela Ameya Prabhu Matthias Bethge Jonas Geiping Great Models Think Alike and this Undermines AI Oversight. 2025 February abs/2502.04313 CoRR https://doi.org/10.48550/arXiv.2502.04313 db/journals/corr/corr2502.html#abs-2502-04313 streams/journals/corr

Thaddäus Wiedemer Yash Sharma 0001 Ameya Prabhu Matthias Bethge Wieland Brendel Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks. 2025 February abs/2502.18326 CoRR https://doi.org/10.48550/arXiv.2502.18326 db/journals/corr/corr2502.html#abs-2502-18326 streams/journals/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 Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs. 2025 February abs/2502.19413 CoRR https://doi.org/10.48550/arXiv.2502.19413 db/journals/corr/corr2502.html#abs-2502-19413 streams/journals/corr

Shiven Sinha Shashwat Goel Ponnurangam Kumaraguru Jonas Geiping Matthias Bethge Ameya Prabhu Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation. 2025 February abs/2502.19414 CoRR https://doi.org/10.48550/arXiv.2502.19414 db/journals/corr/corr2502.html#abs-2502-19414 streams/journals/corr

Andreas Hochlehnert Hardik Bhatnagar Vishaal Udandarao Samuel Albanie Ameya Prabhu Matthias Bethge A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility. 2025 April abs/2504.07086 CoRR https://doi.org/10.48550/arXiv.2504.07086 db/journals/corr/corr2504.html#abs-2504-07086 streams/journals/corr

Alexander Rubinstein 0002 Ameya Prabhu Matthias Bethge Seong Joon Oh Are We Done with Object-Centric Learning? 2025 April abs/2504.07092 CoRR https://doi.org/10.48550/arXiv.2504.07092 db/journals/corr/corr2504.html#abs-2504-07092 streams/journals/corr

Nikhil Chandak Shashwat Goel Ameya Prabhu Moritz Hardt Jonas Geiping Answer Matching Outperforms Multiple Choice for Language Model Evaluation. 2025 July abs/2507.02856 CoRR https://doi.org/10.48550/arXiv.2507.02856 db/journals/corr/corr2507.html#abs-2507-02856 streams/journals/corr

Daniil Zverev Thaddäus Wiedemer Ameya Prabhu Matthias Bethge Wieland Brendel A. Sophia Koepke VGGSounder: Audio-Visual Evaluations for Foundation Models. 2025 August abs/2508.08237 CoRR https://doi.org/10.48550/arXiv.2508.08237 db/journals/corr/corr2508.html#abs-2508-08237 streams/journals/corr

Alexander Panfilov Evgenii Kortukov Kristina Nikolic Matthias Bethge Sebastian Lapuschkin Wojciech Samek Ameya Prabhu Maksym Andriushchenko Jonas Geiping Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs. 2025 September abs/2509.18058 CoRR https://doi.org/10.48550/arXiv.2509.18058 db/journals/corr/corr2509.html#abs-2509-18058 streams/journals/corr

Mikhail Terekhov Alexander Panfilov Daniil Dzenhaliou Caglar Gulcehre Maksym Andriushchenko Ameya Prabhu Jonas Geiping Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols. 2025 October abs/2510.09462 CoRR https://doi.org/10.48550/arXiv.2510.09462 db/journals/corr/corr2510.html#abs-2510-09462 streams/journals/corr

Jackson Harmon Andreas Hochlehnert Matthias Bethge Ameya Prabhu Mapping Post-Training Forgetting in Language Models at Scale. 2025 October abs/2510.17776 CoRR https://doi.org/10.48550/arXiv.2510.17776 db/journals/corr/corr2510.html#abs-2510-17776 streams/journals/corr

Philipp Davydov Ameya Prabhu Matthias Bethge Elisa Nguyen Seong Joon Oh Un-Attributability: Computing Novelty From Retrieval & Semantic Similarity. 2025 October abs/2510.27313 CoRR https://doi.org/10.48550/arXiv.2510.27313 db/journals/corr/corr2510.html#abs-2510-27313 streams/journals/corr

Vishaal Udandarao Shyamgopal Karthik Surabhi S. Nath Andreas Hochlehnert Matthias Bethge Ameya Prabhu Solving Spatial Supersensing Without Spatial Supersensing. 2025 November abs/2511.16655 CoRR https://doi.org/10.48550/arXiv.2511.16655 db/journals/corr/corr2511.html#abs-2511-16655 streams/journals/corr

Nikhil Chandak Shashwat Goel Ameya Prabhu Moritz Hardt Jonas Geiping Scaling Open-Ended Reasoning to Predict the Future. 2025 December abs/2512.25070 CoRR https://doi.org/10.48550/arXiv.2512.25070 db/journals/corr/corr2512.html#abs-2512-25070 streams/journals/corr

Shashwat Goel Ameya Prabhu Philip Torr 0001 Ponnurangam Kumaraguru Amartya Sanyal Corrective Machine Unlearning. 2024 2024 Trans. Mach. Learn. Res. https://openreview.net/forum?id=v8enu4jP9B db/journals/tmlr/tmlr2024.html#GoelP0KS24

Zhongrui Gui Shuyang Sun Runjia Li Jianhao Yuan Zhaochong An Karsten Roth Ameya Prabhu Philip Torr 0001 kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies. 2024 2024 Trans. Mach. Learn. Res. https://openreview.net/forum?id=ZSqP1RT8jC db/journals/tmlr/tmlr2024.html#GuiSLYARP024

Ameya Prabhu Hasan Abed Al Kader Hammoud Ser-Nam Lim Bernard Ghanem Philip Torr 0001 Adel Bibi From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web. 534-559 2024 CoLLAs https://proceedings.mlr.press/v274/prabhu25a.html conf/collas/2024 db/conf/collas/collas2024.html#PrabhuHLG0B24 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 0003 Bhavish Pahwa Ameya Prabhu Suryansh Sharma Emily Silcock Kateryna Solonko David Stap Mihai Surdeanu Yu-Min Tseng Vishaal Udandarao Zengzhi Wang Ruijie Xu 0005 Jinglin Yang Data Contamination Report from the 2024 CONDA Shared Task. 41-56 2024 CONDA https://doi.org/10.18653/v1/2024.conda-1.4 conf/conda/2024 db/conf/conda/conda2024.html#SainzGJCEAGCCCDDFGLLPPS24 streams/conf/conda Ameya Prabhu Shiven Sinha Ponnurangam Kumaraguru Philip Torr 0001 Ozan Sener Puneet K. Dokania RanDumb: Random Representations Outperform Online Continually Learned Representations. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/4309616aaed8e848009bc4a7ef73b493-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#PrabhuSK0SD24 Ameya Prabhu Vishaal Udandarao Philip Torr 0001 Matthias Bethge Adel Bibi Samuel Albanie Efficient Lifelong Model Evaluation in an Era of Rapid Progress. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/874067cee9c98dc9b9980fa6ef70176a-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#PrabhuU0BBA24 Ori Press Andreas Hochlehnert Ameya Prabhu Vishaal Udandarao Ofir Press Matthias Bethge CiteME: Can Language Models Accurately Cite Scientific Claims? 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/0ef47f7b768e1a012e3d995ac8d8fac7-Abstract-Datasets_and_Benchmarks_Track.html conf/nips/2024 db/conf/nips/neurips2024.html#PressHPUPB24 Vishaal Udandarao Ameya Prabhu Adhiraj Ghosh Yash Sharma 0001 Philip Torr 0001 Adel Bibi Samuel Albanie Matthias Bethge No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/715b78ccfb6f4cada5528ac9b5278def-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#UdandaraoPG00BA24 Vishaal Udandarao Karsten Roth Sebastian Dziadzio Ameya Prabhu Mehdi Cherti Oriol Vinyals Olivier J. Hénaff Samuel Albanie Zeynep Akata Matthias Bethge A Practitioner's Guide to Real-World Continual Multimodal Pretraining. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/f1a6a2cdc7e65dbb4579e78f97cd2665-Abstract-Datasets_and_Benchmarks_Track.html conf/nips/2024 db/conf/nips/neurips2024.html#UdandaraoRDPCVH24

Ameya Prabhu Shiven Sinha Ponnurangam Kumaraguru Philip H. S. Torr Ozan Sener Puneet K. Dokania RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning. 2024 abs/2402.08823 CoRR https://doi.org/10.48550/arXiv.2402.08823 db/journals/corr/corr2402.html#abs-2402-08823

Shashwat Goel Ameya Prabhu Philip Torr 0001 Ponnurangam Kumaraguru Amartya Sanyal Corrective Machine Unlearning. 2024 abs/2402.14015 CoRR https://doi.org/10.48550/arXiv.2402.14015 db/journals/corr/corr2402.html#abs-2402-14015

Ameya Prabhu Vishaal Udandarao Philip Torr 0001 Matthias Bethge Adel Bibi Samuel Albanie Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress. 2024 abs/2402.19472 CoRR https://doi.org/10.48550/arXiv.2402.19472 db/journals/corr/corr2402.html#abs-2402-19472

Vishaal Udandarao Ameya Prabhu Adhiraj Ghosh Yash Sharma 0001 Philip H. S. Torr Adel Bibi Samuel Albanie Matthias Bethge No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance. 2024 abs/2404.04125 CoRR https://doi.org/10.48550/arXiv.2404.04125 db/journals/corr/corr2404.html#abs-2404-04125

Shiven Sinha Ameya Prabhu Ponnurangam Kumaraguru Siddharth Bhat Matthias Bethge Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry. 2024 abs/2404.06405 CoRR https://doi.org/10.48550/arXiv.2404.06405 db/journals/corr/corr2404.html#abs-2404-06405

Zhongrui Gui Shuyang Sun Runjia Li Jianhao Yuan Zhaochong An Karsten Roth Ameya Prabhu Philip Torr 0001 kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies. 2024 abs/2404.09447 CoRR https://doi.org/10.48550/arXiv.2404.09447 db/journals/corr/corr2404.html#abs-2404-09447

Ori Press Andreas Hochlehnert Ameya Prabhu Vishaal Udandarao Ofir Press Matthias Bethge CiteME: Can Language Models Accurately Cite Scientific Claims? 2024 abs/2407.12861 CoRR https://doi.org/10.48550/arXiv.2407.12861 db/journals/corr/corr2407.html#abs-2407-12861 streams/journals/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 0003 Bhavish Pahwa Ameya Prabhu Suryansh Sharma Emily Silcock Kateryna Solonko David Stap Mihai Surdeanu Yu-Min Tseng Vishaal Udandarao Zengzhi Wang Ruijie Xu 0005 Jinglin Yang Data Contamination Report from the 2024 CONDA Shared Task. 2024 abs/2407.21530 CoRR https://doi.org/10.48550/arXiv.2407.21530 db/journals/corr/corr2407.html#abs-2407-21530 streams/journals/corr

Karsten Roth Vishaal Udandarao Sebastian Dziadzio Ameya Prabhu Mehdi Cherti Oriol Vinyals Olivier J. Hénaff Samuel Albanie Matthias Bethge Zeynep Akata A Practitioner's Guide to Continual Multimodal Pretraining. 2024 abs/2408.14471 CoRR https://doi.org/10.48550/arXiv.2408.14471 db/journals/corr/corr2408.html#abs-2408-14471 streams/journals/corr

Wenjie Li Jiawei Li Christian Schröder de Witt Ameya Prabhu Amartya Sanyal Delta-Influence: Unlearning Poisons via Influence Functions. 2024 abs/2411.13731 CoRR https://doi.org/10.48550/arXiv.2411.13731 db/journals/corr/corr2411.html#abs-2411-13731 streams/journals/corr

Sebastian Dziadzio Vishaal Udandarao Karsten Roth Ameya Prabhu Zeynep Akata Samuel Albanie Matthias Bethge How to Merge Your Multimodal Models Over Time? 2024 abs/2412.06712 CoRR https://doi.org/10.48550/arXiv.2412.06712 db/journals/corr/corr2412.html#abs-2412-06712 streams/journals/corr

Adhiraj Ghosh Sebastian Dziadzio Ameya Prabhu Vishaal Udandarao Samuel Albanie Matthias Bethge ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities. 2024 abs/2412.06745 CoRR https://doi.org/10.48550/arXiv.2412.06745 db/journals/corr/corr2412.html#abs-2412-06745 streams/journals/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 0010 Joe Cavanagh Max Weiss Sicong Huang 0001 The Floating Droid Tom Tseng Tomasz Korbak Xudong Shen Yuhui Zhang Zhengping Zhou Najoung Kim Samuel R. Bowman Ethan Perez Inverse Scaling: When Bigger Isn't Better. 2023 2023 Trans. Mach. Learn. Res. https://openreview.net/forum?id=DwgRm72GQF db/journals/tmlr/tmlr2023.html#McKenzieLPPMPMK23

Ameya Prabhu Hasan Abed Al Kader Hammoud Puneet K. Dokania Philip H. S. Torr Ser-Nam Lim Bernard Ghanem Adel Bibi Computationally Budgeted Continual Learning: What Does Matter? 3698-3707 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.00360 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#PrabhuHDTLGB23 Yasir Ghunaim Adel Bibi Kumail Alhamoud Motasem Alfarra Hasan Abed Al Kader Hammoud Ameya Prabhu Philip H. S. Torr Bernard Ghanem Real-Time Evaluation in Online Continual Learning: A New Hope. 11888-11897 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.01144 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#GhunaimBAAHPTG23 Hasan Abed Al Kader Hammoud Ameya Prabhu Ser-Nam Lim Philip H. S. Torr Adel Bibi Bernard Ghanem Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? 18806-18815 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.01728 conf/iccv/2023 db/conf/iccv/iccv2023.html#HammoudPLTBG23

Yasir Ghunaim Adel Bibi Kumail Alhamoud Motasem Alfarra Hasan Abed Al Kader Hammoud Ameya Prabhu Philip H. S. Torr Bernard Ghanem Real-Time Evaluation in Online Continual Learning: A New Paradigm. 2023 abs/2302.01047 CoRR https://doi.org/10.48550/arXiv.2302.01047 db/journals/corr/corr2302.html#abs-2302-01047

Ameya Prabhu Zhipeng Cai 0003 Puneet K. Dokania Philip H. S. Torr Vladlen Koltun Ozan Sener Online Continual Learning Without the Storage Constraint. 2023 abs/2305.09253 CoRR https://doi.org/10.48550/arXiv.2305.09253 db/journals/corr/corr2305.html#abs-2305-09253

Hasan Abed Al Kader Hammoud Ameya Prabhu Ser-Nam Lim Philip H. S. Torr Adel Bibi Bernard Ghanem Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? 2023 abs/2305.09275 CoRR https://doi.org/10.48550/arXiv.2305.09275 db/journals/corr/corr2305.html#abs-2305-09275

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 0010 Joe Cavanagh Max Weiss Sicong Huang 0001 The Floating Droid Tom Tseng Tomasz Korbak Xudong Shen Yuhui Zhang Zhengping Zhou Najoung Kim Samuel R. Bowman Ethan Perez Inverse Scaling: When Bigger Isn't Better. 2023 abs/2306.09479 CoRR https://doi.org/10.48550/arXiv.2306.09479 db/journals/corr/corr2306.html#abs-2306-09479

Ameya Prabhu Hasan Abed Al Kader Hammoud Ser-Nam Lim Bernard Ghanem Philip H. S. Torr Adel Bibi From Categories to Classifier: Name-Only Continual Learning by Exploring the Web. 2023 abs/2311.11293 CoRR https://doi.org/10.48550/arXiv.2311.11293 db/journals/corr/corr2311.html#abs-2311-11293

Sri Aurobindo Munagala Sidhant Subramanian Shyamgopal Karthik Ameya Prabhu Anoop M. Namboodiri CLActive: Episodic Memories for Rapid Active Learning. 430-440 2022 CoLLAs https://proceedings.mlr.press/v199/munagala22a.html conf/collas/2022 db/conf/collas/collas2022.html#MunagalaSKPN22

Shashwat Goel Ameya Prabhu Ponnurangam Kumaraguru Evaluating Inexact Unlearning Requires Revisiting Forgetting. 2022 abs/2201.06640 CoRR https://arxiv.org/abs/2201.06640 db/journals/corr/corr2201.html#abs-2201-06640

Shyamgopal Karthik Ameya Prabhu Puneet K. Dokania Vineet Gandhi No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. 2021 ICLR https://openreview.net/forum?id=193sEnKY1ij conf/iclr/2021 db/conf/iclr/iclr2021.html#KarthikPDG21

Shyamgopal Karthik Ameya Prabhu Puneet K. Dokania Vineet Gandhi No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. 2021 abs/2104.00795 CoRR https://arxiv.org/abs/2104.00795 db/journals/corr/corr2104.html#abs-2104-00795

Sri Aurobindo Munagala Ameya Prabhu Anoop M. Namboodiri STQ-Nets: Unifying Network Binarization and Structured Pruning. 2020 BMVC https://www.bmvc2020-conference.com/assets/papers/0113.pdf conf/bmvc/2020 db/conf/bmvc/bmvc2020.html#MunagalaPN20 Ameya Prabhu Philip H. S. Torr Puneet K. Dokania GDumb: A Simple Approach that Questions Our Progress in Continual Learning. 524-540 2020 ECCV (2) https://doi.org/10.1007/978-3-030-58536-5_31 conf/eccv/2020-2 db/conf/eccv/eccv2020-2.html#PrabhuTD20

Shyamgopal Karthik Ameya Prabhu Vineet Gandhi Simple Unsupervised Multi-Object Tracking. 2020 abs/2006.02609 CoRR https://arxiv.org/abs/2006.02609 db/journals/corr/corr2006.html#abs-2006-02609

Ameya Prabhu Charles Dognin Maneesh Singh 0001 Sampling Bias in Deep Active Classification: An Empirical Study. 4056-4066 2019 EMNLP/IJCNLP (1) https://doi.org/10.18653/v1/D19-1417 conf/emnlp/2019-1 db/conf/emnlp/emnlp2019-1.html#PrabhuDS19

Ameya Prabhu Charles Dognin Maneesh Singh 0001 Sampling Bias in Deep Active Classification: An Empirical Study. 2019 abs/1909.09389 CoRR http://arxiv.org/abs/1909.09389 db/journals/corr/corr1909.html#abs-1909-09389

Ameya Prabhu Riddhiman Dasgupta Anush Sankaran Srikanth Tamilselvam Senthil Mani "You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets. 2019 abs/1911.11433 CoRR http://arxiv.org/abs/1911.11433 db/journals/corr/corr1911.html#abs-1911-11433

Ameya Prabhu Harish Krishna Soham Saha Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks. 2018 AAAI https://doi.org/10.1609/aaai.v32i1.12182 conf/aaai/2018 db/conf/aaai/aaai2018.html#PrabhuKS18 8137-8138 Ameya Prabhu Girish Varma Anoop M. Namboodiri Deep Expander Networks: Efficient Deep Networks from Graph Theory. 20-36 2018 ECCV (13) https://doi.org/10.1007/978-3-030-01261-8_2 conf/eccv/2018-13 db/conf/eccv/eccv2018-13.html#PrabhuVN18 Ameya Prabhu Vishal Batchu Rohit Gajawada Sri Aurobindo Munagala Anoop M. Namboodiri Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory. 821-829 2018 WACV https://doi.org/10.1109/WACV.2018.00095 https://doi.ieeecomputersociety.org/10.1109/WACV.2018.00095 conf/wacv/2018 db/conf/wacv/wacv2018.html#PrabhuBGMN18 Ameya Prabhu Vishal Batchu Sri Aurobindo Munagala Rohit Gajawada Anoop M. Namboodiri Distribution-Aware Binarization of Neural Networks for Sketch Recognition. 830-838 2018 WACV https://doi.org/10.1109/WACV.2018.00096 https://doi.ieeecomputersociety.org/10.1109/WACV.2018.00096 conf/wacv/2018 db/conf/wacv/wacv2018.html#PrabhuBMGN18

Ameya Prabhu Vishal Batchu Sri Aurobindo Munagala Rohit Gajawada Anoop M. Namboodiri Distribution-Aware Binarization of Neural Networks for Sketch Recognition. 2018 abs/1804.02941 CoRR http://arxiv.org/abs/1804.02941 db/journals/corr/corr1804.html#abs-1804-02941

Ameya Prabhu Vishal Batchu Rohit Gajawada Sri Aurobindo Munagala Anoop M. Namboodiri Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory. 2018 abs/1804.03867 CoRR http://arxiv.org/abs/1804.03867 db/journals/corr/corr1804.html#abs-1804-03867

Ameya Prabhu Girish Varma Anoop M. Namboodiri Deep Expander Networks: Efficient Deep Networks from Graph Theory. 2017 abs/1711.08757 CoRR http://arxiv.org/abs/1711.08757 db/journals/corr/corr1711.html#abs-1711-08757

Aditya Joshi Ameya Prabhu Manish Shrivastava 0001 Vasudeva Varma Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text. 2482-2491 2016 COLING https://aclanthology.org/C16-1234/ conf/coling/2016 db/conf/coling/coling2016.html#JoshiPSV16 Vinayak Athavale Shreenivas Bharadwaj Monik Pamecha Ameya Prabhu Manish Shrivastava 0001 Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity. 154-160 2016 ICON https://aclanthology.org/W16-6320/ conf/icon-nlp/2016 db/conf/icon-nlp/icon-nlp2016.html#AthavaleBPPS16

Vinayak Athavale Shreenivas Bharadwaj Monik Pamecha Ameya Prabhu Manish Shrivastava 0001 Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity. 2016 abs/1610.09756 CoRR http://arxiv.org/abs/1610.09756 db/journals/corr/corr1610.html#AthavaleBPPS16

Ameya Prabhu Aditya Joshi Manish Shrivastava 0001 Vasudeva Varma Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text. 2016 abs/1611.00472 CoRR http://arxiv.org/abs/1611.00472 db/journals/corr/corr1611.html#PrabhuJSV16

Koustav Ghosal Ameya Prabhu Riddhiman Dasgupta Anoop M. Namboodiri Learning clustered sub-spaces for sketch-based image retrieval. 599-603 2015 ACPR https://doi.org/10.1109/ACPR.2015.7486573 conf/acpr/2015 db/conf/acpr/acpr2015.html#GhosalPDN15 Eneko Agirre Tawsif Ahmed Zeynep Akata Samuel Albanie Motasem Alfarra Kumail Alhamoud Rahaf Aljundi Zhaochong An Maksym Andriushchenko Arvindh Arun Vinayak Athavale Sören Auer Ilze Amanda Auzina Andrew D. Bagdanov Fazl Barez Brian R. Bartoldson Vignesh Baskaran Vishal Batchu Tal Ben-Nun Matthias Bethge Shreenivas Bharadwaj Siddharth Bhat Hardik Bhatnagar Adel Bibi Acer Blake Samuel R. Bowman Wieland Brendel Ben Bucknall Lucas Caccia Zhipeng Cai 0003 Jon Ander Campos Antonio Carta Stephen Casper Joe Cavanagh Nikhil Chandak Karuna K. Chandra Laurent Charlin Weilin ChenWei-Lin Chen Mehdi Cherti Jenny Chim Jonghyun Choi Leshem Choshen Luca D'Amico-Wong Riddhiman Dasgupta Philipp Davydov Melissa Dell Charles Dognin Puneet K. Dokania Vaggelis Dorovatas The Floating Droid Daniil Dzenhaliou Sebastian Dziadzio Shira Eisenberg Yanai Elazar Run-Ze Fan Timothy Fist Tingchen Fu Rohit Gajawada Yarin Gal Vineet Gandhi Iker García-Ferrero Jonas Geiping Mor Geva Bernard Ghanem Koustav Ghosal Adhiraj Ghosh Yasir Ghunaim Ruben Glatt Shashwat Goel Shahriar Golchin Yoav Goldberg Andrew Gritsevskiy Zhongrui Gui Caglar Gulcehre Barbara Hammer Hasan HammoudHasan Abed Al Kader Hammoud Moritz Hardt Jackson Harmon Tyler L. Hayes Nick Akinci Heidrich Olivier J. Hénaff Sergio Hernández-Gutiérrez José Hernández-Orallo Timm Hess Andreas Hochlehnert Sicong Huang 0001 Alesia Ivanova Alon Jacovi Natasha Jaques Jenia Jitsev Aditya Joshi Robert Kaczmarczyk Bhavya Kailkhura Christopher Kanan Shyamgopal Karthik Derik Kauffman Douwe Kiela Najoung Kim Robert Kirk Aaron Kirtland A. Sophia Koepke Vladlen Koltun Tomasz Korbak Evgenii Kortukov Harish Krishna David Krueger 0001 Dhireesha Kudithipudi Ponnurangam Kumaraguru Kwok-Yan Lam Ivan Laptev Sebastian Lapuschkin Jiawei Li Peggy Li Runjia Li Wenjie Li Yucheng Li Ser-Nam Lim Alisa Liu Jiacheng Liu 0010 Pengfei Liu 0003 Xialei Liu Vincenzo Lomonaco Charles London Alexander Lyzhov Anne-Sofie Maerten Senthil Mani Tavish McDonald Ian R. McKenzie Euan McLean Jorge Mendez-Mendez Sören Mindermann Sumeet Ramesh Motwani Aaron Mueller Sri Aurobindo Munagala Martin Mundt Akshat Naik Anoop M. Namboodiri Surabhi S. Nath Elisa Nguyen Huu Nguyen Karina Nguyen Daniel Nichols Kristina Nikolic Aidan O'Gara Seong Joon Oh C.-H. Luke OngLuke Ong Bhavish Pahwa Monik Pamecha Alexander Panfilov Alicia Parrish Darshan Patil Ethan Perez Michael Pieler Fabio Pizzati Ofir Press Ori Press Gollam Rabby Ben Rank Gabriel Recchia Elisa Ricci 0001 Alexis Ross Karsten Roth Alexander Rubinstein 0002 Soham Saha Oscar Sainz Wojciech Samek Anush Sankaran Amartya Sanyal Ludwig Schmidt Christoph Schuhmann Malte Schwerin Ozan Sener Suryansh Sharma Yash Sharma 0001 Xudong Shen Manish Shrivastava 0001 Emily Silcock Maneesh Kumar Singh 0001Maneesh Singh 0001 Shiven Sinha Ronald Skorobogat Kateryna Solonko Steffen Staab David Stap Joschka Strüber Sidhant Subramanian Shuyang Sun Mihai Surdeanu Srikanth Tamilselvam Mikhail Terekhov Philip Torr 0001Philip H. S. Torr Robert Trager Tom Tseng Yu-Min Tseng Tinne Tuytelaars Vishaal Udandarao Girish Varma Vasudeva Varma Gido M. van de Ven Juliane Verwiebe Oriol Vinyals Johan Wagemans Liyuan Wang Zengzhi Wang Joost van de Weijer 0001 Max Weiss Thaddäus Wiedemer Christian Schröder de WittChristian Schroeder de Witt Daniel Wurgaft Ruijie Xu 0005 Jinglin Yang Jianhao Yuan Pengcheng Zeng Yuhui Zhang Zhengping Zhou Daniil Zverev