Ekdeep Singh Lubana

According to our database, Ekdeep Singh Lubana authored at least 34 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Abrupt Learning in Transformers: A Case Study on Matrix Completion.

Pulkit Gopalani, Ekdeep Singh Lubana, Wei Hu

CoRR, 2024

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs.

Itamar Pres, Laura Ruis, Ekdeep Singh Lubana, David Krueger

CoRR, 2024

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing.

Kento Nishi, Maya Okawa, Rahul Ramesh, Mikail Khona, Ekdeep Singh Lubana, Hidenori Tanaka

CoRR, 2024

Analyzing (In)Abilities of SAEs via Formal Languages.

Abhinav Menon, Manish Shrivastava, David Krueger, Ekdeep Singh Lubana

CoRR, 2024

Dynamics of Concept Learning and Compositional Generalization.

Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana, Maya Okawa, Wei Hu, Hidenori Tanaka

CoRR, 2024

A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language.

Ekdeep Singh Lubana, Kyogo Kawaguchi, Robert P. Dick, Hidenori Tanaka

CoRR, 2024

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania

CoRR, 2024

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space.

Core Francisco Park, Maya Okawa, Andrew Lee, Ekdeep Singh Lubana, Hidenori Tanaka

CoRR, 2024

Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, José Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Yoshua Bengio, Danqi Chen, Samuel Albanie, Tegan Maharaj, Jakob N. Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger

CoRR, 2024

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks.

Rahul Ramesh, Ekdeep Singh Lubana, Mikail Khona, Robert P. Dick, Hidenori Tanaka

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model.

Mikail Khona, Maya Okawa, Jan Hula, Rahul Ramesh, Kento Nishi, Robert P. Dick, Ekdeep Singh Lubana, Hidenori Tanaka

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks.

Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tim Rocktäschel, Edward Grefenstette, David Scott Krueger

Proceedings of the Twelfth International Conference on Learning Representations, 2024

In-Context Learning Dynamics with Random Binary Sequences.

Eric J. Bigelow, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tomer D. Ullman

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

FoMo Rewards: Can we cast foundation models as reward functions?

Ekdeep Singh Lubana, Johann Brehmer, Pim de Haan, Taco Cohen

CoRR, 2023

How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks.

Rahul Ramesh, Mikail Khona, Robert P. Dick, Hidenori Tanaka, Ekdeep Singh Lubana

CoRR, 2023

What Mechanisms Does Knowledge Distillation Distill?

Cindy Wu, Ekdeep Singh Lubana, Bruno Kacper Mlodozeniec, Robert Kirk, David Krueger

Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, 2023

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task.

Maya Okawa, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mechanistic Mode Connectivity.

Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick, David Scott Krueger, Hidenori Tanaka

Proceedings of the International Conference on Machine Learning, 2023

What shapes the loss landscape of self supervised learning?

Ziyin Liu, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Analyzing Data-Centric Properties for Contrastive Learning on Graphs.

Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, Jayaraman J. Thiagarajan

CoRR, 2022

Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices.

Puja Trivedi, Ekdeep Singh Lubana, Yujun Yan, Yaoqing Yang, Danai Koutra

Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022

Analyzing Data-Centric Properties for Graph Contrastive Learning.

Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, Jayaraman J. Thiagarajan

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering.

Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar, Robert P. Dick, Akhil Mathur

Proceedings of the International Conference on Machine Learning, 2022

How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation.

Ekdeep Singh Lubana, Puja Trivedi, Danai Koutra, Robert P. Dick

Proceedings of the Conference on Lifelong Learning Agents, 2022

2021

Beyond BatchNorm: Towards a General Understanding of Normalization in Deep Learning.

Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka

CoRR, 2021

Rethinking Quadratic Regularizers: Explicit Movement Regularization for Continual Learning.

Ekdeep Singh Lubana, Puja Trivedi, Robert P. Dick

CoRR, 2021

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning.

Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Gradient Flow Framework For Analyzing Network Pruning.

Ekdeep Singh Lubana, Robert P. Dick

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

OrthoReg: Robust Network Pruning Using Orthonormality Regularization.

Ekdeep Singh Lubana, Puja Trivedi, Conrad D. Hougen, Robert P. Dick, Alfred O. Hero III

CoRR, 2020

Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision.

Benjamin Simpson, Ekdeep Singh Lubana, Yuchen Liu, Robert P. Dick

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Minimalistic Image Signal Processing for Deep Learning Applications.

Ekdeep Singh Lubana, Robert P. Dick, Vinayak Aggarwal, Pyari Mohan Pradhan

Proceedings of the 2019 IEEE International Conference on Image Processing, 2019

Machine Foveation: An Application-Aware Compressive Sensing Framework.

Ekdeep Singh Lubana, Vinayak Aggarwal, Robert P. Dick

Proceedings of the Data Compression Conference, 2019

2018

Digital Foveation: An Energy-Aware Machine Vision Framework.

Ekdeep Singh Lubana, Robert P. Dick

IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2018

Snap: Chlorophyll Concentration Calculator Using RAW Images of Leaves.

Ekdeep Singh Lubana, Mangesh Gurav, Maryam Shojaei Baghini

Proceedings of the 2018 IEEE SENSORS, New Delhi, India, October 28-31, 2018, 2018