Lubana, Ekdeep Singh
- Foundational Challenges in Assuring Alignment and Safety of Large Language Models
2024/04/15 by Anwar, Usman, Abulhair Saparov, Saparov, Abulhair +76 · 31 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Data Quality and Management #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
2024/06/27 by Core Francisco Park, Maya Okawa, Park, Core Francisco +8 · 5 voices · 6 citations
Psychology · #cs.LG #cs.AI
- Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
2023/10/13 by Okawa, Maya, Lubana, Ekdeep Singh, Dick, Robert P. +1 · 17 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
2023/11/21 by Samyak Jain, Jain, Samyak, Robert Kirk +13 · 15 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #Topic Modeling #Adversarial Robustness in Machine Learning
- Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
2025/02/18 by Thomas Fel, Fel, Thomas, Ekdeep Singh Lubana +17 · 20 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Multimodal Machine Learning Applications
- What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
2024/07/14 by Jain, Samyak, Lubana, Ekdeep Singh, Oksuz, Kemal +4 · 14 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Mechanistic Mode Connectivity
2022/11/15 by Ekdeep Singh Lubana, Lubana, Ekdeep Singh, Eric Bigelow +7 · 7 citations
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Neural Networks and Applications
- Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
2025/03/03 by Sai Sumedh R. Hindupur, Ekdeep Singh Lubana, Hindupur, Sai Sumedh R. +5 · 1 voice · 14 citations
Computer Science · #Image Processing and 3D Reconstruction
- Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning
2021/06/10 by Ekdeep Singh Lubana, Robert P. Dick, Lubana, Ekdeep Singh +3 · 4 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
2024/10/22 by Itamar Pres, Laura Ruis, Pres, Itamar +5 · 7 citations
Engineering · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Safety Systems Engineering in Autonomy
- How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation
2021/02/04 by Ekdeep Singh Lubana, Lubana, Ekdeep Singh, Puja Trivedi +5 · 3 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
- In-Context Learning Dynamics with Random Binary Sequences
2023/10/26 by Eric Bigelow, Ekdeep Singh Lubana, Bigelow, Eric J. +7 · 5 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Language and cultural evolution #Machine Learning (cs.LG) #Topic Modeling
- Analyzing (In)Abilities of SAEs via Formal Languages
2024/10/15 by Menon, Abhinav, Shrivastava, Manish, Krueger, David +1 · 7 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
2025/06/03 by Valérie Costa, VINICIUS OLIVEIRA DA COSTA, Thomas Fel +9 · 1 voice · 10 citations
Computer Science · #Data Visualization and Analytics #Video Analysis and Summarization #cs.LG
- Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
2022/05/23 by Lubana, Ekdeep Singh, Tang, Chi Ian, Kawsar, Fahim +2 · 3 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Detecting High-Stakes Interactions with Activation Probes
2025/06/12 by McKenzie, Alex, Pawar, Urja, Blandfort, Phil +4 · 12 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
2024/08/22 by Ekdeep Singh Lubana, Lubana, Ekdeep Singh, Kawaguchi, Kyogo +4 · 5 citations
Physics and Astronomy · Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Language and cultural evolution #Machine Learning (cs.LG) #Opinion Dynamics and Social Influence
- Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
2023/11/21 by Rahul Ramesh, Ekdeep Singh Lubana, Ramesh, Rahul +7 · 3 citations
Computer Science · Psychology · #AI in Service Interactions #FOS: Computer and information sciences #Human-Automation Interaction and Safety #Machine Learning (cs.LG) #Speech and dialogue systems
- In-Context Learning Strategies Emerge Rationally
2025/06/21 by Daniel Wurgaft, Ekdeep Singh Lubana, Wurgaft, Daniel +9 · 2 voices · 5 citations
#cs.LG #cs.AI
- What shapes the loss landscape of self-supervised learning?
2022/10/02 by Liu Ziyin, Ziyin, Liu, Ekdeep Singh Lubana +5 · 2 citations
Computer Science · #Data Analysis #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Physical sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning and Data Classification #Statistics and Probability (physics.data-an)
- Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
2024/10/22 by Kento Nishi, Nishi, Kento, Rahul Ramesh +9 · 4 citations
Computer Science · #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Semantic Web and Ontologies
- A Gradient Flow Framework For Analyzing Network Pruning
2020/09/24 by Ekdeep Singh Lubana, Lubana, Ekdeep Singh, Robert P. Dick +1 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Network Security and Intrusion Detection #Software Testing and Debugging Techniques #Software-Defined Networks and 5G
- Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
2021/11/05 by Trivedi, Puja, Lubana, Ekdeep Singh, Yan, Yujun +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Abrupt Learning in Transformers: A Case Study on Matrix Completion
2024/10/29 by Pulkit Gopalani, Ekdeep Singh Lubana, Gopalani, Pulkit +3 · 3 citations
Computer Science · #Computability, Logic, AI Algorithms #Neural Networks and Applications
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
2025/11/01 by Eric Bigelow, Bigelow, Eric, Daniel Wurgaft +12 · 1 voice · 3 citations
Computer Science · Neuroscience · #Topic Modeling #Explainable Artificial Intelligence (XAI) #Embodied and Extended Cognition
- Analyzing Data-Centric Properties for Graph Contrastive Learning
2022/08/04 by Trivedi, Puja, Lubana, Ekdeep Singh, Heimann, Mark +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Swing-by Dynamics in Concept Learning and Compositional Generalization
2024/10/10 by Yang, Yongyi, Park, Core Francisco, Lubana, Ekdeep Singh +3 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- The Impact of Off-Policy Training Data on Probe Generalisation
2025/11/21 by Nathalie Kirch, Kirch, Nathalie, Samuel Dower +7 · 2 citations
Computer Science · Neuroscience · #Topic Modeling #Neurobiology of Language and Bilingualism #Speech and dialogue systems
- Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
2024/02/12 by Khona, Mikail, Okawa, Maya, Hula, Jan +5 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Priors in Time: Missing Inductive Biases for Language Model Interpretability
2025/11/03 by Lubana, Ekdeep Singh, Rager, Can, Hindupur, Sai Sumedh R. +13 · 2 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #Multimodal Machine Learning Applications #Topic Modeling