Ba, Demba E.

12 publications

ICML 2025 Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle

NeurIPS 2025 From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba E. Ba

NeurIPS 2025 Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry Sai Sumedh R. Hindupur, Ekdeep Singh Lubana, Thomas Fel, Demba E. Ba

ICLRW 2025 Traveling Waves Integrate Spatial Information into Spectral Representations Mozes Jacobs, Roberto C. Budzinski, Lyle Muller, Demba E. Ba, T. Anderson Keller

ICMLW 2024 Constructing Gauge-Invariant Neural Networks for Scientific Applications Manos Theodosis, Demba E. Ba, Nima Dehmamy

ICMLW 2024 Constructing Gauge-Invariant Neural Networks for Scientific Applications Manos Theodosis, Demba E. Ba, Nima Dehmamy

TMLR 2024 Discriminative Reconstruction via Simultaneous Dense and Sparse Coding Abiy Tasissa, Manos Theodosis, Bahareh Tolooshams, Demba E. Ba

ICML 2023 Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models Alexander Lin, Bahareh Tolooshams, Yves Atchade, Demba E. Ba

NeurIPSW 2022 Learning Unfolded Networks with a Cyclic Group Structure Manos Theodosis, Demba E. Ba

NeurIPSW 2022 Local Geometry Constraints in V1 with Deep Recurrent Autoencoders Jonathan Raymond Huml, Demba E. Ba

NeurIPSW 2022 Sparse, Geometric Autoencoder Models of V1 Jonathan Raymond Huml, Abiy Tasissa, Demba E. Ba

TMLR 2022 Stable and Interpretable Unrolled Dictionary Learning Bahareh Tolooshams, Demba E. Ba