AIConfPaper
← Search

Bahareh Tolooshams

9 accepted papers

2025

A Unified Model for Compressed Sensing MRI Across Undersampling Patterns

Armeet Singh Jatyani, Jiayun Wang, Aditi Chandrashekar, Zihui Wu, Miguel Liu-Schiaffini, Bahareh Tolooshams +1
CVPR 2025poster

Compressed Sensing MRI reconstructs images of the body's internal anatomy from undersampled measurements, thereby reducing the scan time - the time subjects need to remain still. Recently, deep learning has shown great potential for reconstructing high-fidelity images from highly undersampled measu…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Diffusion State-Guided Projected Gradient for Inverse Problems

Rayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar
ICLR 2025poster

Recent advancements in diffusion models have been effective in learning data priors for solving inverse problems. They leverage diffusion sampling steps for inducing a data prior while using a measurement guidance gradient at each step to impose data consistency. For general inverse problems, approx…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba E. Ba
NeurIPS 2025poster

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability literature. However, recent work has demonstrated phenomenolo…

Cited by 0Source ↗Scholar ↗
2025

NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models

Luca Ghafourpour, Valentin Duruisseaux, Bahareh Tolooshams, Philip H. Wong, Costas A. Anastassiou, Anima Anandkumar
NeurIPS 2025poster

Characterizing the cellular properties of neurons is fundamental to understanding their function in the brain. In this quest, the generation of bio-realistic models is central towards integrating multimodal cellular data sets and establishing causal relationships. However, current modeling approach…

Cited by 0Source ↗Scholar ↗
2023

Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models

Alexander Lin, Bahareh Tolooshams, Yves Atchade, Demba E. Ba
ICML 2023poster

Latent Gaussian models have a rich history in statistics and machine learning, with applications ranging from factor analysis to compressed sensing to time series analysis. The classical method for maximizing the likelihood of these models is the expectation-maximization (EM) algorithm. For problems…

Cited by 1Source ↗PDF ↗Scholar ↗
2022

A Training Framework for Stereo-Aware Speech Enhancement Using Deep Neural Networks

Bahareh Tolooshams, Kazuhito Koishida
ICASSP 2022accepted

Deep learning-based speech enhancement has shown unprecedented performance in recent years. The most popular mono speech enhancement frameworks are end-to-end networks mapping the noisy mixture into an estimate of the clean speech. With growing computational power and availability of multichannel mi…

Cited by 0Source ↗Scholar ↗
2021

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution

Bahareh Tolooshams, Satish Mulleti, Demba E. Ba, Yonina C. Eldar
ICASSP 2021accepted

We propose a learned-structured unfolding neural network for the problem of compressive sparse multichannel blind-deconvolution. In this problem, each channel’s measurements are given as convolution of a common source signal and sparse filter. Unlike prior works where the compression is achieved eit…

Cited by 0Source ↗Scholar ↗
2020

Channel-Attention Dense U-Net for Multichannel Speech Enhancement

Bahareh Tolooshams, Ritwik Giri, Andrew H. Song, Umut Isik, Arvindh Krishnaswamy
ICASSP 2020accepted

Supervised deep learning has gained significant attention for speech enhancement recently. The state-of-the-art deep learning methods perform the task by learning a ratio/binary mask that is applied to the mixture in the time-frequency domain to produce the clean speech. Despite the great performanc…

Cited by 0Source ↗Scholar ↗
2020

Convolutional dictionary learning based auto-encoders for natural exponential-family distributions

Bahareh Tolooshams, Andrew Song, Simona Temereanca, Demba Ba
ICML 2020poster

We introduce a class of auto-encoder neural networks tailored to data from the natural exponential family (e.g., count data). The architectures are inspired by the problem of learning the filters in a convolutional generative model with sparsity constraints, often referred to as convolutional dictio…

Cited by 36Source ↗PDF ↗code ↗Scholar ↗