Publications

Graph Neural Networks Meet Probabilistic Graphical Models: A Survey
Chenqing Hua
Sitao Luan
Qian Zhang
Jie Fu
Guy Wolf
2025-04-05
IEEE International Conference on Acoustics, Speech, and Signal Processing (publié)
doi.org
Hyperedge Representations with Hypergraph Wavelets: Applications to Spatial Transcriptomics
Xingzhi Sun
Charles Xu
João Felipe Rocha
Chen Liu
Benjamin Hollander-Bodie
Laney Goldman
Marcello DiStasio
Michael Perlmutter
Smita Krishnaswamy
In many data-driven applications, higher-order relationships among multiple objects are essential in capturing complex interactions. Hypergr… (voir plus)aphs, which generalize graphs by allowing edges to connect any number of nodes, provide a flexible and powerful framework for modeling such higher-order relationships. In this work, we introduce hypergraph diffusion wavelets and describe their favorable spectral and spatial properties. We demonstrate their utility for biomedical discovery in spatially resolved transcriptomics by applying the method to represent disease-relevant cellular niches for Alzheimer’s disease.
2025-04-05
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
Eleonora Mancini
Francesco Paissan
Paolo Torroni
Mirco Ravanelli
Cem Subakan
Speech impairments in Parkinson's disease (PD) provide significant early indicators for diagnosis. While models for speech-based PD detectio… (voir plus)n have shown strong performance, their interpretability remains underexplored. This study systematically evaluates several explainability methods to identify PD-specific speech features, aiming to support the development of accurate, interpretable models for clinical decision-making in PD diagnosis and monitoring. Our methodology involves (i) obtaining attributions and saliency maps using mainstream interpretability techniques, (ii) quantitatively evaluating the faithfulness of these maps and their combinations obtained via union and intersection through a range of established metrics, and (iii) assessing the information conveyed by the saliency maps for PD detection from an auxiliary classifier. Our results reveal that, while explanations are aligned with the classifier, they often fail to provide valuable information for domain experts.
2025-04-05
2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (publié)
doi.org
arxiv.org
Latent Representation Learning for Multimodal Brain Activity Translation
Arman Afrasiyabi
Dhananjay Bhaskar
Erica Lindsey Busch
Laurent Caplette
Rahul Singh
Guillaume Lajoie
Nicholas B Turk-Browne
Smita Krishnaswamy
Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordi… (voir plus)ngs such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision. However, integrating these heterogeneous data sources remains a challenge, which limits a comprehensive understanding of brain function. We present the Spatiotemporal Alignment of Multimodal Brain Activity (SAMBA) framework, which bridges the spatial and temporal resolution gaps across modalities by learning a unified latent space free of modality-specific biases. SAMBA introduces a novel attention-based wavelet decomposition for spectral filtering of electrophysiological recordings, graph attention networks to model functional connectivity between functional brain units, and recurrent layers to capture temporal autocorrelations in brain signal. We show that the training of SAMBA, aside from achieving translation, also learns a rich representation of brain information processing. We showcase this classify external stimuli driving brain activity from the representation learned in hidden layers of SAMBA, paving the way for broad downstream applications in neuroscience research and clinical contexts.
2025-04-05
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
Eleonora Mancini
Francesco Paissan
Mirco Ravanelli
Cem Subakan
Neural networks are typically black-boxes that remain opaque with regards to their decision mechanisms. Several works in the literature have… (voir plus) proposed post-hoc explanation methods to alleviate this issue. This paper proposes LMAC-TD, a post-hoc explanation method that trains a decoder to produce explanations directly in the time domain. This methodology builds upon the foundation of L-MAC, Listenable Maps for Audio Classifiers, a method that produces faithful and listenable explanations. We incorporate SepFormer, a popular transformer-based time-domain source separation architecture. We show through a user study that LMAC-TD significantly improves the audio quality of the produced explanations while not sacrificing from faithfulness.
2025-04-05
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
Principal Curvatures Estimation with Applications to Single Cell Data
Yanlei Zhang
Lydia Mezrag
Xingzhi Sun
Charles Xu
Kincaid MacDonald
Dhananjay Bhaskar
Smita Krishnaswamy
Guy Wolf
Bastian Rieck
2025-04-05
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
What Are They Doing? Joint Audio-Speech Co-Reasoning
Yingzhi Wang
Pooneh Mousavi
Artem Ploujnikov
Mirco Ravanelli
In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are prese… (voir plus)nt in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks. In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech processing, strictly requiring co-reasoning across both modalities. We also release a scene-reasoning dataset called "What Are They Doing". Additionally, we provide deeper insights into the models' behaviors by analyzing their dependence on each modality.
2025-04-05
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
Accelerated learning of a noninvasive human brain-computer interface via manifold geometry
Erica Lindsey Busch
E. Chandra Fincke
Guillaume Lajoie
Smita Krishnaswamy
Nicholas B Turk-Browne
2025-04-02
bioRxiv (prépublication)
doi.org
Spinal Cord Tract Integrity in Degenerative Cervical Myelopathy
Newton Cho
Abdul Al-Shawwa
W. Bradley Jacobs
Nathan Evaniew
Jacques Bouchard
Steve Casha
Stephan duPlessis
Peter Lewkonia
Fred Nicholls
Alex Soroceanu
Ganesh Swamy
Kenneth C. Thomas
Michael M. H. Yang
Julien Cohen-Adad
David W. Cadotte
Degenerative cervical myelopathy (DCM) is the most common cause of spinal dysfunction globally. Despite surgical intervention, motor dysfunc… (voir plus)tion may persist in many patients. The purpose of this study was to comprehensively examine specific spinal cord tract changes in patients with DCM, to better understand potential substrates for compensatory recovery of function. Cervical spinal cord MRI scans with diffusion tensor imaging were performed in patients with DCM and in healthy volunteers. Spinal Cord Toolbox was used to register the PAM50 template, which includes a probabilistic atlas of the white matter tracts of the spinal cord, to the imaging data. Fractional anisotropy (FA) was extracted for each tract at C3 above the level of maximal compression and compared between patients with DCM and healthy volunteers and between patients with mild vs moderate to severe DCM. We included 25 patients with DCM (13 mild and 12 moderate to severe) and 6 healthy volunteers. FA was significantly reduced in DCM subjects relative to healthy volunteers for the lateral corticospinal tract (mild DCM vs healthy ∆ = −0.13, P = .018; moderate to severe DCM vs healthy ∆ = −0.11, P = .047), fasciculus gracilis (mild DCM vs healthy ∆ = −0.16, P = .010; moderate to severe DCM vs healthy ∆ = −0.13, P = .039), and fasciculus cuneatus (mild DCM vs healthy ∆ = −0.16, P = .007; moderate to severe DCM vs healthy ∆ = −0.15, P = .012). There were no differences in FA for all tracts between mild and moderate-to-severe DCM subjects. Patients with DCM had altered diffusion tensor imaging signal in their lateral corticospinal tract, fasciculus gracilis, and fasciculus cuneatus in comparison with healthy volunteers. These findings indicate that DCM is characterized by injury to these structures, which suggests that other tracts within the cord could potentially act as substrates for compensatory motor recovery.
2025-04-02
Neurosurgery (inconnu)
doi.org
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
Sara Vera Marjanovi'c
Arkil Patel
Vaibhav Adlakha
Milad Aghajohari
Parishad BehnamGhader
Mehar Bhatia
Aditi Khandelwal
Austin Kraft
Benno Krojer
Xing Han Lu
Xing Han Lu
Nicholas Meade
Dongchan Shin
Amirhossein Kazemnejad
Gaurav Kamath
Marius Mosbach
Karolina Stanczak
Siva Reddy
Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an ans… (voir plus)wer for a given input, DeepSeek-R1 creates detailed multi-step reasoning chains, seemingly"thinking"about a problem before providing an answer. This reasoning process is publicly available to the user, creating endless opportunities for studying the reasoning behaviour of the model and opening up the field of Thoughtology. Starting from a taxonomy of DeepSeek-R1's basic building blocks of reasoning, our analyses on DeepSeek-R1 investigate the impact and controllability of thought length, management of long or confusing contexts, cultural and safety concerns, and the status of DeepSeek-R1 vis-\`a-vis cognitive phenomena, such as human-like language processing and world modelling. Our findings paint a nuanced picture. Notably, we show DeepSeek-R1 has a 'sweet spot' of reasoning, where extra inference time can impair model performance. Furthermore, we find a tendency for DeepSeek-R1 to persistently ruminate on previously explored problem formulations, obstructing further exploration. We also note strong safety vulnerabilities of DeepSeek-R1 compared to its non-reasoning counterpart, which can also compromise safety-aligned LLMs.
2025-04-01
ArXiv (prépublication)
arxiv.org
arxiv.org
A Truncated Newton Method for Optimal Transport
Mete Kemertas
Amir-massoud Farahmand
Allan D. Jepson
2025-04-01
ArXiv (prépublication)
doi.org
arxiv.org
Addressing Missing Modality Challenges in MRI Images: A Comprehensive Review
Reza Azad
Mohammad Dehghanmanshadi
Nika Khosravi
Julien Cohen-Adad
Dorit Merhof
2025-03-31
Computational Visual Media (publié)
doi.org