Publications

FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
Luca Della Libera
Cem Subakan
Mirco Ravanelli
Neural audio codecs are a fundamental component of modern generative audio pipelines. Although recent codecs achieve strong low-bitrate reco… (voir plus)nstruction and provide powerful representations for downstream tasks, most are non-streamable, limiting their use in real-time applications. We present FocalCodec-Stream, a hybrid codec based on focal modulation that compresses speech into a single binary codebook at 0.55 - 0.80 kbps with a theoretical latency of 80 ms. Our approach combines multi-stage causal distillation of WavLM with targeted architectural improvements, including a lightweight refiner module that enhances quality under latency constraints. Experiments show that FocalCodec-Stream outperforms existing streamable codecs at comparable bitrates, while preserving both semantic and acoustic information. The result is a favorable trade-off between reconstruction quality, downstream task performance, latency, and efficiency. Code and checkpoints will be released at https://github.com/lucadellalib/focalcodec.
2025-09-01
arXiv (publié)
doi.org
arxiv.org
Identifying birdsong syllables without labelled data
Mélisande Teng
Julien Boussard
David Rolnick
Hugo Larochelle
Identifying sequences of syllables within birdsongs is key to tackling a wide array of challenges, including bird individual identification … (voir plus)and better understanding of animal communication and sensory-motor learning. Recently, machine learning approaches have demonstrated great potential to alleviate the need for experts to label long audio recordings by hand. However, they still typically rely on the availability of labelled data for model training, restricting applicability to a few species and datasets. In this work, we build the first fully unsupervised algorithm to decompose birdsong recordings into sequences of syllables. We first detect syllable events, then cluster them to extract templates -- syllable representations -- before performing matching pursuit to decompose the recording as a sequence of syllables. We evaluate our automatic annotations against human labels on a dataset of Bengalese finch songs and find that our unsupervised method achieves high performance. We also demonstrate that our approach can distinguish individual birds within a species through their unique vocal signatures, for both Bengalese finches and another species, the great tit.
2025-09-01
arXiv (publié)
doi.org
arxiv.org
Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance
Mohamed Mohamed
Brennan Nichyporuk
Douglas Arnold
Tal Arbel
Vision-language models have demonstrated impressive capabilities in generating 2D images under various conditions; however the impressive pe… (voir plus)rformance of these models in 2D is largely enabled by extensive, readily available pretrained foundation models. Critically, comparable pretrained foundation models do not exist for 3D, significantly limiting progress in this domain. As a result, the potential of vision-language models to produce high-resolution 3D counterfactual medical images conditioned solely on natural language descriptions remains completely unexplored. Addressing this gap would enable powerful clinical and research applications, such as personalized counterfactual explanations, simulation of disease progression scenarios, and enhanced medical training by visualizing hypothetical medical conditions in realistic detail. Our work takes a meaningful step toward addressing this challenge by introducing a framework capable of generating high-resolution 3D counterfactual medical images of synthesized patients guided by free-form language prompts. We adapt state-of-the-art 3D diffusion models with enhancements from Simple Diffusion and incorporate augmented conditioning to improve text alignment and image quality. To our knowledge, this represents the first demonstration of a language-guided native-3D diffusion model applied specifically to neurological imaging data, where faithful three-dimensional modeling is essential to represent the brain's three-dimensional structure. Through results on two distinct neurological MRI datasets, our framework successfully simulates varying counterfactual lesion loads in Multiple Sclerosis (MS), and cognitive states in Alzheimer's disease, generating high-quality images while preserving subject fidelity in synthetically generated medical images. Our results lay the groundwork for prompt-driven disease progression analysis within 3D medical imaging.
2025-09-01
arXiv (publié)
doi.org
arxiv.org
Metabolic Control and Frequency of Clinical Monitoring Among Canadian Children With Phenylalanine Hydroxylase Deficiency: A Retrospective Cohort Study
Nataliya Yuskiv
Ammar Saad
Beth K. Potter
Sylvia Stockler‐Ipsiroglu
John J. Mitchell
Steven Hawken
Kylie Tingley
Michael Pugliese
Monica Lamoureux
Andrea J. Chow
Jonathan B. Kronick
Kumanan Wilson
Annette Feigenbaum
Sharan Goobie
Michal Inbar-Feigenberg
Julian Little
Saadet Mercimek‐Andrews
Amy Pender
Chitra Prasad
Andreas Schulze … (voir 9 de plus)
Yannis Trakadis
Gloria Ho
Hilary Vallance
Valerie Austin
Anthony Vandersteen
Andrea C. Yu
Cheryl Rockman‐Greenberg
Aizeddin Mhanni
Pranesh Chakraborty
2025-09-01
JIMD Reports (publié)
doi.org
A Multimodal and Multi-centric Head and Neck Cancer Dataset for Segmentation, Diagnosis and Outcome Prediction
Numan Saeed
Salma Hassan
Shahad Hardan
Ahmed Aly
Darya Taratynova
Umair Nawaz
Ufaq Khan
Muhammad Ridzuan
Vincent Andrearczyk
Adrien Depeursinge
Yutong Xie
Thomas Eugene
Raphael Metz
Mélanie Dore
Gregory Delpon
Vijay Ram Kumar Papineni
Kareem Wahid
Cem Dede
Alaa Mohamed Shawky Ali
Carlos Sjogreen … (voir 23 de plus)
Mohamed Naser
Clifton D. Fuller
Valentin Oreiller
Mario Jreige
John O. Prior
Catherine Cheze Le Rest
Olena Tankyevych
Pierre Decazes
Su Ruan
Stephanie Tanadini-Lang
Martin Vallières
Hesham M. Elhalawani
Ronan Abgral
Romain Floch
Kevin Kerleguer
Ulrike Schick
Maelle Mauguen
David Bourhis
Jean-Christophe Leclere
Amandine Sambourg
Arman Rahmim
Mathieu Hatt
Mohammad Yaqub
We present a publicly available multimodal dataset for head and neck cancer research, comprising 1123 annotated Positron Emission Tomography… (voir plus)/Computed Tomography (PET/CT) studies from patients with histologically confirmed disease, acquired from 10 international medical centers. All studies contain co-registered PET/CT scans with varying acquisition protocols, reflecting real-world clinical diversity from a long-term, multi-institution retrospective collection. Primary gross tumor volumes (GTVp) and involved lymph nodes (GTVn) were manually segmented by experienced radiation oncologists and radiologists following established guidelines. We provide anonymized NifTi files, expert-annotated segmentation masks, comprehensive clinical metadata, and radiotherapy dose distributions for a patient subset. The metadata include TNM staging, HPV status, demographics, long-term follow-up outcomes, survival times, censoring indicators, and treatment information. To demonstrate its utility, we benchmark three key clinical tasks: automated tumor segmentation, recurrence-free survival prediction, and HPV status classification, using state-of-the-art deep learning models like UNet, SegResNet, and multimodal prognostic frameworks.
2025-09-01
arXiv (publié)
doi.org
OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
Victor Livernoche
Akshatha Arodi
Andreea Musulan
Zachary Yang
Adam Salvail
Gaétan Marceau Caron
Jean-François Godbout
Reihaneh Rabbany
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically… (voir plus) sensitive contexts. This challenge is amplified by the increasing realism of modern generative models, which our human perception study confirms are often indistinguishable from real images. Yet, existing deepfake detection benchmarks rely on outdated generators or narrowly scoped datasets (e.g., single-face imagery), limiting their utility for real-world detection. To address these gaps, we present OpenFake, a large politically grounded dataset specifically crafted for benchmarking against modern generative models with high realism, and designed to remain extensible through an innovative crowdsourced adversarial platform that continually integrates new hard examples. OpenFake comprises nearly four million total images: three million real images paired with descriptive captions and almost one million synthetic counterparts from state-of-the-art proprietary and open-source models. Detectors trained on OpenFake achieve near-perfect in-distribution performance, strong generalization to unseen generators, and high accuracy on a curated in-the-wild social media test set, significantly outperforming models trained on existing datasets. Overall, we demonstrate that with high-quality and continually updated benchmarks, automatic deepfake detection is both feasible and effective in real-world settings.
2025-09-01
arXiv (publié)
doi.org
Reasoning with Preference Constraints: A Benchmark for Language Models in Many-to-One Matching Markets
Marylou Fauchard
Florian Carichon
Margarida Carvalho
Golnoosh Farnadi
Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including… (voir plus) combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have further enhanced this capability, making LLMs both powerful and accessible tools for a wide range of users, including non-experts. However, applying LLMs to matching problems, which require reasoning under preferential and structural constraints, remains underexplored. To address this gap, we introduce a novel benchmark of 369 instances of the College Admission Problem, a canonical example of a matching problem with preferences, to evaluate LLMs across key dimensions: feasibility, stability, and optimality. We employ this benchmark to assess the performance of several open-weight LLMs. Our results first reveal that while LLMs can satisfy certain constraints, they struggle to meet all evaluation criteria consistently. They also show that reasoning LLMs, like QwQ and GPT-oss, significantly outperform traditional models such as Llama, Qwen or Mistral, defined here as models used without any dedicated reasoning mechanisms. Moreover, we observed that LLMs reacted differently to the various prompting strategies tested, which include Chain-of-Thought, In-Context Learning and role-based prompting, with no prompt consistently offering the best performance. Finally, we report the performances from iterative prompting with auto-generated feedback and show that they are not monotonic; they can peak early and then significantly decline in later attempts. Overall, this work offers a new perspective on model reasoning performance and the effectiveness of prompting strategies in combinatorial optimization problems with preferential constraints.
2025-09-01
arXiv (publié)
doi.org
Relative Trajectory Balance is equivalent to Trust-PCL
Tristan Deleu
Padideh Nouri
Yoshua Bengio
Doina Precup
Recent progress in generative modeling has highlighted the importance of Reinforcement Learning (RL) for fine-tuning, with KL-regularized me… (voir plus)thods in particular proving to be highly effective for both autoregressive and diffusion models. Complementing this line of work, the Relative Trajectory Balance (RTB) objective was recently introduced in the context of Generative Flow Networks (GFlowNets) to serve the same role of improving fine-tuning in sequential generative models. Building on prior work linking GFlowNets and maximum-entropy RL, we establish in this paper an equivalence between RTB and Trust-PCL, an off-policy RL method with KL regularization. This equivalence situates RTB within the broader theoretical landscape of KL-regularized RL, and clarifies its relationship to earlier methods. Leveraging this insight, we revisit an illustrative example from the RTB paper and show that KL-regularized RL methods achieve comparable performance, offering an alternative perspective to what was previously reported.
2025-09-01
ArXiv (prépublication)
doi.org
arxiv.org
Relative Trajectory Balance is equivalent to Trust-PCL
Tristan Deleu
Padideh Nouri
Yoshua Bengio
Doina Precup
2025-09-01
ArXiv (prépublication)
doi.org
arxiv.org
Relative Trajectory Balance is equivalent to Trust-PCL
Tristan Deleu
Padideh Nouri
Yoshua Bengio
Doina Precup
Recent progress in generative modeling has highlighted the importance of Reinforcement Learning (RL) for fine-tuning, with KL-regularized me… (voir plus)thods in particular proving to be highly effective for both autoregressive and diffusion models. Complementing this line of work, the Relative Trajectory Balance (RTB) objective was recently introduced in the context of Generative Flow Networks (GFlowNets) to serve the same role of improving fine-tuning in sequential generative models. Building on prior work linking GFlowNets and maximum-entropy RL, we establish in this paper an equivalence between RTB and Trust-PCL, an off-policy RL method with KL regularization. This equivalence situates RTB within the broader theoretical landscape of KL-regularized RL, and clarifies its relationship to earlier methods. Leveraging this insight, we revisit an illustrative example from the RTB paper and show that KL-regularized RL methods achieve comparable performance, offering an alternative perspective to what was previously reported.
2025-09-01
arXiv (publié)
doi.org
SSL-AD: Spatiotemporal Self-Supervised Learning for Generalizability and Adaptability Across Alzheimer's Prediction Tasks and Datasets
Emily Kaczmarek
Justin Szeto
Brennan Nichyporuk
Tal Arbel
Alzheimer's disease is a progressive, neurodegenerative disorder that causes memory loss and cognitive decline. While there has been extensi… (voir plus)ve research in applying deep learning models to Alzheimer's prediction tasks, these models remain limited by lack of available labeled data, poor generalization across datasets, and inflexibility to varying numbers of input scans and time intervals between scans. In this study, we adapt three state-of-the-art temporal self-supervised learning (SSL) approaches for 3D brain MRI analysis, and add novel extensions designed to handle variable-length inputs and learn robust spatial features. We aggregate four publicly available datasets comprising 3,161 patients for pre-training, and show the performance of our model across multiple Alzheimer's prediction tasks including diagnosis classification, conversion detection, and future conversion prediction. Importantly, our SSL model implemented with temporal order prediction and contrastive learning outperforms supervised learning on six out of seven downstream tasks. It demonstrates adaptability and generalizability across tasks and number of input images with varying time intervals, highlighting its capacity for robust performance across clinical applications. We release our code and model publicly at https://github.com/emilykaczmarek/SSL-AD.
2025-09-01
arXiv (publié)
doi.org
On the frequency variation in load-flow calculations for islanded alternating current microgrids
Matthias Molénat
Jean Mahseredjian
Nasim Rashidirad
Antoine Lesage-Landry
2025-09-01
Mathematics and Computers in Simulation (publié)
doi.org