Publications

StarCoder: may the source be with you!
Raymond Li
Loubna Ben allal
Yangtian Zi
Niklas Muennighoff
Denis Kocetkov
Chenghao Mou
Marc Marone
Christopher Akiki
Jia LI
Jenny Chim
Qian Liu
Evgenii Zheltonozhskii
Terry Yue Zhuo
Thomas Wang
Olivier Dehaene
Mishig Davaadorj
Joel Lamy-Poirier
Joao Monteiro
Oleh Shliazhko
Nicolas Gontier … (see 47 more)
Nicholas Meade
Armel Zebaze
Ming-Ho Yee
Logesh Kumar Umapathi
Jian Zhu
Ben Lipkin
Muhtasham Oblokulov
Zhiruo Wang
Rudra Murthy
Jason T Stillerman
Siva Sankalp Patel
Dmitry Abulkhanov
Marco Zocca
Manan Dey
Zhihan Zhang
N. Fahmy
Urvashi Bhattacharyya
Wenhao Yu
Swayam Singh
Sasha Luccioni
Paulo Villegas
M. Kunakov
Fedor Zhdanov
Manuel Romero
Tony Lee
Nadav Timor
Jennifer Ding
Claire S Schlesinger
Hailey Schoelkopf
Jan Ebert
Tri Dao
Mayank Mishra
Alex Gu
Jennifer Robinson
Carolyn Jane Anderson
Brendan Dolan-Gavitt
Danish Contractor
Siva Reddy
Daniel Fried
Dzmitry Bahdanau
Yacine Jernite
Carlos Muñoz Ferrandis
Sean Hughes
Thomas Wolf
Arjun Guha
Leandro Von Werra
Harm de Vries
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs)… (see more), introduces StarCoder and StarCoderBase: 15.5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention. StarCoderBase is trained on 1 trillion tokens sourced from The Stack, a large collection of permissively licensed GitHub repositories with inspection tools and an opt-out process. We fine-tuned StarCoderBase on 35B Python tokens, resulting in the creation of StarCoder. We perform the most comprehensive evaluation of Code LLMs to date and show that StarCoderBase outperforms every open Code LLM that supports multiple programming languages and matches or outperforms the OpenAI code-cushman-001 model. Furthermore, StarCoder outperforms every model that is fine-tuned on Python and still retains its performance on other programming languages. We take several important steps towards a safe open-access model release, including an improved PII redaction pipeline and a novel attribution tracing tool, and make the StarCoder models publicly available under a more commercially viable version of the Open Responsible AI Model license.
2023-12-16
TMLR (accepted)
doi.org
openreview.net
RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain
Sangeet Sagar
Mirco Ravanelli
Bernd Kiefer
Ivana Kruijff-Korbayová
Josef van Genabith
Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional … (see more)speech in noisy and reverberant acoustic environments. This poses a particular challenge in the search and rescue (SAR) domain, where transcribing conversations among rescue team members is crucial to support real-time decision-making. The scarcity of speech data and associated background noise in SAR scenarios make it difficult to deploy robust speech recognition systems. To address this issue, we have created and made publicly available a German speech dataset called RescueSpeech. This dataset includes real speech recordings from simulated rescue exercises. Additionally, we have released competitive training recipes and pre-trained models. Our study highlights that the performance attained by state-of-the-art methods in this challenging scenario is still far from reaching an acceptable level.
2023-12-15
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)
doi.org
arxiv.org
Speech Emotion Diarization: Which Emotion Appears When?
Yingzhi Wang
Mirco Ravanelli
Alaa Nfissi
Alya Yacoubi
Speech Emotion Recognition (SER) typically relies on utterance-level solutions. However, emotions conveyed through speech should be consider… (see more)ed as discrete speech events with definite temporal boundaries, rather than attributes of the entire utterance. To reflect the fine-grained nature of speech emotions, we propose a new task: Speech Emotion Diarization (SED). Just as Speaker Diarization answers the question of "Who speaks when?", Speech Emotion Diarization answers the question of "Which emotion appears when?". To facilitate the evaluation of the performance and establish a common benchmark for researchers, we introduce the Zaion Emotion Dataset (ZED), an openly accessible speech emotion dataset that includes non-acted emotions recorded in real-life conditions, along with manually-annotated boundaries of emotion segments within the utterance. We provide competitive baselines and open-source the code and the pre-trained models.
2023-12-15
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)
doi.org
arxiv.org
TorchAudio 2.1: Advancing Speech Recognition, Self-Supervised Learning, and Audio Processing Components for Pytorch
Jeff Hwang
Moto Hira
Caroline Chen
Xiaohui Zhang
Zhaoheng Ni
Guangzhi Sun
Pingchuan Ma
Ruizhe Huang
Vineel Pratap
Yuekai Zhang
Anurag Kumar
Chin-Yun Yu
Chuang Zhu
Chunxi Liu
Jacob Kahn
Mirco Ravanaelli
Peng Sun
Shinji Watanabe
Yangyang Shi
Yumeng Tao … (see 4 more)
Robin Scheibler
Samuele Cornell
Sean Kim
Stavros Petridis
TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of au… (see more)dio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio’s development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.
2023-12-15
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)
doi.org
arxiv.org
Genetic landscape of an<i>in vivo</i>protein interactome
Savandara Besse
Tatsuya Sakaguchi
Louis Gauthier
Zahra Sahaf
Olivier Péloquin
Lidice Gonzalez
Xavier Castellanos-Girouard
Nazli Koçatug
Chloé Matta
Julie G. Hussin
Stephen W. Michnick
Adrian W.R. Serohijos
Protein-interaction quantitative trait locus (“piQTL”) mapping reveals sensitivity ofin vivoPPIs to polymorphisms across the yeast genom… (see more)eTrans-piQTLs significantly outnumber and are stronger than cis-piQTLsSNPs in non-coding RNAs and 3’ UTRs have comparable effects to PPI as SNPs in coding regionspiQTL mapping reveals known and novel mechanism of yeast and human drugs
2023-12-14
bioRxiv (preprint)
doi.org
Temporal encoding in deep reinforcement learning agents
Dongyan Lin
Ann Zixiang Huang
Blake Aaron Richards
Neuroscientists have observed both cells in the brain that fire at specific points in time, known as “time cells”, and cells whose activ… (see more)ity steadily increases or decreases over time, known as “ramping cells”. It is speculated that time and ramping cells support temporal computations in the brain and carry mnemonic information. However, due to the limitations in animal experiments, it is difficult to determine how these cells really contribute to behavior. Here, we show that time cells and ramping cells naturally emerge in the recurrent neural networks of deep reinforcement learning models performing simulated interval timing and working memory tasks, which have learned to estimate expected rewards in the future. We show that these cells do indeed carry information about time and items stored in working memory, but they contribute to behavior in large part by providing a dynamic representation on which policy can be computed. Moreover, the information that they do carry depends on both the task demands and the variables provided to the models. Our results suggest that time cells and ramping cells could contribute to temporal and mnemonic calculations, but the way in which they do so may be complex and unintuitive to human observers.
2023-12-14
Scientific Reports (published)
doi.org
Feasibility of cognitive neuroscience data collection during a speleological expedition
Anita Paas
Hugo R. Jourde
Arnaud Brignol
Marie-Anick Savard
Zseyvfin Eyqvelle
Samuel Bassetto
Giovanni Beltrame
Emily B.J. Coffey
In human cognitive neuroscience and neuropsychology studies, laboratory-based research tasks have been important to establish principles of … (see more)brain function and its relationship to behaviour; however, they differ greatly from real-life experiences. Several elements of real-life situations that impact human performance, such as stressors, are difficult or impossible to replicate in the laboratory. Expeditions offer unique possibilities for studying human cognition in complex environments that can transfer to other situations with similar features. For example, as caves share several of the physical and psychological challenges of safety-critical environments such as spaceflight, underground expeditions have been developed as an analogue for astronaut training purposes, suggesting that they might also be suitable for studying aspects of behaviour and cognition that cannot be fully examined under laboratory conditions. While a large range of topics and tools have been proposed for use in such environments, few have been evaluated in the field. We tested the feasibility of collecting human physiological, cognitive, and subjective experience data concerning brain state, sleep, cognitive workload, and fatigue, during a speleological expedition in a remote region. We document our approaches and challenges experienced, and provide recommendations and suggestions to aid future work. The data support the idea that cave expeditions are relevant naturalistic paradigms that offer unique possibilities for cognitive neuroscience to complement laboratory work and help improve human performance and safety in operational environments.
2023-12-13
bioRxiv (preprint)
doi.org
Learning to repeatedly solve routing problems
Mouad Morabit
Guy Desaulniers
Andrea Lodi
In the last years, there has been a great interest in machine‐learning‐based heuristics for solving NP‐hard combinatorial optimization… (see more) problems. The developed methods have shown potential on many optimization problems. In this paper, we present a learned heuristic for the reoptimization of a problem after a minor change in its data. We focus on the case of the capacited vehicle routing problem with static clients (i.e., same client locations) and changed demands. Given the edges of an original solution, the goal is to predict and fix the ones that have a high chance of remaining in an optimal solution after a change of client demands. This partial prediction of the solution reduces the complexity of the problem and speeds up its resolution, while yielding a good quality solution. The proposed approach resulted in solutions with an optimality gap ranging from 0% to 1.7% on different benchmark instances within a reasonable computing time.
2023-12-13
Networks (published)
doi.org
arxiv.org
Asymmetric Actor-Critic with Approximate Information State
Amit Sinha
Aditya Mahajan
Reinforcement learning (RL) for partially observable Markov decision processes (POMDPs) is a challenging problem because decisions need to b… (see more)e made based on the entire history of observations and actions. However, in several scenarios, state information is available during the training phase. We are interested in exploiting the availability of this state information during the training phase to efficiently learn a history-based policy using RL. Specifically, we consider actor-critic algorithms, where the actor uses only the history information but the critic uses both history and state. Such algorithms are called asymmetric actor-critic, to highlight the fact that the actor and critic have asymmetric information. Motivated by the recent success of using representation losses in RL for POMDPs [1], we derive similar theoretical results for the asymmetric actor-critic case and evaluate the effectiveness of adding such auxiliary losses in experiments. In particular, we learn a history representation-called an approximate information state (AIS)-and bound the performance loss when acting using AIS.
2023-12-12
IEEE Conference on Decision and Control (published)
doi.org
Current Practices in Voice Data Collection and Limitations to Voice AI Research: A National Survey.
Emily Evangelista
Rohan Kale
Desiree McCutcheon
Anais Rameau
Alexander Gelbard
Maria Powell
Michael Johns
Anthony Law
Phillip Song
Matthew Naunheim
Stephanie Watts
Paul C. Bryson
Matthew G. Crowson
Jeremy Pinto
Yael Bensoussan
INTRODUCTION Accuracy and validity of voice AI algorithms rely on substantial quality voice data. Although commensurable amounts of voice da… (see more)ta are captured daily in voice centers across North America, there is no standardized protocol for acoustic data management, which limits the usability of these datasets for voice artificial intelligence (AI) research. OBJECTIVE The aim was to capture current practices of voice data collection, storage, analysis, and perceived limitations to collaborative voice research. METHODS A 30-question online survey was developed with expert guidance from the voicecollab.ai members, an international collaborative of voice AI researchers. The survey was disseminated via REDCap to an estimated 200 practitioners at North American voice centers. Survey questions assessed respondents' current practices in terms of acoustic data collection, storage, and retrieval as well as limitations to collaborative voice research. RESULTS Seventy-two respondents completed the survey of which 81.7% were laryngologists and 18.3% were speech language pathologists (SLPs). Eighteen percent of respondents reported seeing 40%-60% and 55% reported seeing >60 patients with voice disorders weekly (conservative estimate of over 4000 patients/week). Only 28% of respondents reported utilizing standardized protocols for collection and storage of acoustic data. Although, 87% of respondents conduct voice research, only 38% of respondents report doing so on a multi-institutional level. Perceived limitations to conducting collaborative voice research include lack of standardized methodology for collection (30%) and lack of human resources to prepare and label voice data adequately (55%). CONCLUSION To conduct large-scale multi-institutional voice research with AI, there is a pertinent need for standardization of acoustic data management, as well as an infrastructure for secure and efficient data sharing. LEVEL OF EVIDENCE Level 5 Laryngoscope, 2023.
2023-12-12
The Laryngoscope (published)
doi.org
Detection and evaluation of bias-inducing features in machine learning
Moses Openja
Gabriel Laberge
Foutse Khomh
2023-12-12
Empirical Software Engineering (published)
doi.org
arxiv.org
Preserving Privacy in GANs Against Membership Inference Attack
Mohammadhadi Shateri
Francisco Messina
Fabrice Labeau
Pablo Piantanida
Generative Adversarial Networks (GANs) have been widely used for generating synthetic data for cases where there is a limited size real-worl… (see more)d dataset or when data holders are unwilling to share their data samples. Recent works showed that GANs, due to overfitting and memorization, might leak information regarding their training data samples. This makes GANs vulnerable to Membership Inference Attacks (MIAs). Several defense strategies have been proposed in the literature to mitigate this privacy issue. Unfortunately, defense strategies based on differential privacy are proven to reduce extensively the quality of the synthetic data points. On the other hand, more recent frameworks such as PrivGAN and PAR-GAN are not suitable for small-size training datasets. In the present work, the overfitting in GANs is studied in terms of the discriminator, and a more general measure of overfitting based on the Bhattacharyya coefficient is defined. Then, inspired by Fano's inequality, our first defense mechanism against MIAs is proposed. This framework, which requires only a simple modification in the loss function of GANs, is referred to as the maximum entropy GAN or MEGAN and significantly improves the robustness of GANs to MIAs. As a second defense strategy, a more heuristic model based on minimizing the information leaked from generated samples about the training data points is presented. This approach is referred to as mutual information minimization GAN (MIMGAN) and uses a variational representation of the mutual information to minimize the information that a synthetic sample might leak about the whole training data set. Applying the proposed frameworks to some commonly used data sets against state-of-the-art MIAs reveals that the proposed methods can reduce the accuracy of the adversaries to the level of random guessing accuracy with a small reduction in the quality of the synthetic data samples.
2023-12-12
IEEE Transactions on Information Forensics and Security (unknown)
doi.org
arxiv.org