Publications

Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing

Shengchao Liu

Weili Nie

Chengpeng Wang

Jiarui Lu

Zhuoran Qiao

Ling Liu

Jian Tang

Chaowei Xiao

Animashree Anandkumar

There is increasing adoption of artificial intelligence in drug discovery. However, existing studies use machine learning to mainly utilize … (see more)the chemical structures of molecules but ignore the vast textual knowledge available in chemistry. Incorporating textual knowledge enables us to realize new drug design objectives, adapt to text-based instructions and predict complex biological activities. Here we present a multi-modal molecule structure-text model, MoleculeSTM, by jointly learning molecules' chemical structures and textual descriptions via a contrastive learning strategy. To train MoleculeSTM, we construct a large multi-modal dataset, namely, PubChemSTM, with over 280,000 chemical structure-text pairs. To demonstrate the effectiveness and utility of MoleculeSTM, we design two challenging zero-shot tasks based on text instructions, including structure-text retrieval and molecule editing. MoleculeSTM has two main properties: open vocabulary and compositionality via natural language. In experiments, MoleculeSTM obtains the state-of-the-art generalization ability to novel biochemical concepts across various benchmarks.

2023-12-18

Nature Machine Intelligence (published)

doi.org

arxiv.org

Addressing Sample Inefficiency in Multi-View Representation Learning

Kumar Krishna Agrawal

Arna Ghosh

Adam M. Oberman

Blake Richards

2023-12-17

ArXiv (preprint)

doi.org

openreview.net

Pseudo-random Instance Generators in C++ for Deterministic and Stochastic Multi-commodity Network Design Problems

Eric Larsen

Serge Bisaillon

Jean-François Cordeau

Emma Frejinger

Network design problems constitute an important family of combinatorial optimization problems for which numerous exact and heuristic algorit… (see more)hms have been developed over the last few decades. Two central problems in this family are the multi-commodity, capacitated, fixed charge network design problem (MCFNDP) and its stochastic counterpart, the two-stage MCFNDP with recourse. These are standard problems that often serve as work benches for devising and testing models and algorithms in stylized but close-to-realistic settings. The purpose of this paper is to introduce two flexible, high-speed generators capable of simulating a wide range of settings for both the deterministic and stochastic MCFNDPs. We hope that, by facilitating systematic experimentation with new and larger sets of instances, these generators will lead to a more thorough assessment of the performance achieved by exact and heuristic solution methods in both deterministic and stochastic settings. We also hope that making these generators available will promote the reproducibility and comparability of published research.

2023-12-17

ArXiv (preprint)

arxiv.org

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 49 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

Jan Ebert

M. Kunakov

Fedor Zhdanov

Manuel Romero

Tony Lee

Nadav Timor

Jennifer Ding

Claire S Schlesinger

Hailey Schoelkopf

Jana Ebert

Tri Dao

Mayank Mishra

Alex Gu

Jennifer Robinson

Sean Hughes

Carolyn Jane Anderson

Brendan Dolan-Gavitt

Danish Contractor

Siva Reddy

Daniel Fried

Dzmitry Bahdanau

Yacine Jernite

Carlos Muñoz Ferrandis

Sean M. 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.

2023-12-17

TMLR (accepted)

doi.org

openreview.net

StarVector: Generating Scalable Vector Graphics Code from Images

Juan A. Rodriguez

Shubham Agarwal

Issam Hadj Laradji

Pau Rodriguez

David Vazquez

Chris Pal

Marco Pedersoli

Scalable Vector Graphics (SVGs) have become integral in modern image rendering applications due to their infinite scalability in resolution,… (see more) versatile usability, and editing capabilities. SVGs are particularly popular in the fields of web development and graphic design. Existing approaches for SVG modeling using deep learning often struggle with generating complex SVGs and are restricted to simpler ones that require extensive processing and simplification. This paper introduces StarVector, a multimodal SVG generation model that effectively integrates Code Generation Large Language Models (CodeLLMs) and vision models. Our approach utilizes a CLIP image encoder to extract visual representations from pixel-based images, which are then transformed into visual tokens via an adapter module. These visual tokens are pre-pended to the SVG token embeddings, and the sequence is modeled by the StarCoder model using next-token prediction, effectively learning to align the visual and code tokens. This enables StarVector to generate unrestricted SVGs that accurately represent pixel images. To evaluate StarVector's performance, we present SVG-Bench, a comprehensive benchmark for evaluating SVG methods across multiple datasets and relevant metrics. Within this benchmark, we introduce novel datasets including SVG-Stack, a large-scale dataset of real-world SVG examples, and use it to pre-train StarVector as a large foundation model for SVGs. Our results demonstrate significant enhancements in visual quality and complexity handling over current methods, marking a notable advancement in SVG generation technology. Code and models: https://github.com/joanrod/star-vector

2023-12-17

ArXiv (preprint)

doi.org

arxiv.org

Rescuespeech: A German Corpus for Speech Recognition in Search and Rescue Domain

Sangeet Sagar

Mirco Ravanelli

Bernd Kiefer

Ivana Kruijff-KorbayovÃ¡

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.

2023-12-16

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)

doi.org

arxiv.org

Self-supervised multimodal learning for group inferences from MRI data: Discovering disorder-relevant brain regions and multimodal links

Alex Fedorov

Eloy Geenjaar

Lei Wu

Tristan Sylvain

Thomas P. DeRamus

Margaux Luck

Maria Misiura

Girish Mittapalle

(Rex) Devon Hjelm

Sergey M. Plis

Vince D. Calhoun

2023-12-16

NeuroImage (published)

doi.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 and to unify various fine-grained methods under a single objective, 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, 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.

2023-12-16

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 Ravanelli

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.

2023-12-16

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)

doi.org

arxiv.org

FoMo-Bench: a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models

Nikolaos Ioannis Bountos

Arthur Ouaknine

David Rolnick

2023-12-15

ArXiv (preprint)

doi.org

arxiv.org