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.
2022-12-31
Trans. Mach. Learn. Res. (published)
doi.org
openreview.net
Stochastic Generative Flow Networks
Ling Pan
Dinghuai Zhang
Moksh Jain
Longbo Huang
Yoshua Bengio
2022-12-31
Conference on Uncertainty in Artificial Intelligence (published)
doi.org
proceedings.mlr.press
Structure-aware Protein Self-supervised Learning
Can (Sam) Chen
Jingbo Zhou
Fan Wang
Xue Liu
Dejing Dou
Protein representation learning methods have shown great potential to yield useful representation for many downstream tasks, especially on p… (see more)rotein classification. Moreover, a few recent studies have shown great promise in addressing insufficient labels of proteins with self-supervised learning methods. However, existing protein language models are usually pretrained on protein sequences without considering the important protein structural information. To this end, we propose a novel structure-aware protein self-supervised learning method to effectively capture structural information of proteins. In particular, a well-designed graph neural network (GNN) model is pretrained to preserve the protein structural information with self-supervised tasks from a pairwise residue distance perspective and a dihedral angle perspective, respectively. Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning. Specifically, we identify the relation between the sequential information in the protein language model and the structural information in the specially designed GNN model via a novel pseudo bi-level optimization scheme. Experiments on several supervised downstream tasks verify the effectiveness of our proposed method.The code of the proposed method is available in https://github.com/GGchen1997/STEPS_Bioinformatics.
2022-12-31
Bioinformatics (published)
doi.org
arxiv.org
SUMMIT: Scaffolding OSS Issue Discussion Through Summarization
Saskia Gilmer
Avinash Bhat
Shuvam Shah
Kevin Cherry
Jinghui Cheng
Jin L.C. Guo
2022-12-31
arXiv.org (preprint)
doi.org
SUNMASK: Mask Enhanced Control in Step Unrolled Denoising Autoencoders
Kyle Kastner
Tim Cooijmans
Yusong Wu
Aaron Courville
2022-12-31
EvoMUSART@EvoStar (published)
doi.org
openreview.net
Supplementary Material for MixupE
Yingtian Zou
Vikas Verma
Sarthak Mittal
Wai Hoh Tang
Hieu Pham
Juho Kannala
Yoshua Bengio
Arno Solin
Kenji Kawaguchi
We denote by z = (x,y) the input and output pair where x ∈ X ⊆ R and y ∈ Y ⊆ R . Let fθ(x) ∈ R be the output of the logits (i.e.,… (see more) the last layer before the softmax or sigmoid) of the model parameterized by θ. We use l(θ, z) = h(fθ(x)) − yfθ(x) to denote the loss function. Let g(·) be the activation function. We use x(i) to index i-th element of the vector x and xj to represent j-th variable in a set. The notation list is:
2022-12-31
(published)
www.semanticscholar.org
A Survey of Diversification Metrics and Approaches in Retrieval Systems: From the Perspective of Search and Recommendation
Haolun Wu
Yansen Zhang
Chen Ma
Fuyuan Lyu
Fernando Diaz
Xue Liu
Diversifying search results is an important research topic in retrieval systems in order to satisfy both the various interests of customers … (see more)and the equal market exposure of providers. There has been a growing attention on diversity-aware research during recent years, accompanied by a proliferation of literature on methods to promote diversity in search and recommendation. However, the diversity-aware studies in retrieval systems lack a systematic organization and are rather fragmented. In this survey, we are the first to propose a unified taxonomy for classifying the metrics and approaches of diversification in both search and recommendation, which are two of the most extensively researched fields of retrieval systems. We begin the survey with a brief discussion of why diversity is important in retrieval systems
2022-12-31
(published)
www.semanticscholar.org
Survey of Scientific Rigor Studied in Machine Learning
D. Sculley
Gary R. Holt
Daniel R. Golovin
Eugene V. Davydov
Todd Phillips
Dietmar Ebner
Michael Young
Jean-francois Crespo
Dan Dennison
Emily Fox
Hugo Larochelle
The concern that Artificial Intelligence (AI) and Machine Learning (ML) are entering a “reproducibility crisis” has spurred significant … (see more)research in the past few years. Yet with each paper, it is often unclear what someone means by “reproducibility” and where it fits in the larger scope of what we will call the “scientific rigor” literature. Ultimately, the lack of clear rigor standards can affect the manner in which businesses seeking to adopt AI/ML implement such capabilities. In this survey, we will use 66 papers published since 2017 to construct a proposed set of 8 high-level categories of scientific rigor, what they are, and the history of work conducted in each. Our proposal is that these eight rigor types are not mutually exclusive and present a model for how they influence each other. To encourage more to study these questions, we map these rigors to the adoption process in real-world business use cases. In doing so, we can quantify gaps in the literature that suggest an under focus on the issues necessary for scientific rigor research to transition to practice
2022-12-31
(published)
www.semanticscholar.org
Syntactic Substitutability as Unsupervised Dependency Syntax
Jasper Jian
Siva Reddy
Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore th… (see more)e hypothesis that syntactic dependencies can be represented in language model attention distributions and propose a new method to induce these structures theory-agnostically. Instead of modeling syntactic relations as defined by annotation schemata, we model a more general property implicit in the definition of dependency relations, syntactic substitutability. This property captures the fact that words at either end of a dependency can be substituted with words from the same category. Substitutions can be used to generate a set of syntactically invariant sentences whose representations are then used for parsing. We show that increasing the number of substitutions used improves parsing accuracy on natural data. On long-distance subject-verb agreement constructions, our method achieves 79.5% recall compared to 8.9% using a previous method. Our method also provides improvements when transferred to a different parsing setup, demonstrating that it generalizes.
2022-12-31
EMNLP (published)
doi.org
openreview.net
Technology-enhanced trauma training in low-resource settings: A scoping review and feasibility analysis of educational technologies.
Minahil Khan
Fabio Botelho
Laura Pinkham
Elena Guadagno
Dan Poenaru
2022-12-31
Journal of Pediatric Surgery (published)
doi.org
Temporal Abstraction in Reinforcement Learning with the Successor Representation
Marlos C. Machado
Andre Barreto
Doina Precup
Michael Bowling
2022-12-31
J. Mach. Learn. Res. (published)
arxiv.org
arxiv.org
Test-time Defense against Adversarial Attacks: Detection and Reconstruction of Adversarial Examples via Masked Autoencoder
Yun-Yun Tsai
Ju-Chin Chao
Albert Wen
Zhaoyuan Yang
Chengzhi Mao
Tapan Shah
Junfeng Yang
Existing defense methods against adversarial attacks can be categorized into training time and test time defenses. Training time defense, i.… (see more)e., adversarial training, requires a significant amount of extra time for training and is often not able to be generalized to unseen attacks. On the other hand, test time defense by test time weight adaptation requires access to perform gradient descent on (part of) the model weights, which could be infeasible for models with frozen weights. To address these challenges, we propose DRAM, a novel defense method to Detect and Reconstruct the multiple types of Adversarial attacks via Masked autoencoder (MAE). We demonstrate how to use MAE losses to build a KS-test to detect adversarial attacks. Moreover, the MAE losses can be used to repair adversarial samples from unseen attack types. In this sense, DRAM neither requires model weight updates in test time nor augments the training set with more adversarial samples. Evaluating DRAM on the large-scale ImageNet data, we achieve the best detection rate of 82% on average on eight types of adversarial attacks compared with other detection baselines. For reconstruction, DRAM improves the robust accuracy by 6% ∼ 41% for Standard ResNet50 and 3% ∼ 8% for Robust ResNet50 compared with other self-supervision tasks, such as rotation prediction and contrastive learning.
2022-12-31
(published)
www.semanticscholar.org