Publications

Assessing the Security of GitHub Copilot Generated Code - A Targeted Replication Study
Vahid Majdinasab
Michael Joshua Bishop
Shawn Rasheed
Arghavan Moradi Dakhel
Amjed Tahir
Foutse Khomh
2024-03-11
2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) (publié)
doi.org
arxiv.org
Deep Learning Model Reuse in the HuggingFace Community: Challenges, Benefit and Trends
Mina Taraghi
Gianolli Dorcelus
Armstrong Foundjem
Florian Tambon
Foutse Khomh
The ubiquity of large-scale Pre-Trained Models (PTMs) is on the rise, sparking interest in model hubs, and dedicated platforms for hosting P… (voir plus)TMs. Despite this trend, a comprehensive exploration of the challenges that users encounter and how the community leverages PTMs remains lacking. To address this gap, we conducted an extensive mixed-methods empirical study by focusing on discussion forums and the model hub of HuggingFace, the largest public model hub. Based on our qualitative analysis, we present a taxonomy of the challenges and benefits associated with PTM reuse within this community. We then conduct a quantitative study to track model-type trends and model documentation evolution over time. Our findings highlight prevalent challenges such as limited guidance for beginner users, struggles with model output comprehensibility in training or inference, and a lack of model understanding. We also identified interesting trends among models where some models maintain high upload rates despite a decline in topics related to them. Additionally, we found that despite the introduction of model documentation tools, its quantity has not increased over time, leading to difficulties in model comprehension and selection among users. Our study sheds light on new challenges in reusing PTMs that were not reported before and we provide recommendations for various stakeholders involved in PTM reuse.
2024-03-11
2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) (publié)
doi.org
arxiv.org
Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection
Xingfang Wu
Heng Li
Nobukazu Yoshioka
Hironori Washizaki
Foutse Khomh
2024-03-11
2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) (publié)
doi.org
arxiv.org
Rethinking Machine Learning Benchmarks in the Context of Professional Codes of Conduct
Peter Henderson
Jieru Hu
Mona Diab
Joelle Pineau
2024-03-11
Proceedings of the Symposium on Computer Science and Law (publié)
doi.org
Continuous iron spreading on carbon-shell composite nanotubes for electromagnetic wave absorption
Yuanyuan Zhang
Yining Li
Can Zhang
Zhenjie Guan
Liang Zhen
Jian-Tang Jiang
2024-03-10
Communications Materials (publié)
doi.org
Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport
Alexander Tong
Nikolay Malkin
Guillaume Huguet
Yanlei Zhang
Jarrid Rector-Brooks
Kilian Fatras
Guy Wolf
Yoshua Bengio
Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (voir plus)mulation-based maximum likelihood training. We introduce the generalized \textit{conditional flow matching} (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, OT-CFM is the first method to compute dynamic OT in a simulation-free way. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schrödinger bridge inference.
2024-03-10
TMLR (accepté)
openreview.net
openreview.net
IntentGPT: Few-shot Intent Discovery with Large Language Models
Juan A. Rodriguez
Nicholas Botzer
David Vázquez
Christopher Pal
Marco Pedersoli
Issam Hadj Laradji
2024-03-10
ICLR.cc/2024/Workshop/LLMAgents (poster)
doi.org
openreview.net
Investigating Robot Influence on Human Behaviour By Leveraging Entrainment Effects
Lixiao Zhu
AJung Moon
2024-03-10
Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction (publié)
doi.org
Long-term survival and functional outcomes of critically ill patients with hematologic malignancies: a Canadian multicenter prospective study
Laveena Munshi
Guillaume Dumas
Bram Rochwerg
Farah Shoukat
Michael Detsky
Dean A. Fergusson
Bruno Ferreyro
Paul Heffernan
Margaret Herridge
Sheldon Magder
Mark Minden
Rakesh Patel
Salman Qureshi
Aaron Schimmer
Santhosh Thyagu
Han Ting Wang
Sangeeta Mehta
2024-03-10
Intensive Care Medicine (publié)
doi.org
Perspectives on Robotic Systems for the Visually Impaired.
Christopher Yee Wong
Rahatul Amin Ananto
Tanaka Akiyama
Joseph Paul Nemargut
AJung Moon
Many roboticists hope to build robots and develop technologies that would one day help vulnerable populations to improve their quality of li… (voir plus)fe. As there are over 2.2 billion people with visual impairments in the world, this vulnerable population is a prime target for robotic assistants to help. In a discussion with a Certified Orientation and Mobility Specialist, someone who helps individuals with visual impairments navigate and perform daily tasks effectively, some interesting and counterintuitive questions were raised about technological developments, particularly robots. While these devices were meant to help the BVI population, many are, in reality, not practically beneficial. In this article, we highlight certain misconceptions about the BVI population and their needs. We emphasize the mismatch between robotics research and the needs of the individuals with visual impairments, especially from the lens of HRI researchers.
2024-03-10
Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction (publié)
doi.org
Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science
Xiangru Tang
Qiao Jin
Kunlun Zhu
Tongxin Yuan
Yichi Zhang
Wangchunshu Zhou
Meng Qu
Yilun Zhao
Jian Tang
Zhuosheng Zhang
Arman Cohan
Zhiyong Lu
Mark Gerstein
2024-03-10
ICLR.cc/2024/Workshop/LLMAgents (poster)
openreview.net
openreview.net
Generative Models for Decision Making
Bogdan Mazoure
Lisa Lee
Roberta Raileanu
Yilun Du
Walter Talbott
Katherine Metcalf
R Devon Hjelm
Alexander T Toshev
Generative Artificial Intelligence (AI) has made significant advancements in recent years, particularly with the development of large langua… (voir plus)ge and diffusion models. These generative models have demonstrated impressive capabilities in various tasks, such as text generation and image and audio synthesis. Concurrently, Reinforcement Learning (RL) has made significant strides in solving complex sequential decision-making problems with the help of external knowledge sources . However, there remains untapped potential in combining generative models with RL algorithms to tackle real-world challenges, particularly to improve sample efficiency of tabula rasa training by introducing priors from related domains such as visual question-answering, image captioning and image generation. This workshop aims to bring together researchers and practitioners from the fields of generative AI and reinforcement learning to explore the latest advances, methodologies, and applications. By fostering collaborations between these two domains, we intend to unlock new opportunities for addressing complex problems that lie at the intersection of both fields.
2024-03-07
ICLR.cc/2024/Workshop_Proposals (publié)
openreview.net
openreview.net