Searched for: +
(1 - 20 of 182)

Pages

document
Zhu, P. (author), Wang, Zhen (author), Okumura, Manabu (author), Yang, J. (author)
Textbook question answering is challenging as it aims to automatically answer various questions on textbook lessons with long text and complex diagrams, requiring reasoning across modalities. In this work, we propose MRHF, a novel framework that incorporates dense passage re-ranking and the mixture-of-experts architecture for TQA. MRHF...
conference paper 2024
document
Zhou, Yimin (author), Gillavry, Merlijn Mac (author), Yang, Pengzhi (author), Xu, Zihao (author), Zhang, Baitian (author), Bidarra, Rafael (author)
As one of the most disruptive human-computer interaction techniques, Virtual Reality (VR) provides a novel way to examine human movements, e.g. when investigating Body Ownership (BO) in the field of cognitive sciences, especially when the visual output diverges from real-world actions. Previous research in BO uses questionnaires and brain...
conference paper 2024
document
Wang, S. (author), Zong, Qihang (author), Yang, Huiru (author), Huang, Qianming (author), Ye, Huaiyu (author), French, P.J. (author)
In recent years, flexible strain sensors based on metal cracks have garnered significant interest for their exceptional sensitivity. However, striking a balance between sensitivity and detection range remains a significant challenge, which often limits its wider application. Herein, we introduce an innovative laser transmission pyrolysis...
conference paper 2024
document
Yang, Q. (author), Spaan, M.T.J. (author)
Without an assigned task, a suitable intrinsic objective for an agent is to explore the environment efficiently. However, the pursuit of exploration will inevitably bring more safety risks.<br/>An under-explored aspect of reinforcement learning is how to achieve safe efficient exploration when the task is unknown.<br/>In this paper, we propose a...
conference paper 2023
document
Sharifi Noorian, S. (author), Qiu, S. (author), Sayin, Burcu (author), Balayn, A.M.A. (author), Gadiraju, Ujwal (author), Yang, J. (author), Bozzon, A. (author)
High-quality data plays a vital role in developing reliable image classification models. Despite that, what makes an image difficult to classify remains an unstudied topic. This paper provides a first-of-its-kind, model-agnostic characterization of image atypicality based on human understanding. We consider the setting of image classification...
conference paper 2023
document
Yang, Q. (author), Simão, T. D. (author), Jansen, Nils (author), Tindemans, Simon H. (author), Spaan, M.T.J. (author)
Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once...
conference paper 2023
document
Mesbah, Sepideh (author), Arous, Ines (author), Yang, J. (author), Bozzon, A. (author)
Evaluating design ideas is necessary to predict their success and assess their impact early on in the process. Existing methods rely either on metrics computed by systems that are effective but subject to errors and bias, or experts' ratings, which are accurate but expensive and long to collect. Crowdsourcing offers a compelling way to...
conference paper 2023
document
Arango, Erica (author), Nogal Macho, M. (author), Yang, M. (author), Sousa, Hélder S. (author), Stewart, Mark G. (author), Matos, José C. (author)
Wildfires have become a source of concern for society due to the increase in frequency, intensity, and unpredictability. This has caused serious impacts all over the world, even in areas where this type of problem did not occur before. Studies on the adaptation of critical infrastructure have been conducted to reduce the...
conference paper 2023
document
Esgin, Muhammed F. (author), Ersoy, O. (author), Kuchta, Veronika (author), Loss, Julian (author), Sakzad, Amin (author), Steinfeld, Ron (author), Yang, Xiangwen (author), Zhao, Raymond K. (author)
In this work, we study the blockchain leader election problem. The purpose of such protocols is to elect a leader who decides on the next block to be appended to the blockchain, for each block proposal round. Solutions to this problem are vital for the security of blockchain systems. We introduce an efficient blockchain leader election method...
conference paper 2023
document
Sayin, Burcu (author), Yang, J. (author), Passerini, Andrea (author), Casati, Fabio (author)
In this paper, we argue that the way we have been training and evaluating ML models has largely forgotten the fact that they are applied in an organization or societal context as they provide value to people. We show that with this perspective we fundamentally change how we evaluate and select machine learning models.
conference paper 2023
document
Sayin, Burcu (author), Yang, J. (author), Passerini, Andrea (author), Casati, Fabio (author)
In many practical applications, machine learning models are embedded into a pipeline involving a human actor that decides whether to trust the machine prediction or take a default route (e.g., classify the example herself). Selective classifiers have the option to abstain from making a prediction on an example they do not feel confident about...
conference paper 2023
document
Poliotti, M. (author), Yang, Y. (author), De Boer, Ane (author)
In old Dutch inner cities like Amsterdam a large number of steel-concrete bridge decks built between 1880 and 1960 remain in service nowadays and currently need assessment of their bearing capacity. A significant number of these decks were designed without any mechanical connectors like shear studs in the interface between concrete and steel....
conference paper 2023
document
Silva Ortiz, P. (author), Van Der Bruggen, B. (author), Yang, X. (author), Jocher, A. (author), Pinto Mariano, A. (author), Posada Duque, J.A. (author)
Integrating low-carbon technologies within biorefineries, with applications targeting energyefficient separation systems, is essential to achieving net zero emissions in the coming years. To address this target, we investigated potential biorefinery pathways featuring process intensification in the bioethanol and biodiesel industries. The role...
conference paper 2023
document
Balayn, A.M.A. (author), Yurrita Semperena, M. (author), Yang, J. (author), Gadiraju, Ujwal (author)
Fairness toolkits are developed to support machine learning (ML) practitioners in using algorithmic fairness metrics and mitigation methods. Past studies have investigated practical challenges for toolkit usage, which are crucial to understanding how to support practitioners. However, the extent to which fairness toolkits impact practitioners’...
conference paper 2023
document
Balayn, A.M.A. (author), Rikalo, N. (author), Yang, J. (author), Bozzon, A. (author)
Handling failures in computer vision systems that rely on deep learning models remains a challenge. While an increasing number of methods for bug identification and correction are proposed, little is known about how practitioners actually search for failures in these models. We perform an empirical study to understand the goals and needs of...
conference paper 2023
document
Fu, Bin (author), Sun, B. (author), Guo, Hang (author), Yang, Tao (author), Fu, Wenxing (author)
The current study presents an online iterative adaptive dynamic programming approach to resolve the zero-sum game (ZSG) for nonlinear continuous-time (CT) systems containing a partially unknown dynamic. The Hamilton-Jacobian-Issacs (HJI) equation is solved along the state trajectory according to the value function approximation and the policy...
conference paper 2023
document
Lu, J. (author), Yang, Y. (author), van der Ham, H.W.M. (author), Fu, Danny (author)
Geopolymer concrete is a new alternative material to conventional concrete with less carbon dioxide emissions. Researchers have reported much research on the material properties of geopolymer concrete. However, research on the behaviour of this newmaterial at the structural level is still limited, especially at a full-scale structural level....
conference paper 2023
document
Ibrahim, M.S. (author), Poliotti, M. (author), Yang, Y. (author), Hendriks, M.A.N. (author)
Typically precast girders are designed and utilized as simple supported members. Alternatively, the precast girders can be made continuous at the intermediate support using cast-in-place concrete topping. Once the girders are made continuous, time-dependent restraint moments will occur. The magnitude of the restraint moment is mainly affected by...
conference paper 2023
document
Sierra, P.L. (author), Poliotti, M. (author), Yang, Y. (author), Martinez García, Xavier (author), Chacón, Rolando (author)
In this work, dynamic characterization of a simply supported beam is carried out during different steps in a failure load test. The main goal of this work is to evaluate the evolution of the structural dynamic parameters of the beam with different status of damage. Real-scale prestressed concrete beams are tested to investigate its shear...
conference paper 2023
document
Lammerts, Philippe (author), Lippmann, P. (author), Hsu, Yen Chia (author), Casati, Fabio (author), Yang, J. (author)
Hate speech moderation remains a challenging task for social media platforms. Human-AI collaborative systems offer the potential to combine the strengths of humans' reliability and the scalability of machine learning to tackle this issue effectively. While methods for task handover in human-AI collaboration exist that consider the costs of...
conference paper 2023
Searched for: +
(1 - 20 of 182)

Pages