Zobrazeno 1 - 10
of 1 681
pro vyhledávání: '"Baumler A"'
Autor:
Baumler, Connor, Daumé III, Hal
AI-based systems such as language models can replicate and amplify social biases reflected in their training data. Among other questionable behavior, this can lead to LM-generated text--and text suggestions--that contain normatively inappropriate ste
Externí odkaz:
http://arxiv.org/abs/2409.20390
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protecte
Externí odkaz:
http://arxiv.org/abs/2310.08617
Autor:
Goyal, Navita, Briakou, Eleftheria, Liu, Amanda, Baumler, Connor, Bonial, Claire, Micher, Jeffrey, Voss, Clare R., Carpuat, Marine, Daumé III, Hal
NLP systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models' knowledge or reasoning to only the retrieved
Externí odkaz:
http://arxiv.org/abs/2305.14331
Publikováno v:
Journal of International Maritime Safety, Environmental Affairs, and Shipping, Vol 8, Iss 4 (2024)
The retreating ice coverage and reduced (ice) thickness scientifically recorded in the wider Arctic region, during the last few decades, are transforming it into a more accessible operating environment. Vessels engaged in maritime transport activitie
Externí odkaz:
https://doaj.org/article/acd6538a1f5349a1b090d2da9f26cb0a
Autor:
Belinda Hernandez, Ross Shegog, Christine Markham, Susan Emery, Elizabeth Baumler, Laura Thormaehlen, Rejane Andina Teixeira, Yanneth Rivera, Olive Pertuit, Chelsey Kanipe, Iraina Witherspoon, Janis Doss, Victor Jones, Melissa Peskin
Publikováno v:
JMIR Formative Research, Vol 8, p e64412 (2024)
BackgroundSexual harassment (SH) and sexual assault (SA) are serious public health problems among US service members. Few SH and SA prevention interventions have been developed exclusively for the military. Code of Respect (X-CoRe) is an innovative w
Externí odkaz:
https://doaj.org/article/96ca1485604042ca80fb21ea411465d1
Autor:
Katelyn J. Baumler, Raymond E. Schaak
Publikováno v:
ACS Nanoscience Au, Vol 4, Iss 5, Pp 290-316 (2024)
Externí odkaz:
https://doaj.org/article/f408087130e343bcbf8dbf2a5794fe89
Publikováno v:
In Ocean Engineering 15 October 2024 310 Part 1
Publikováno v:
IEEE Access, Vol 12, Pp 52030-52050 (2024)
This survey aims to provide an overview of various methods for generating data-driven test scenarios for assessing automated driving systems (ADSs). The survey updates the overall process of scenario generation and categorizes the current methods usi
Externí odkaz:
https://doaj.org/article/b204a1815a2a483dbcf1a1a2196fbb7c
Autor:
Maximilian Baumler, Gunther Prokop
Publikováno v:
IEEE Access, Vol 12, Pp 28950-28971 (2024)
Automated driving systems should be able to avoid road traffic accidents and drive more safely than human drivers do. Test scenarios derived from real-world data such as police accident data can help assess the safety performance of automated driving
Externí odkaz:
https://doaj.org/article/81503a0270f44643af9b37e7c408030c
Autor:
Maximilian Baumler, Gunther Prokop
Publikováno v:
IEEE Access, Vol 12, Pp 16354-16374 (2024)
Scenario-based testing will help to validate automated driving systems (ADS) and establish safer road traffic. To date, most data-driven test scenario generation methods rely primarily on one data source such as police accident data (PD), naturalisti
Externí odkaz:
https://doaj.org/article/d0d9605b75324bcfac917d8bbe7ac4fd