Zobrazeno 1 - 10
of 3 553
pro vyhledávání: '"Rieser, A."'
Autor:
Rastogi, Charvi, Teh, Tian Huey, Mishra, Pushkar, Patel, Roma, Ashwood, Zoe, Davani, Aida Mostafazadeh, Diaz, Mark, Paganini, Michela, Parrish, Alicia, Wang, Ding, Prabhakaran, Vinodkumar, Aroyo, Lora, Rieser, Verena
AI systems crucially rely on human ratings, but these ratings are often aggregated, obscuring the inherent diversity of perspectives in real-world phenomenon. This is particularly concerning when evaluating the safety of generative AI, where percepti
Externí odkaz:
http://arxiv.org/abs/2410.17032
Autor:
Dago, Salambô, Rieser, Jakob, Ciampini, Mario A., Mlynář, Vojtech, Kugi, Andreas, Aspelmeyer, Markus, Deutshmann-Olek, Andreas, Kiesel, Nikolai
We demonstrate the stable trapping of a levitated nanoparticle on top of an inverted potential using a combination of optical readout and electrostatic control. The feedback levitation on an inverted potential (FLIP) method stabilizes the particle at
Externí odkaz:
http://arxiv.org/abs/2410.17253
Autor:
Collins, Katherine M., Kim, Najoung, Bitton, Yonatan, Rieser, Verena, Omidshafiei, Shayegan, Hu, Yushi, Chen, Sherol, Dutta, Senjuti, Chang, Minsuk, Lee, Kimin, Liang, Youwei, Evans, Georgina, Singla, Sahil, Li, Gang, Weller, Adrian, He, Junfeng, Ramachandran, Deepak, Dvijotham, Krishnamurthy Dj
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This paper investi
Externí odkaz:
http://arxiv.org/abs/2406.16807
Autor:
Weidinger, Laura, Mellor, John, Pegueroles, Bernat Guillen, Marchal, Nahema, Kumar, Ravin, Lum, Kristian, Akbulut, Canfer, Diaz, Mark, Bergman, Stevie, Rodriguez, Mikel, Rieser, Verena, Isaac, William
This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised instructions for
Externí odkaz:
http://arxiv.org/abs/2406.11757
Autor:
Gabriel, Iason, Manzini, Arianna, Keeling, Geoff, Hendricks, Lisa Anne, Rieser, Verena, Iqbal, Hasan, Tomašev, Nenad, Ktena, Ira, Kenton, Zachary, Rodriguez, Mikel, El-Sayed, Seliem, Brown, Sasha, Akbulut, Canfer, Trask, Andrew, Hughes, Edward, Bergman, A. Stevie, Shelby, Renee, Marchal, Nahema, Griffin, Conor, Mateos-Garcia, Juan, Weidinger, Laura, Street, Winnie, Lange, Benjamin, Ingerman, Alex, Lentz, Alison, Enger, Reed, Barakat, Andrew, Krakovna, Victoria, Siy, John Oliver, Kurth-Nelson, Zeb, McCroskery, Amanda, Bolina, Vijay, Law, Harry, Shanahan, Murray, Alberts, Lize, Balle, Borja, de Haas, Sarah, Ibitoye, Yetunde, Dafoe, Allan, Goldberg, Beth, Krier, Sébastien, Reese, Alexander, Witherspoon, Sims, Hawkins, Will, Rauh, Maribeth, Wallace, Don, Franklin, Matija, Goldstein, Josh A., Lehman, Joel, Klenk, Michael, Vallor, Shannon, Biles, Courtney, Morris, Meredith Ringel, King, Helen, Arcas, Blaise Agüera y, Isaac, William, Manyika, James
This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute sequences of act
Externí odkaz:
http://arxiv.org/abs/2404.16244
Autor:
Casadio, Marco, Dinkar, Tanvi, Komendantskaya, Ekaterina, Arnaboldi, Luca, Daggitt, Matthew L., Isac, Omri, Katz, Guy, Rieser, Verena, Lemon, Oliver
Deep neural networks have exhibited substantial success in the field of Natural Language Processing and ensuring their safety and reliability is crucial: there are safety critical contexts where such models must be robust to variability or attack, an
Externí odkaz:
http://arxiv.org/abs/2403.10144
Autor:
Lindner, Stefan, Juschitz, Paul, Rieser, Jakob, Fein, Yaakov Y., Ciampini, Mario, Aspelmeyer, Markus, Kiesel, Nikolai
Many experiments in the field of optical levitation with nanoparticles today are limited by the available technologies for particle loading. Here we introduce a new particle loading method that solves the main challenges, namely deterministic positio
Externí odkaz:
http://arxiv.org/abs/2311.13920
Autor:
Pantazopoulos, Georgios, Nikandrou, Malvina, Parekh, Amit, Hemanthage, Bhathiya, Eshghi, Arash, Konstas, Ioannis, Rieser, Verena, Lemon, Oliver, Suglia, Alessandro
Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation. To tackle these challen
Externí odkaz:
http://arxiv.org/abs/2311.04067
Autor:
Weidinger, Laura, Rauh, Maribeth, Marchal, Nahema, Manzini, Arianna, Hendricks, Lisa Anne, Mateos-Garcia, Juan, Bergman, Stevie, Kay, Jackie, Griffin, Conor, Bariach, Ben, Gabriel, Iason, Rieser, Verena, Isaac, William
Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a three-layered framew
Externí odkaz:
http://arxiv.org/abs/2310.11986
Autor:
Wilson, Bruce W., Schlosser, Yann, Tarkany, Rayane, Moujahid, Meriam, Nesset, Birthe, Dinkar, Tanvi, Rieser, Verena
When giving directions to a lost-looking tourist, would you first reference the street-names, cardinal directions, landmarks, or simply tell them to walk five hundred metres in one direction then turn left? Depending on the circumstances, one could r
Externí odkaz:
http://arxiv.org/abs/2309.14499