Zobrazeno 1 - 10
of 4 557
pro vyhledávání: '"de Witt, A."'
Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC, often fail to accu
Externí odkaz:
http://arxiv.org/abs/2411.13731
Autor:
Lakara, Kumud, Sock, Juil, Rupprecht, Christian, Torr, Philip, Collomosse, John, de Witt, Christian Schroeder
One of the most challenging forms of misinformation involves the out-of-context (OOC) use of images paired with misleading text, creating false narratives. Existing AI-driven detection systems lack explainability and require expensive fine-tuning. We
Externí odkaz:
http://arxiv.org/abs/2410.20140
Autor:
da Silva, Rafael Ferreira, Bard, Deborah, Chard, Kyle, de Witt, Shaun, Foster, Ian T., Gibbs, Tom, Goble, Carole, Godoy, William, Gustafsson, Johan, Haus, Utz-Uwe, Hudson, Stephen, Jha, Shantenu, Los, Laila, Paine, Drew, Suter, Frédéric, Ward, Logan, Wilkinson, Sean, Amaris, Marcos, Babuji, Yadu, Bader, Jonathan, Balin, Riccardo, Balouek, Daniel, Beecroft, Sarah, Belhajjame, Khalid, Bhattarai, Rajat, Brewer, Wes, Brunk, Paul, Caino-Lores, Silvina, Casanova, Henri, Cassol, Daniela, Coleman, Jared, Coleman, Taina, Colonnelli, Iacopo, Da Silva, Anderson Andrei, de Oliveira, Daniel, Elahi, Pascal, Elfaramawy, Nour, Elwasif, Wael, Etz, Brian, Fahringer, Thomas, Ferreira, Wesley, Filgueira, Rosa, Tande, Jacob Fosso, Gadelha, Luiz, Gallo, Andy, Garijo, Daniel, Georgiou, Yiannis, Gritsch, Philipp, Grubel, Patricia, Gueroudji, Amal, Guilloteau, Quentin, Hamalainen, Carlo, Enriquez, Rolando Hong, Huet, Lauren, Kesling, Kevin Hunter, Iborra, Paula, Jahangiri, Shiva, Janssen, Jan, Jordan, Joe, Kanwal, Sehrish, Kunstmann, Liliane, Lehmann, Fabian, Leser, Ulf, Li, Chen, Liu, Peini, Luettgau, Jakob, Lupat, Richard, Fernandez, Jose M., Maheshwari, Ketan, Malik, Tanu, Marquez, Jack, Matsuda, Motohiko, Medic, Doriana, Mohammadi, Somayeh, Mulone, Alberto, Navarro, John-Luke, Ng, Kin Wai, Noelp, Klaus, Kinoshita, Bruno P., Prout, Ryan, Crusoe, Michael R., Ristov, Sashko, Robila, Stefan, Rosendo, Daniel, Rowell, Billy, Rybicki, Jedrzej, Sanchez, Hector, Saurabh, Nishant, Saurav, Sumit Kumar, Scogland, Tom, Senanayake, Dinindu, Shin, Woong, Sirvent, Raul, Skluzacek, Tyler, Sly-Delgado, Barry, Soiland-Reyes, Stian, Souza, Abel, Souza, Renan, Talia, Domenico, Tallent, Nathan, Thamsen, Lauritz, Titov, Mikhail, Tovar, Benjamin, Vahi, Karan, Vardar-Irrgang, Eric, Vartina, Edite, Wang, Yuandou, Wouters, Merridee, Yu, Qi, Bkhetan, Ziad Al, Zulfiqar, Mahnoor
The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogen
Externí odkaz:
http://arxiv.org/abs/2410.14943
Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to scale them up
Externí odkaz:
http://arxiv.org/abs/2410.08201
A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However, a central problem in evaluating the quality of SAEs is the absence of
Externí odkaz:
http://arxiv.org/abs/2410.07456
The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real-world settings. In this paper
Externí odkaz:
http://arxiv.org/abs/2410.07436
As a powerful and rapidly advancing dual-use technology, AI offers both immense benefits and worrisome risks. In response, governing bodies around the world are developing a range of regulatory AI laws and policies. This paper compares three distinct
Externí odkaz:
http://arxiv.org/abs/2410.21279
Autor:
Mathew, Yohan, Matthews, Ollie, McCarthy, Robert, Velja, Joan, de Witt, Christian Schroeder, Cope, Dylan, Schoots, Nandi
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been identified as a central form of u
Externí odkaz:
http://arxiv.org/abs/2410.03768
Autor:
Simelane, Senkhosi, Deane, Roger, Kemball, Athol, Botha, Roelf, Julie, Roufurd, Molamu, Keitumetse, Tiplady, Adrian, de Witt, Aletha
Global expansion of the Event Horizon Telescope (EHT) will see the strategic addition of antennas at new geographical locations, transforming the sensitivity and imaging fidelity of the $\lambda \sim 1\,$mm EHT array. A possible South African EHT sta
Externí odkaz:
http://arxiv.org/abs/2409.08003
Autor:
Zesch, Torsten, Hanses, Michael, Seidel, Niels, Aggarwal, Piush, Veiel, Dirk, de Witt, Claudia
Using the full potential of LLMs in higher education is hindered by challenges with access to LLMs. The two main access modes currently discussed are paying for a cloud-based LLM or providing a locally maintained open LLM. In this paper, we describe
Externí odkaz:
http://arxiv.org/abs/2407.13013