Echoes from the scattering of wavepackets on wormholes von Gálvez Ghersi, José T, Frolov, Andrei V, Dobre, David A

Volltext

Unbraiding the bounce: superluminality around the corner von Dobre, David A., Frolov, Andrei V., Ghersi, José T. Gálvez, Ramazanov, Sabir, Vikman, Alexander

Volltext

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features von Beznosikov, Aleksandr, Dobre, David, Gidel, Gauthier

Volltext bestellen

Cepheid Variables in the Andromeda Galaxy from Simon Fraser University's Trottier Observatory von Trottier, Howord, Abraham, Rohan, Aburegebo, Zina, Cheung, Tereso, Cimone, Matthew, Dally, Kyle, Dobre, David, Grover, Rohit, Kollesøe, Sarah Sovit, Kelly, Katherine, Lee, David, Mazurenko, Oleg, Morley, Christina, Robus, Anjo, Watterson, Ryne, Wright, Aidan, Arthurs, Ken, Conrad, Robert, Krysa, Andrew, Miller, J Karl, Sebulsky, Greg, Siniak, Paul

Volltext

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space von Schwinn, Leo, Dobre, David, Xhonneux, Sophie, Gidel, Gauthier, Gunnemann, Stephan

Volltext bestellen

In-Context Learning Can Re-learn Forbidden Tasks von Xhonneux, Sophie, Dobre, David, Tang, Jian, Gidel, Gauthier, Sridhar, Dhanya

Volltext bestellen

Adversarial Attacks and Defenses in Large Language Models: Old and New Threats von Schwinn, Leo, Dobre, David, Günnemann, Stephan, Gidel, Gauthier

Volltext bestellen

Raising the Bar for Certified Adversarial Robustness with Diffusion Models von Altstidl, Thomas, Dobre, David, Eskofier, Björn, Gidel, Gauthier, Schwinn, Leo

Volltext bestellen

Dissecting adaptive methods in GANs von Jelassi, Samy, Dobre, David, Mensch, Arthur, Li, Yuanzhi, Gidel, Gauthier

Volltext bestellen

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features von Beznosikov, Aleksandr, Dobre, David, Gauthier Gidel

Volltext

Learning diverse attacks on large language models for robust red-teaming and safety tuning von Lee, Seanie, Kim, Minsu, Cherif, Lynn, Dobre, David, Lee, Juho, Hwang, Sung Ju, Kawaguchi, Kenji, Gidel, Gauthier, Bengio, Yoshua, Malkin, Nikolay, Jain, Moksh

Volltext bestellen

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise von Gorbunov, Eduard, Danilova, Marina, Dobre, David, Dvurechensky, Pavel, Gasnikov, Alexander, Gidel, Gauthier

Volltext bestellen

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space von Schwinn, Leo, Dobre, David, Xhonneux, Sophie, Gauthier Gidel, Gunnemann, Stephan

Volltext

In-Context Learning Can Re-learn Forbidden Tasks von Xhonneux, Sophie, Dobre, David, Tang, Jian, Gauthier Gidel, Sridhar, Dhanya

Volltext

Adversarial Attacks and Defenses in Large Language Models: Old and New Threats von Schwinn, Leo, Dobre, David, Günnemann, Stephan, Gauthier Gidel

Volltext

Raising the Bar for Certified Adversarial Robustness with Diffusion Models von Altstidl, Thomas, Dobre, David, Eskofier, Björn, Gauthier Gidel, Schwinn, Leo

Volltext

Dissecting adaptive methods in GANs von Jelassi, Samy, Dobre, David, Mensch, Arthur, Li, Yuanzhi, Gauthier Gidel

Volltext

Echoes from the scattering of wavepackets on wormholes von Gálvez Ghersi, José T, Frolov, Andrei V, Dobre, David A

Volltext

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise von Gorbunov, Eduard, Danilova, Marina, Dobre, David, Dvurechensky, Pavel, Gasnikov, Alexander, Gauthier Gidel

Volltext

Unbraiding the Bounce: Superluminality around the Corner von Dobre, David A, Frolov, Andrei V, Gálvez Ghersi, José T, Sabir Ramazanov, Vikman, Alexander

Volltext