Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Zhou, Andy"'
Autor:
Zeng, Yi, Klyman, Kevin, Zhou, Andy, Yang, Yu, Pan, Minzhou, Jia, Ruoxi, Song, Dawn, Liang, Percy, Li, Bo
We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative A
Externí odkaz:
http://arxiv.org/abs/2406.17864
Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated moderation
Externí odkaz:
http://arxiv.org/abs/2405.20413
Standard federated learning approaches suffer when client data distributions have sufficient heterogeneity. Recent methods addressed the client data heterogeneity issue via personalized federated learning (PFL) - a class of FL algorithms aiming to pe
Externí odkaz:
http://arxiv.org/abs/2404.02478
The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with jailbreaks prior to
Externí odkaz:
http://arxiv.org/abs/2402.03299
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have not been a
Externí odkaz:
http://arxiv.org/abs/2401.17263
We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for better teac
Externí odkaz:
http://arxiv.org/abs/2311.01441
While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- t
Externí odkaz:
http://arxiv.org/abs/2310.04406
Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain. In this paper, we propose a novel approach for domain generalization
Externí odkaz:
http://arxiv.org/abs/2309.12530
FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning
Publikováno v:
International Workshop on Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities in Conjunction with ICML 2023
Recent advancements in federated learning (FL) seek to increase client-level performance by fine-tuning client parameters on local data or personalizing architectures for the local task. Existing methods for such personalization either prune a global
Externí odkaz:
http://arxiv.org/abs/2306.13264
Electromyogram (EMG) pattern recognition can be used to classify hand gestures and movements for human-machine interface and prosthetics applications, but it often faces reliability issues resulting from limb position change. One method to address th
Externí odkaz:
http://arxiv.org/abs/2103.05267