Zobrazeno 1 - 10
of 24 312
pro vyhledávání: '"P. Förster"'
It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify the authen
Externí odkaz:
http://arxiv.org/abs/2411.05197
Zero-shot coordination (ZSC) is a popular setting for studying the ability of reinforcement learning (RL) agents to coordinate with novel partners. Prior ZSC formulations assume the $\textit{problem setting}$ is common knowledge: each agent knows the
Externí odkaz:
http://arxiv.org/abs/2411.04976
Autor:
Carvajal, J. P., Bauer, F. E., Reyes-Jainaga, I., Förster, F., Arancibia, A. M. Muñoz, Catelan, M., Sánchez-Sáez, P., Ricci, C., Bayo, A.
A significant challenge in the study of transient astrophysical phenomena is the identification of bogus events, with human-made Earth-orbiting satellites and debris remain a key contaminant. Existing pipelines effectively identify satellite trails b
Externí odkaz:
http://arxiv.org/abs/2411.03258
Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the outer-loop app
Externí odkaz:
http://arxiv.org/abs/2411.00666
Autor:
Bauch, Gerrit, Foerster, Manuel
We conceptualize the communication of narratives as a cheap-talk game under model uncertainty. The sender has private information about the true data generating process of publicly observable data. The receiver is uncertain about how to interpret the
Externí odkaz:
http://arxiv.org/abs/2410.23259
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
While large models trained with self-supervised learning on offline datasets have shown remarkable capabilities in text and image domains, achieving the same generalisation for agents that act in sequential decision problems remains an open challenge
Externí odkaz:
http://arxiv.org/abs/2410.23208
Autor:
Vantaraki, Christina, Grassi, Matías P., Ignatova, Kristina, Foerster, Michael, Arnalds, Unnar B., Primetzhofer, Daniel, Kapaklis, Vassilios
We investigate the design of magnetic ordering in one-dimensional mesoscopic magnetic Ising chains by modulating long-range interactions. These interactions are affected by geometrical modifications to the chain, which adjust the energy hierarchy and
Externí odkaz:
http://arxiv.org/abs/2410.21903
We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios (each with 33
Externí odkaz:
http://arxiv.org/abs/2410.21159
Publikováno v:
2024 IEEE 7th International Conference on Soft Robotics (RoboSoft), San Diego, CA, USA, 2024, pp. 933-939
Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptio
Externí odkaz:
http://arxiv.org/abs/2410.18519
Autor:
Förster, Arno, Bruneval, Fabien
Hedin's $GW$ approximation to the electronic self-energy has been impressively successful to calculate quasiparticle energies, such as ionization potentials, electron affinities, or electronic band structures. The success of this fairly simple approx
Externí odkaz:
http://arxiv.org/abs/2410.17843