Prépublication
· 2026 arXiv
EN
Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop....
Aakash Sarkar, Ananya Mukherjee et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replacements of a queried event. Both use the...
Yunuo Wang, Maoyuan Chen et al.
#cs.SD
Prépublication
· 2026 arXiv
EN
We investigate single-field inflation models that can produce large curvature perturbations at sub-Mpc scales while remaining consistent with cosmological observations across multiple regimes. We highlight the tension between generating enhanced small-scale pe...
Qing-Yang Wang, Jing-Zhi Zhou et al.
#astro-ph.CO
Prépublication
· 2026 arXiv
EN
Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the stored labels were written by the system itself. We present Foyer, a self-hosted...
Federico Lucca
#cs.CL
Prépublication
· 2026 arXiv
EN
The theory of Inflation, supplemented by fluctuations of the quantum vacuum, is the leading paradigm to explain the correlations of inhomogeneities at very large distances in the Universe. Particle physics methods fail when strong non-linearity and non-perturb...
Yoann L. Launay
#gr-qc
Prépublication
· 2026 arXiv
EN
Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline, cost-conditional readiness assessment: select a routing policy on calibration data under explicit costs, then evaluate that frozen...
Sachin Gupta
#cs.LG
Prépublication
· 2026 arXiv
EN
Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into hidden states, while...
Ali Najar, Hosein Hasani et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Multilingual pipelines such as FineWeb2 apply one recipe across a thousand languages, leaving the failure modes of individual languages unanticipated. We use an LLM once, as a corpus debugger rather than a classifier: a tool-using agent explores the corpus thr...
Marek Šuppa, Ivan Vykopal et al.
#cs.CL
Document numérisé
· 1735 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1735. Thème : chimie. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Chimie
Document numérisé
· 1735 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1735. Thème : chimie. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Chimie
Prépublication
· 2026 arXiv
EN
The Pandora spacecraft is a smallsat selected in NASA's inaugural class of Pioneers missions. The aim of the Pandora mission is to disentangle stellar activity signals from exoplanet atmospheric transmission spectroscopy measurements. Pandora accomplishes this...
Emily A. Gilbert, Elisa V. Quintana et al.
#astro-ph.IM
Prépublication
· 2026 arXiv
EN
Gravitational waves provide one of the most powerful observational probes for discriminating among inflationary models. In particular, it has recently become clear that the high-frequency gravitational-wave spectrum encodes a wealth of information about the pr...
Naoya Kitajima, Kamil Mudrunka et al.
#hep-ph