Tootfinder

Canonical traces of fiber products and their applications
Shinya Kumashiro, Sora Miyashita
https://arxiv.org/abs/2506.04899 https://a…

Canonical traces of fiber products and their applications
We study the canonical trace of the fiber product of Noetherian rings. Furthermore, we extend results on the class of Cohen-Macaulay rings called Teter type to Noetherian rings. As an application of our study on canonical traces and Noetherian rings of Teter type, we compute the canonical trace of the Stanley-Reisner ring arising from a non-connected simplicial complex. In particular, we provide a characterization of Stanley-Reisner rings for which the canonical trace contains the graded maxima…

Hello les gens !
Pour commencer la journée (qui est déjŠ bien avancée) rien de tel qu'une petite chanson sous-estimée d'un obscur groupe de Liverpool... Original, brillant et feel good, l'une de leurs meilleures chansons .
You Know My Name ? Look Up The Number !
https://youtu.be/9DkaRUtp3w8

Wanted to find out how many calories are in poop to make a nice fat-positive post on here, but after wading through 5 separate results from the top to the bottom of the first page of results, every single one of them showed signs of AI authorship, so none of the info was trustworthy (several contradicted each other or themselves). The one article that cited legit sources didn't include a straightforward answer to the question. Of course, I could dig past the first page, or look through the cited sources do some math myself, and that's not even that hard to do. But 10 years ago, a trustworthy answer would have been among the first 5 search results. When we say #AI is destroying the digital commons, this is what we mean.
Gonna go find some academic papers to answer this and report back.

⛓️‍💥 Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
#ai #llm

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the robustness of LMs to text encoded with non-canonical tokenizations entirely unseen during training. Surprisingly, when evaluated across 20 benchmarks, we find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly…

The neurological basis for non-visual illustration https://intellectdiscover.com/content/journals/10.1386/jill_00117_7 "this article poses the question of whether there is a theoretical precedent for creating visual imagery in the minds of blind peopl…

The c-Entropy of non-dissipative L-systems
Sergey Belyi, Konstantin A. Makarov, Eduard Tsekanovskii
https://arxiv.org/abs/2506.05144 https://

The c-Entropy of non-dissipative L-systems
In this paper, we extend the definition of c-entropy to canonical L-systems with non-dissipative state-space operators. We also introduce the concepts of dissipation and accumulation coefficients for such systems. In addition, we examine the coupling of these L-systems and derive closed form expressions for the corresponding c-entropy.

Kein Verbot vorgesehen: Creative Commons arbeitet an Lizenzen fürs KI-Training
Creative Commons will dafür sorgen, dass Verantwortliche für Datensätze signalisieren können, was sie dafür erwarten, wenn damit ein KI-Modell trainiert wird.

How the Bochum dish lost the signal from #Resilience at 19:15:33 UTC which would be 1 to 2 minutes before the nominal landing time. It never came back - while on the webcast, which just aborted, they didn't say *anything* and refer to a news briefing in a few hours. Same crisis (non-)communication as two years ago, I'm afraid ...

Interference-Aware Multiuser Hybrid Precoding for Coexistence with LEO Satellite Communication
Nima Razavi, Murat Bayraktar, Nuria Gonzalez Prelcic, Robert W. Heath Jr
https://arxiv.org/abs/2506.03438

Interference-Aware Multiuser Hybrid Precoding for Coexistence with LEO Satellite Communication
Interference from terrestrial networks can reduce the communication rate for low Earth orbit (LEO) satellites in the upper mid-band. To coexist in frequency, MIMO precoding can be used to reduce the signal that impinges on the LEO satellite. We present a beamforming algorithm designed for the hybrid architecture that incorporates a satellite interference penalty while optimizing the analog and digital precoders. Our algorithm optimizes the precoding at the base station (BS) within the set of pr…

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning
Maxime Toquebiau, Jae-Yun Jun, Fa\"iz Benamar, Nicolas Bredeche
https://arxiv.org/abs/2506.05236

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning
Communication is a fundamental aspect of coordinated behavior in multi-agent reinforcement learning. Yet, most prior works in this field have focused on emergent communication protocols developed from scratch, often resulting in inefficient or non-interpretable systems. Inspired by the role of language in natural intelligence, we investigate how grounding agents in a human-defined language can improve learning and coordination of multiple embodied agents. We propose a framework in which agents …