Large language models are billed by the token, and tokens are not distributed evenly across languages. We measure how many tokens ten widely deployed tokenizers require to encode identical content in Kazakh and English, using 900 sentence-aligned pairs from OPUS-100 with bootstrap confidence intervals over 10,000 resam...
Alikhan Akim, Zhibek Sarsen· Zenodo (CERN European Organi...· 0 citations
BACKGROUND Small Language Models (SLMs) running on local hardware can reduce the privacy, latency, and cost concerns associated with cloud-based Large Language Models (LLMs) in healthcare, but deciding when to use them is typically informal and unsystematic in current practice. The problem is compounded by model turnov...
Large language models are billed by the token, and tokens are not distributed evenly across languages. We measure how many tokens ten widely deployed tokenizers require to encode identical content in Kazakh and English, using 900 sentence-aligned pairs from OPUS-100 with bootstrap confidence intervals over 10,000 resam...
Alikhan Akim, Zhibek Sarsen· Zenodo (CERN European Organi...· 0 citations
RealAIGC: Towards More Realistic Evaluation of AI-Generated Code Detection in Real-World Code Repository Artifact Update (Camera Ready) In response to the latest feedback, we have substantially enhanced our replication materials in terms of dataset coverage, usability, and methodological transparency. RealAIGC++ Datase...
Chen Wentao, Chen Yufei· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
How many words can you write before a language model can infer who you are? This work went looking for that number and found that the question is malformed, which is itself the finding. 72 authors from the Blog Authorship Corpus, balanced across three age bands and both genders, were shown to local language models in g...
Zaid Ali Syed· Zenodo (CERN European Organi...· 0 citations
Deception probes on language models answer a binary question: is this response deceptive? Charts allow a graded one, because a chart rendered from its own distortion parameters has an exact Tufte Lie Factor. We render 1,685 charts from real statistical series under parameterised distortions and train linear probes on t...
Carson CONCEPTION Rodrigues· Zenodo (CERN European Organi...· 0 citations
Dreaming and large language model hallucination are usually studied apart, one as biology and the other as engineering. We argue they are two expressions of a single computation: generative reconstruction from distributed memory under incomplete constraints. Neither the sleeping brain nor an autoregressive model retrie...
RealAIGC: Towards More Realistic Evaluation of AI-Generated Code Detection in Real-World Code Repository Artifact Update (Camera Ready) In response to the latest feedback, we have substantially enhanced our replication materials in terms of dataset coverage, usability, and methodological transparency. RealAIGC++ Datase...
Chen Wentao, Chen Yufei· Zenodo (CERN European Organi...· 0 citations
Abstract Large Language Models (LLMs) play a critical role in how humans access information. While their core functionality relies on the ability to comprehend written requests, our understanding of this ability is currently constrained, because most benchmarks evaluate LLMs in high-resource languages that are predomin...
Natalia Moskvina, Raquel Montero, Masaya Yoshida et al.· Scientific Reports· 0 citations
Short takeaway: Mnemorphics is a mega‑document—a merged research codex—combining acoustic metamaterials, shockwave diodes, energy‑harvesting physics, AI cognitive‑warfare systems, particle‑capture engineering, and large‑scale defensive architecture. It reads like a fusion of hard engineering, corrected physical models,...
francis lee· Zenodo (CERN European Organi...· 0 citations
This study develops a comparative benchmark for software effort estimation using the benchmark suite implemented in Python and the result package generated by that suite. Eleven regressors were compared under a leakage-safe protocol on a COCOMO-like dataset of 62 projects and 20 numeric predictors, with 49 projects res...
Jaime Aguilar-Ortiz, Víctor M. Zamudio-García, Marcos Yamir Gómez-Ramos et al.· International Journal of Com...· 0 citations
The mapped literature suggests that future policies should promote transparent, auditable, and participatory AI governance, support multilingual and culturally inclusive datasets, and integrate content moderation into broader digital public health and anti-discrimination strategies.
David Ruiz-Muñoz, A. M. Sánchez-Sánchez, Francisca J. Sánchez-Sánchez· Sexuality Research & Social...· 0 citations
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
