Tootfinder

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Wissam Salhab, Darine Ameyed, Hamid Mcheick, Fehmi Jaafar
https://arxiv.org/abs/2510.12713

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robu…

China's elite universities are preparing to launch a new undergraduate major in
"embodied intelligence,"
an emerging field that combines AI with robotics.
Seven universities
— including Shanghai Jiao Tong University, Zhejiang University, Beijing Institute of Technology, and Xi'an Jiaotong University
— have applied to offer the new major, according to a public notice published in November by China's Ministry of Education.
These schools…

China's top universities plan to roll out 'embodied intelligence' majors to fuel Beijing's robotics push
Seven Chinese universities plan to launch an "embodied intelligence" major as Beijing races to build a pipeline of robotics and AI talent.

Techniques of Artificial Intelligence Applied to Near-Infrared Spectra
Aminata Sow, Tidiane Diallo
https://arxiv.org/abs/2510.10638 https://arxiv.org/pdf/2…

Techniques of Artificial Intelligence Applied to Near-Infrared Spectra
This article explores the application of various artificial intelligence techniques to the analysis of near-infrared (NIR) spectra of paracetamol, within the spectral range of 900 nm to 1800 nm. The main objective is to evaluate the performance of several dimensionality reduction algorithms; namely, Principal Component Analysis (PCA), Kernel PCA (KPCA), Sparse Kernel PCA, t-Distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP) in modeling an…

Performance Intelligence
Learn valuable lessons that can be applied to optimising performance in your personal and professional life...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/strivestronger/

To my mind the following article suggests that the present day "AI" approach is very wrong.
Why? Because biological RI (Real Intelligence) out performs CI (Computer Intelligence) by orders of magnitude on many dimensions: power required (perhaps 20 to 50 watts for the human brain), weight, size, cooling, and ability to innovate in new ways.
Our present digital computer approach to intelligence seems about as apt as trying to power passenger airplanes using onboard coal…

OpenAI Signs $38 Billion Cloud Computing Deal With Amazon
After signing agreements to use computing power from Nvidia, AMD and Oracle, OpenAI is partnering with the world’s largest cloud computing company.

DIPSY: A new Disc Instability Population SYnthesis, II. The Populations of Companions Formed Through Disc Instability
O. Schib, C. Mordasini, A. Emsenhuber, R. Helled
https://arxiv.org/abs/2510.02437

DIPSY: A new Disc Instability Population SYnthesis, II. The Populations of Companions Formed Through Disc Instability
We applied the global end-to-end model described in Paper~I of this series to perform a population synthesis of companions formed via disc instability (DI). By using initial conditions compatible with both observations and hydrodynamical simulations, and by studying a large range of primary masses (0.05-5 Msol), we can provide quantitative predictions of the outcome of DI. In the baseline population, we find that ~10 % of the discs fragment, and about half of these end up with a surviving com…

Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Hailay Kidu Teklehaymanot, Wolfgang Nejdl
https://arxiv.org/abs/2510.12389

Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Tokenization disparities pose a significant barrier to achieving equitable access to artificial intelligence across linguistically diverse populations. This study conducts a large-scale cross-linguistic evaluation of tokenization efficiency in over 200 languages to systematically quantify computational inequities in large language models (LLMs). Using a standardized experimental framework, we applied consistent preprocessing and normalization protocols, followed by uniform tokenization through …

Another post on #Quansight PBC blog: "BLAS/LAPACK #packaging"
#BLAS and #LAPACK are the standard libraries for linear algebra. The original implementation, often called Netlib LAPACK, developed since the 1980s, nowadays serves primarily as the origin of the standard interface, the reference implementation and a conformance test suite. The end users usually use optimized implementations of the same interfaces. The choice ranges from generically tuned libraries such as OpenBLAS and BLIS, through libraries focused on specific hardware such as Intel® oneMKL, Arm Performance Libraries or the Accelerate framework on macOS, to ATLAS that aims to automatically optimize for a specific system.
The diversity of available libraries, developed in parallel with the standard interfaces, along with vendor-specific extensions and further downstream changes, adds quite a bit of complexity around using these libraries in software, and distributing such software afterwards. This problem entangles implementation authors, consumer software authors, build system maintainers and distribution maintainers. Software authors generally wish to distribute their packages built against a generically optimized BLAS/LAPACK implementation. Advanced users often wish to be able to use a different implementation, more suited to their particular needs. Distributions wish to be able to consistently build software against their system libraries, and ideally provide users the ability to switch between different implementations. Then, build systems need to provide the scaffolding for all of that.
I have recently taken up the work to provide such a scaffolding for the Meson build system; to add support for BLAS and LAPACK dependencies to Meson. While working on it, I had to learn a lot about BLAS/LAPACK packaging: not only how the different implementations differ from one another, but also what is changed by their respective downstream packaging. In this blog post, I would like to organize and share what I have learned.
"""
#CondaForge #Debian #Fedora #Gentoo

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Xiaoshuang Ji, Zhendong Zhao, Xiaoyan Gu, Xiaojun Chen, Xin Zhao, Zeyao Liu
https://arxiv.org/abs/2510.08034

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream tasks. Among numerous PEFT strategies, Low-Rank Adaptation (LoRA) has emerged as one of the most widely adopted approaches due to its robust empirical performance and low implementation complexity. In practical deployment, LoRA is typically applied to the $W^Q$ and $W^V$ projection matrices of self-attention modules, en…

A Study of Rule Omission in Raven's Progressive Matrices
Binze Li
https://arxiv.org/abs/2510.03127 https://arxiv.org/pdf/2510.03127

A Study of Rule Omission in Raven's Progressive Matrices
Analogical reasoning lies at the core of human cognition and remains a fundamental challenge for artificial intelligence. Raven's Progressive Matrices (RPM) serve as a widely used benchmark to assess abstract reasoning by requiring the inference of underlying structural rules. While many vision-based and language-based models have achieved success on RPM tasks, it remains unclear whether their performance reflects genuine reasoning ability or reliance on statistical shortcuts. This study invest…