Technology Innovation Institute (TII), Abu Dhabi, has released Falcon-H1R-7B, a 7B parameter reasoning specialized model that matches or exceeds many 14B to 47B reasoning models in math, code and general benchmarks, while staying compact and efficient. It builds on Falcon H1 7B Base and is available on Hugging Face under the Falcon-H1R collection. Falcon-H1R-7B is interesting because it combines 3 design choices in 1 system, a hybrid Transformer along with Mamba2 backbone, a very long context that reaches […]

Ver mais

The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of modern multi-core shared memory systems, it is challenging to determine the number of threads that minimises the multi-thread GEMM runtime. We present a proof-of-concept approach to building an Architecture and Data-Structure Aware Linear Algebra (ADSALA) software library that uses machine learning to optimise the runtime performance of […]

Ver mais

Preliminaries ‘An Introduction to Probabilistic Generative Models for Linear Classification’ Idea of logistic regression1 Logistic sigmoid function(logistic function for short) had been introduced in post ‘An Introduction to Probabilistic Generative Models for Linear Classification’. It has an elegant form: [ delta(a)=frac{1}{1+e^{-a}}tag{1} ] and when (a=0), (delta(a)=frac{1}{2}) and this is just the half of the range of logistic function. This gives us a strong implication that we can set (a) equals to some functions (y(mathbf{x})), and then

Ver mais

arXiv:2601.07873v1 Announce Type: new Abstract: Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm, which appends an update matrix to the original parameter matrix, has been shown by some studies to damage key numerical stability indicators (such as condition number and norm), thereby reducing editing performance and general abilities, especially in sequential editing scenario. Although subsequent methods have made some improvements, they remain within […]

Ver mais

Vision–language–action (VLA) models often suffer from limited robustness in long-horizon manipulation tasks due to their inability to explicitly exploit structural symmetries and to react adaptively when such symmetries are violated by environmental uncertainty. To address this limitation, this paper proposes PI-VLA, a symmetry-aware predictive and interactive VLA framework for robust robotic manipulation. PI-VLA is built upon three key symmetry-driven principles. First, a Cognitive–Motor Synergy (CMS) module jointly generates discrete and continuous action chunks together with predictive world-model features […]

Ver mais

arXiv:2601.04352v1 Announce Type: new Abstract: This study presents a comprehensive comparative analysis of custom-built Convolutional Neural Networks (CNNs) against popular pre-trained architectures (ResNet-18 and VGG-16) using both feature extraction and transfer learning approaches. We evaluated these models across five diverse image classification datasets from Bangladesh: Footpath Vision, Auto Rickshaw Detection, Mango Image Classification, Paddy Variety Recognition, and Road Damage Detection. Our experimental results demonstrate that transfer learning with fine-tuning consistently outperforms both custom CNNs built from scratch and […]

Ver mais

arXiv:2508.05663v3 Announce Type: replace Abstract: Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. However, their reliance on local interactions makes them inherently vulnerable to malicious behavior. In this work, we investigate an adversarial threat that we term the “Pac-Man” attack, in which a malicious node probabilistically terminates any RW that visits it. This stealthy behavior gradually eliminates active RWs from the network, […]

Ver mais

arXiv:2601.05262v1 Announce Type: new Abstract: Modern dense information retrieval (IR) models usually rely on costly large-scale pretraining. In this paper, we introduce LLM2IR, an efficient unsupervised contrastive learning framework to convert any decoder-only large language model (LLM) to an information retrieval model. Despite its simplicity, the effectiveness is proven among different LLMs on multiple IR benchmarks including LoCo, LongEmbed and BEIR. We also find that models with a longer context length tend to have a stronger IR capacity […]

Ver mais

By Michael Nielsen, January 2019 What does it mean to understand a piece of mathematics? Naively, we perhaps think of this in relatively black and white terms: initially you don’t understand a piece of mathematics, then you go through a brief grey period where you’re learning it, and with some luck and hard work you emerge out the other side “understanding” the mathematics. In reality, mathematical understanding is much more nuanced. My experience is that it’s nearly always […]

Ver mais

Slang interpretation has been a challenging downstream task for Large Language Models (LLMs) as the expressions are inherently embedded in contextual, cultural, and linguistic frameworks. In the absence of domain-specific training data, it is difficult for LLMs to accurately interpret slang meaning based on lexical information. This paper attempts to investigate the challenges of slang inference using large LLMs and presents a greedy search-guided chain-of-thought framework for slang interpretation. Through our experiments, we conclude that the model size […]

Ver mais