SEARCH · Searcharxiv

Results for “cs.GL”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9Linked to original sources

arXiv2025

Advancing AI Challenges for the United States Department of the Air Force

The DAF-MIT AI Accelerator is a collaboration between the United States Department of the Air Force (DAF) and the Massachusetts Institute of Technology (MIT). This program pioneers fundamental advances in artificial intelligence (AI) to expand the competitive advantage of the United States in the defense and civilian sectors. In recent years, AI Accelerator projects have developed and launched public challenge problems aimed at advancing AI research in priority areas. Hallmarks of AI Accelerator challenges include large, publicly available, and AI-ready datasets to stimulate open-source solutions and engage the wider academic and private sector AI ecosystem. This article supplements our previous publication, which introduced AI Accelerator challenges. We provide an update on how ongoing and new challenges have successfully contributed to AI research and applications of AI technologies.

cs.AI↗

arXiv2025

Kaggle Chronicles: 15 Years of Competitions, Community and Data Science Innovation

Since 2010, Kaggle has been a platform where data scientists from around the world come together to compete, collaborate, and push the boundaries of Data Science. Over these 15 years, it has grown from a purely competition-focused site into a broader ecosystem with forums, notebooks, models, datasets, and more. With the release of the Kaggle Meta Code and Kaggle Meta Datasets, we now have a unique opportunity to explore these competitions, technologies, and real-world applications of Machine Learning and AI. And so in this study, we take a closer look at 15 years of data science on Kaggle - through metadata, shared code, community discussions, and the competitions themselves. We explore Kaggle's growth, its impact on the data science community, uncover hidden technological trends, analyze competition winners, how Kagglers approach problems in general, and more. We do this by analyzing millions of kernels and discussion threads to perform both longitudinal trend analysis and standard exploratory data analysis. Our findings show that Kaggle is a steadily growing platform with increasingly diverse use cases, and that Kagglers are quick to adapt to new trends and apply them to real-world challenges, while producing - on average - models with solid generalization capabilities. We also offer a snapshot of the platform as a whole, highlighting its history and technological evolution. Finally, this study is accompanied by a video (https://www.youtube.com/watch?v=YVOV9bIUNrM) and a Kaggle write-up (https://kaggle.com/competitions/meta-kaggle-hackathon/writeups/kaggle-chronicles-15-years-of-competitions-communi) for your convenience.

cs.LG↗

arXiv2025

LLM Architecture, Scaling Laws, and Economics: A Quick Summary

The current standard architecture of Large Language Models (LLMs) with QKV self-attention is briefly summarized, including the architecture of a typical Transformer. Scaling laws for compute (flops) and memory (parameters plus data) are given, along with their present (2025) rough cost estimates for the parameters of present LLMs of various scales, including discussion of whether DeepSeek should be viewed as a special case. Nothing here is new, but this material seems not otherwise readily available in summary form.

cs.GL↗

arXiv2026

Validation of a Small Language Model for DSM-5 Substance Category Classification in Child Welfare Records

Background: Recent studies have demonstrated that large language models (LLMs) can perform binary classification tasks on child welfare narratives, detecting the presence or absence of constructs such as substance-related problems, domestic violence, and firearms involvement. Whether smaller, locally deployable models can move beyond binary detection to classify specific substance types from these narratives remains untested. Objective: To validate a locally hosted LLM classifier for identifying specific substance types aligned with DSM-5 categories in child welfare investigation narratives. Methods: A locally hosted 20-billion-parameter LLM classified child maltreatment investigation narratives from a Midwestern U.S. state. Records previously identified as containing substance-related problems were passed to a second classification stage targeting seven DSM-5 substance categories. Expert human review of 900 stratified cases assessed classification precision, recall, and inter-method reliability (Cohen's kappa). Test-retest stability was evaluated using approximately 15,000 independently classified records. Results: Five substance categories achieved almost perfect inter-method agreement (kappa = 0.94-1.00): alcohol, cannabis, opioid, stimulant, and sedative/hypnotic/anxiolytic. Classification precision ranged from 92% to 100% for these categories. Two low-prevalence categories (hallucinogen, inhalant) performed poorly. Test-retest agreement ranged from 92.1% to 99.1% across the seven categories. Conclusions: A small, locally hosted LLM can reliably classify substance types from child welfare administrative text, extending prior work on binary classification to multi-label substance identification.

cs.CL↗

arXiv2026

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their performance. To address these training bottlenecks, we propose MicroCoder-GRPO, an improved Group Relative Policy Optimization approach with three innovations: conditional truncation masking to improve long output potential while maintaining training stability, diversity-determined temperature selection to maintain and encourage output diversity, and removal of KL loss with high clipping ratios to facilitate solution diversity. MicroCoder-GRPO achieves up to 17.6% relative improvement over strong baselines on LiveCodeBench v6, with more pronounced gains under extended context evaluation. Additionally, we release MicroCoder-Dataset, a more challenging training corpus that achieves 3x larger performance gains than mainstream datasets on LiveCodeBench v6 within 300 training steps, and MicroCoder-Evaluator, a robust framework with approximately 25% improved evaluation accuracy and around 40% faster execution. Through comprehensive analysis across more than thirty controlled experiments, we reveal 34 training insights across seven main aspects, demonstrating that properly trained models can achieve competitive performance with larger counterparts.

cs.LG↗

arXiv2026

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage Data Processing Framework encompassing collection, processing, filtering, and verification, incorporating Automatic Difficulty Filtering via an LLM-based predict-calibrate-select framework that leverages multi-dimensional difficulty metrics across five weighted dimensions to retain challenging problems while removing simplistic ones. The resulting MicroCoder dataset comprises tens of thousands of curated real competitive programming problems from diverse platforms, emphasizing recency and difficulty. Evaluations on strictly unseen LiveCodeBench demonstrate that MicroCoder achieves 3x larger performance gains within 300 training steps compared to widely-used baseline datasets of comparable size, with consistent advantages under both GRPO and its variant training algorithms. The MicroCoder dataset delivers obvious improvements on medium and hard problems across different model sizes, achieving up to 17.2% relative gains in overall performance where model capabilities are most stretched. These results validate that difficulty-aware data curation improves model performance on challenging tasks, providing multiple insights for dataset creation in code generation.

cs.CL↗

arXiv2026

Linux and High-Performance Computing

In the 1980s, high-performance computing (HPC) became another tool for research in the open (non-defense) science and engineering research communities. However, HPC came with a high price tag; the first Cray-2 machines, released in 1985, cost between \$12 million and \$17 million, according to the Computer History Museum, and were largely available only at government research labs or through national supercomputing centers. In the 1990s, with demand for HPC increasing due to vast datasets, more complex modeling, and the growing computational needs of scientific applications, researchers began experimenting with building HPC machines from clusters of servers running the Linux operating system. By the late 1990s, two approaches to Linux-based parallel computing had emerged: the personal computer cluster methodology that became known as Beowulf and the Roadrunner architecture aimed at a more cost-effective supercomputer. While Beowulf attracted attention because of its low cost and thereby greater accessibility, Roadrunner took a different approach. While still affordable compared to vector processors and other commercially available supercomputers, Roadrunner integrated its commodity components with specialized networking technology. Furthermore, these systems initially served different purposes. While Beowulf focused on providing affordable parallel workstations for individual researchers at NASA, Roadrunner set out to provide a multi-user system that could compete with the commercial supercomputers that dominated the market at the time. This paper analyzes the technical decisions, performance implications, and long-term influence of both approaches. Through this analysis, we can start to judge the impact of both Roadrunner and Beowulf on the development of Linux-based supercomputers.

cs.DC↗

arXiv2026

POSIM: A Multi-Agent Simulation Framework for Social Media Public Opinion Evolution and Governance

Modeling social media public opinion evolution is essential for governance decision-making. Traditional epidemic models and rule-based agent-based models (ABMs) fail to capture the cognitive processes and adaptive behaviors of real users. Recent large language model (LLM)-based social simulations can reproduce group-level phenomena like polarization and conformity, yet remain unable to recreate the irrational interactions and multi-phase dynamics of real public opinion events. We present POSIM (Public Opinion Simulator), a multi-agent simulation framework for social media public opinion evolution and governance. POSIM integrates LLM-driven agents with a Belief--Desire--Intention (BDI) cognitive architecture that accounts for irrational factors, places them in a virtual social media environment with social networks and recommendation mechanisms, and drives temporal dynamics through a Hawkes point process engine that captures the co-evolution of agents and the environment across event phases. To validate the framework, we collect real-world public opinion datasets from the Weibo platform covering the full interaction chain of users. Experiments show that POSIM successfully reproduces key characteristics of public opinion evolution from individual mechanisms to collective phenomena, and its effectiveness is further supported by multiple statistical metrics. Building on POSIM, governance-oriented guidance and intervention experiments uncover a counterintuitive empathy paradox: empathetic guidance deepens negative sentiment instead of easing it under certain conditions, offering new insights for governance strategy design. These results demonstrate that the proposed framework can fully serve as a computational experimentation platform for proactive strategy evaluation and evidence-based governance. All source code is available at https://github.com/DeepCogLab/posim/.

cs.GL↗

arXiv2026

On the First Computer Science Research Paper in an Indian Language and the Future of Science in Indian Languages

I describe my experience writing the first original, modern Computer Science research paper expressed entirely in an Indian language. The paper is in Telugu, a language with approximately 100 million speakers. The paper is in the field of distributed computing and it introduces a technique for proving epistemic logic based lower bounds for multiprocessor algorithms. A key hurdle to writing the paper was developing technical terminology for advanced computer science concepts, including those in algorithms, distributed computing, and discrete mathematics. I overcame this challenge by deriving and coining native language scientific terminology through the powerful, productive, Pāninian grammar of Samskrtam. The typesetting of the paper was an additional challenge, since mathematical typesetting in Telugu is underdeveloped. I overcame this problem by developing a Telugu XeLaTeX template, which I call TeluguTeX. Leveraging this experience of writing an original computer science research paper in an Indian language, I lay out a vision for how to ameliorate the state of scientific writing at all levels in Indic languages -- languages whose native speakers exceed one billion people -- through the further development of the Sanskrit technical lexicon and through technological internationalization.

cs.GL↗

arXiv2026

The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligence

Dr. David Blackwell was a mathematician and statistician of the first rank, whose contributions to statistical theory, game theory, and decision theory predated many of the algorithmic breakthroughs that define modern artificial intelligence. This survey examines three of his most consequential theoretical results the Rao Blackwell theorem, the Blackwell Approachability theorem, and the Blackwell Informativeness theorem (comparison of experiments) and traces their direct influence on contemporary AI and machine learning. We show that these results, developed primarily in the 1940s and 1950s, remain technically live across modern subfields including Markov Chain Monte Carlo inference, autonomous mobile robot navigation (SLAM), generative model training, no-regret online learning, reinforcement learning from human feedback (RLHF), large language model alignment, and information design. NVIDIAs 2024 decision to name their flagship GPU architecture (Blackwell) provides vivid testament to his enduring relevance. We also document an emerging frontier: explicit Rao Blackwellized variance reduction in LLM RLHF pipelines, recently proposed but not yet standard practice. Together, Blackwell theorems form a unified framework addressing information compression, sequential decision making under uncertainty, and the comparison of information sources precisely the problems at the core of modern AI.

cs.GL↗

arXiv2026

From Physical Difference to Meaning: A Constructor-Theoretic Framework for Prebiotic Information in Casimir-Lifshitz-Coupled Protocell Clusters

This paper develops a physical framework for the prebiotic emergence of information and meaning. Building on Constructor Theory, we define information as a reproducible physical difference and meaning as a difference with stable functional consequences. Casimir-Lifshitz-coupled protocell clusters serve as a minimal model that exhibits reproducible attractors, ordered transitions, and autonomous task structures. We show that such clusters carry both informational states (e.g., distances, geometries, gradients) and meaningful states that regulate prebiotic tasks such as approach, exchange, or stabilization. This approach integrates physical mechanisms, computational mechanics, and early proto-semantic functions into a coherent account of information formation before biology.

physics.bio-ph↗

arXiv2026

A Brief History of Fréchet Distances: From Curves and Probability Laws to FID

This note provides a chronological account of Fréchet distances, starting with Maurice Fréchet's 1906 doctoral thesis on distances in abstract sets and tracing the Fréchet distance between polygonal curves and its algorithmic computation in the 1990s. It then continues with his 1957 paper on a coupling-based distance between probability laws with a brief glimpse of Wasserstein distance and optimal transport. We further attempt to draw connections between the distributional, coupling-based facet of Fréchet distances on probability laws and the geometric facet on curves. The note ends with a modern use case, the Fréchet Inception Distance (FID) in the era of deep generative model evaluation, interpretable as the Wasserstein-2 distance between multivariate Gaussians in a learned feature space. An appendix includes \TeX{}ified faithful English translations of Fréchet's 1906 thesis and 1957 paper, and Lévy's 1950 note for reader convenience.

cs.GL↗

arXiv2026

People, IT, and Structuration (PIS): An Integrative Theoretical Framework for Management Information Systems

The Management Information Systems (MIS) discipline has long grappled with how to theorize the complex, mutually constitutive relationships among people, information technology, and organizational structures. Decades of research have produced influential but fragmented theoretical streams from socio-technical systems theory to technology acceptance models, from adaptive structuration theory to sociomateriality, and each illuminating important facets while leaving integrative questions unresolved. This paper proposes the People - IT - Structuration (PIS) framework as a unifying theoretical lens that synthesizes these streams. Drawing on Giddens' structuration theory, we conceptualize People (P), Information Technology (I), and Structure (S) not as independent variables but as mutually constitutive elements engaged in ongoing structuration processes. We trace the intellectual history of MIS theorizing to demonstrate how PIS resolves persistent tensions in the field,e.g. between technological and social determinism, between variance and process approaches, and between micro-level interaction and macro-level institutional dynamics. We develop a set of formal propositions articulating the mechanisms through which P, I, and S co-evolve, and extend the framework to address contemporary phenomena including artificial intelligence, algorithmic management, and human-AI collaboration. The PIS framework offers both a retrospective lens for understanding the discipline's theoretical evolution and a prospective tool for guiding research in the AI era.

cs.HC↗

arXiv2026

Tensor Cookbook: Mastering Tensors through Diagrams

High-dimensional data arise naturally in many areas of science and engineering, including machine learning, signal processing, computational physics, and statistics. Such data are often represented as tensors, multi-dimensional generalizations of matrices. While tensors provide a natural representation for multi-modal structure, their direct manipulation quickly becomes challenging as the order grows: the number of parameters increases exponentially, and algebraic expressions involving many indices become difficult to interpret and implement. Tensor networks (TNs) provide an effective framework for addressing these challenges. Originally introduced by Penrose and developed extensively in quantum physics, the graphical language of tensor networks encodes contractions as edges in a graph, reducing notational overhead and revealing structural properties obscured by index notation. Despite the central role of high-dimensional tensors in modern machine learning and numerical analysis, tensor network diagrams remain underutilized outside quantum computing, partly due to the lack of a self-contained mathematical reference accessible to a broad technical audience. This manuscript provides a self-contained guide to tensor networks and their use in tensor algebra. We present the main operations on tensors, contractions, products, and reshaping through, graphical notation, and show how classical tensor decompositions and related computations are naturally expressed in this framework. We also illustrate how tensor networks simplify the derivation of gradients and the manipulation of high-dimensional probability distributions. Throughout, we show that the diagrammatic approach yields genuinely shorter and more transparent proofs of classical identities, rank bounds, and gradient formulas that would otherwise require laborious index manipulation.

cs.LG↗

arXiv2026

History of the Muddy Children Puzzle

The Muddy Children Puzzle is a puzzle about knowledge and ignorance that has been inspiring for the development of epistemic logic. Who came up with it first? This is unclear. We trace the origin of the Muddy Children Puzzle through logical and literary publications over the past two centuries. The puzzle inspired a numerous variations such as involving numbers or coloured hats. We also present a novel hats puzzle involving self-reference.

cs.AI↗

arXiv2026

From the NYU Ultracomputer to Modern Exascale: A Historical and Architectural Survey of In-Network Computing and Scalable Synchronization

This paper presents a historical and technical survey of the hardware architectures, interconnection networks, and synchronization primitives that have shaped massively parallel systems over the past four decades. We examine the design of the NYU Ultracomputer and the IBM Research Parallel Processor Prototype (RP3), focusing on the hardware implementation of the Fetch-and-Add primitive in multistage interconnection networks. We contrast these early attempts at fine-grained, shared-memory hardware combining with the distributed-memory architectures of the IBM SP series and the modern in-network computation models found in NVIDIA SHARP and HPE Slingshot. We provide a technical analysis of message-passing synchronization, presenting a complete profiling of MPI operation frequencies and detailing the low-level hardware mapping of one-sided RMA atomics to PCIe Atomics and GPU caches. We investigate the software-hardware boundary in modern deep learning, detailing how HIP translation, Triton compilation, and 4-bit quantization (W4A16) execute on modern heterogeneous silicon. To evaluate alternative network node designs, we present a historical hardware case study analyzing the feasibility of implementing active combining switches using message-passing Inmos Transputers programmed in Occam. Finally, we contextualize the evolution of concurrent software synchronization by examining Isaac Dimitrovsky's parallel "group lock" primitive, tracing its downstream echoes in group mutual exclusion (GME) and room synchronization, and reflect on the historical, philosophical divide between American systems engineering and European formal methods.

cs.DC↗

arXiv2026

LLM for the development of FCM

This article is about the development of a fuzzy cognitive map using a local large language model. In the light of recent advances it is evident that large language models, and even local large language models are capable of extracting quantities from textual data. In other words, a local LLM like Qwen2.5-32B, or probably larger, can accept entities as prompt input and determine relevant quantitative data as the model output. In turn, this output can be utilized for the construction of a data driven fuzzy cognitive map. Hence, this implementation is achieved and then the model is thoroughly tested; Qwen2.5-32B is used and the data is extracted from hotel reviews from TripAdvisor. Furthermore, the extracted documents pass through the model unfiltered and then a fuzzy cognitive map is trained and evaluated. A case is made about Greek reviews where a star topology FCM is formed that indicates the preferences of the reviewers. Finally, external validation is performed to establish whether the fuzzy cognitive map can correlate the star rating of the review -an outcome outside the model's inference scope -with its predicted satisfaction.

cs.NE↗

arXiv2026

The Reconstructions of Konrad Zuse's Z3 Computer

This paper reviews the various reconstructions of Konrad Zuse's Z3 computer, built in 1941. The first is the reconstruction made by Zuse himself in the 1960s, which is now housed at the Deutsches Museum in Munich. Second is the 2001 reconstruction, made in Berlin, and which has a didactic purpose. Third is the Z3r, a Z3 reconstruction built by Horst Zuse in honor of his father's 100th birthday. Fourth is the reconstruction by Christoph Traber in Switzerland. All of these machines strive to preserve the cultural heritage that the Z3 represents.

cs.GL↗