THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗452 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- OpenAlex · Published · First archived
Voice-enhanced image caption generation with vision transformers and Google Cloud TTS ↗
Abstract Today, when it comes to the digital world, engaging image captions are crucial to such industries as travel, where the strong visuals play a crucial role in attracting the audience. Nonetheless, manual captioning is both time-consuming and usually lacks the subtlety of a scene. The paper presents an AI-based model of automatic image captioning with contextual enrichment, based on deep learning models, which have been trained using the Flickr8k dataset. We combine a pretrained Vision Transformer (ViT) that retrieves granular visual features and global contextual features of images usin…
- OpenAlex · Published · First archived
Beyond the prompt for pedestrian traffic and crowd behavior management: PedAgent, a Large Language Model empowered Agent with an integrated simulating-analyzing-optimizing functional chain ↗
Pedestrian walking is one of the most fundamental modes of daily travel, yet recurrent pedestrian flow-related safety accidents, e.g., crowd crushes, highlight the urgent need for more intelligent management of high-density pedestrian facilities, for instance, urban subway stations. Existing pedestrian flow simulation models and empirically validated management policies provide valuable support, but they rarely satisfy the full-process requirements of crowd behavior management, i.e., simulation software can generate individual-level trajectories, but it usually lacks the ability to derive case…
- OpenAlex · Published · First archived
Generative LLM for adaptive taxonomy-informed multi-label classification in construction safety ↗
Accurate hierarchical multi-label classification of construction accident narratives is vital, yet traditional methods struggle with the Occupational Injury and Illness Classification System (OIICS), which contains over 2000 labels across four attributes with four-level hierarchies and is subject to taxonomic updates. This paper proposes the Adaptive Generative Construction Classification (AGCC), a taxonomy-informed generative framework that reformulates coding as structured sequence-to-sequence generation. Each attribute is predicted at a variable depth using leaf codes, while taxonomy-inform…
- OpenAlex · Published · First archived
Consensus Ensembles for Zero-Shot Algorithm Classification with Large Language Models ↗
Manual classification of algorithmic problems is costly and inconsistent, although it remains essential for curriculum sequencing, recommendation systems, and quality control on competitive programming platforms. To address this limitation, this study investigates whether consensus-based, zero-shot classification using large language models can replace manual annotation. Five architecturally diverse models were evaluated: Claude Sonnet v4.6 (CS4.6), DeepSeek v3.2 (DS3.2), Gemini v3 Flash (G3F), GPT v5.4 (GPT5.4), and Grok v4.1 Fast (GRK4.1). Each model independently classified 2911 LeetCode pr…
- OpenAlex · Published · First archived
LeakAgent: a multi-agent system for leak detection using multi-modal large language model coordination in water distribution network ↗
Water distribution networks (WDNs) suffer from severe leakage, yet pinpointing the leaks remains difficult. Data-driven detection is typically split into disconnected stages of hydraulic modelling, partitioning, sensor planning and analysis, and it treats the questions of whether a leak exists and where it lies as separate problems, which limits accuracy and transfer across networks. Here we show that these tasks can be unified within a multi-agent system (MAS) coordinated in natural language by a large language model (LLM). A single hydraulic pressure-sensitivity field, computed once, informs…
- OpenAlex · Published · First archived
Benchmark-Driven Selection of AI Can Improve Capabilities of Reasoning Language Models in Epistemology ↗
Abstract Evaluation of reasoning language models gained importance after it was observed that they can combine their existing capabilities into novel traces of intermediate steps before task completion and that the traces can sometimes help them to generalize better than past models. We show that better performance results not only from test time algorithmic improvements or model sizes but also from letting tasks from impactful benchmarks inspire curricula for learning. We call this benchmark-driven selection of AI and show its effects on DeepSeek-R1, the first open-weight large reasoning mode…
- OpenAlex · Published · First archived
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality ↗
Large Language Models (LLMs) perform differently on identical tasks when prompted in different languages—a phenomenon known as language bias. Although well-documented for general text generation, the extent to which language bias affects code generation quality and programming conventions remains largely unexplored. To address this gap, we investigate how the natural language used to describe programming tasks influences the quality of source code generated by three prominent LLMs: GPT-4o mini , DeepSeek, and Claude. Our study includes 460 coding tasks spanning Python (230 tasks) and Java (230…
- OpenAlex · Published · First archived
GrIT: Group Informed Transformer for Sequential Recommendation ↗
Sequential recommender systems aim to predict a user's future interests by extracting temporal patterns from their behavioral history. Existing approaches typically employ transformer-based architectures to process long sequences of user interactions, capturing preference shifts by modeling temporal relationships between items. However, these methods often overlook the influence of group-level features that capture the collective behavior of similar users. We hypothesize that explicitly modeling temporally evolving group dynamics alongside individual user histories can significantly enhance ne…
- OpenAlex · Published · First archived
MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code ↗
With the advent of large language models (LLMs), numerous software service providers are developing LLMs tailored for code generation, such as CodeLlama. However, these models can be exploited by malicious developers to generate malicious code, posing severe threats to the software ecosystem. To address this issue, we first conducted an empirical study and built MCGTest , a dataset of \(406\) prompts designed to elicit malicious code from LLMs. Leveraging this dataset, we propose MCGMark , a watermarking method to trace and attribute LLM-generated malicious code. MCGMark subtly embeds user-spe…
- Europe PMC · Published · First archived
EdiProPred: Prediction of Edible Plant Tissue-Associated Proteins Using Large Language Models ↗
Ensuring the safety and suitability of proteins considered for food and biotechnology applications is an important challenge. Computational approaches can facilitate the prioritisation of candidate proteins for further investigation, particularly given the rapid growth of genomic and metagenomic sequence datasets. In this study, we developed computational models to distinguish edible plant tissue-associated (EPTA) proteins from non-EPTA proteins. The positive class comprised 939 proteins with experimentally validated evidence of expression in plant tissues commonly consumed by humans, hereafte
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.