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 ↗460 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.
- Hacker News · Posted on Hacker News · First archived
PSSA: A non-transformer language model written from scratch in Rust ↗
Hacker News discussion.
- OpenAlex · Published · First archived
A hybrid 4-DoF control for bidirectional series half three-level CLLC converter with minimum RMS current in solid state transformer ↗
The bidirectional series half three-level CLLC (SHBCLLC) converter is an attractive option for solid state transformer due to its high efficiency and bidirectional power flow capability. However, existing variable-frequency and pulse width modulation (PWM) modulation exhibit large inductor RMS current. Additionally, PWM control methods fail to achieve ZVS across the entire operating range. To address this issue, a four-degrees-of-freedom control (4-DoF) modulation strategy is proposed in this paper. The proposed modulation scheme achieves lower RMS current and full-range ZVS operation, thereby…
- OpenAlex · Published · First archived
A Guided Implicit Generative Adversarial CNN–Transformer Framework for Class-Imbalanced Hyperspectral Image Classification ↗
Hyperspectral image (HSI) classification is important for land-cover recognition and remote-sensing scene analysis. However, class imbalance severely limits performance when minority classes contain only a few labeled samples, causing models to show strong overall results while failing to identify minority classes effectively. We propose a 3D guided implicit generative adversarial oversampling model (3D-GIGAMO), a generation–classification collaborative framework that alleviates class imbalance by producing class-conditioned minority-class patches for task-oriented oversampling, while learning…
- OpenAlex · Published · First archived
Can Large Language Model-Based Chatbots Support Sustainable AI-Enhanced Education? Evidence from Young Learners’ Conceptions ↗
Understanding learners’ conceptions of artificial intelligence (AI)-supported learning can inform the sustainable integration of AI into education. This study examined primary school students’ conceptions of large language model-based (LLM-based) chatbots-supported learning and explored differences associated with learning motivation. Seventy-two students participated in learning activities designed around the CLEAR prompt-engineering framework. A mixed-methods approach combined the draw-and-write technique with questionnaires assessing learning motivation, self-efficacy, and critical thinking…
- OpenAlex · Published · First archived
Evaluating Large Language Models with a Unified Prompt-Based Pipeline for Turkish News Summarization and Tag Extraction ↗
News texts are critically important in facilitating readers quick access to accurate information in today’s substantially increasing information-driven world. The very fast pace of news flow and the abundance of highly informative data across various fields require the analysis of summarization and tag extraction tasks. This study aims to measure the multitasking performance of summarization and tag extraction tasks in Turkish news texts using a unified pipeline with a small datasets and different prompt techniques. Summarization and tag extraction tasks were performed with a single pipeline u…
- OpenAlex · Published · First archived
A Hybrid UKF–ST-Graph Transformer Framework for Cooperative Localization in Ship Ad-Hoc Networks ↗
In sea environment the localization of ships is very important for traffic management. AutomaticIdentification System (AIS) dataset is widely used to get information of ship. This paper proposed ahybrid localization framework for Ship Ad hoc Networks (SANETs) using AIS dataset. This studyintegrates an Unscented Kalman Filter (UKF) with Spatio-Temporal Graph Transformer (ST-GT)built on SANETs to provide cooperative localization. First, UKF is utilized raw AIS data to getinitial position estimates for ship. Then, a SANETs based on spatial proximity is constructed to fromfeatures such as node deg…
- OpenAlex · Published · First archived
MT-brainVLM: a multi-task 3D vision–language model for hierarchical report generation with dual-path Shapley explainability ↗
Hierarchically organised report generation from high-dimensional 3D inputs is a central yet underexplored capability of multi-task vision–language models (VLMs), obstructed by three problems: unifying report generation with structurally incompatible auxiliary heads under one weight-shared backbone, natively handling partially available modalities, and providing axiomatically grounded, numerically verifiable attributions for multi-output predictions. We propose MT-BrainVLM, an end-to-end multi-task 3D VLM coupling a modality-aware 3D U-Net encoder and mask-gated fusion, a BLIP-2-style Q-Former…
- OpenAlex · Published · First archived
A Binary Hybrid Particle Whale Optimization Framework for Feature Selection in Industrial Transformer Partial Discharge Classification ↗
Partial discharge (PD) testing based on IEC 60270 is widely employed for assessing the insulation integrity of power transformers. Although numerous statistical descriptors can be extracted from PD measurements, redundant and irrelevant features can degrade classification performance, particularly in small datasets. This study proposes a binary hybrid particle whale optimization algorithm (BHPWOA) for multi-objective wrapper-based feature selection in transformer insulation severity classification. The analysis comprises 64 IEC 60270 partial-discharge test sessions collected from 30 power tran…
- OpenAlex · Published · First archived
Open-ended Human Activity Understanding via LLM-assisted Motion Decomposition and Semantic Fusion ↗
Human activity is a fundamental component of intelligent interactive systems. Existing human activity recognition (HAR) follows a closed-ended assumption—defining a fixed set of activity classes and classifying each sensor signal into one of them—yet real-world human behavior is complex and ever-changing and thus cannot be fully represented by any fixed set. We present a new paradigm for open-ended human activity understanding (HAU), shifting the goal from closed-set classification to understanding activities via their meta-motions. To achieve this, we design MOSAIC, a motion decomposition and…
- OpenAlex · Published · First archived
Automated Health Care Thematic Analysis Using a Multiagent Large Language Model: Algorithm Development and Evaluation Study ↗
Background Understanding patients’ experiences is essential for advancing patient-centered care, especially in chronic diseases that require ongoing communication. Qualitative thematic analysis is widely used to explore these experiences; however, the process remains labor-intensive, subjective, and difficult to scale. Objective This study aimed to develop and evaluate Collaborative Theme Identification Agents (CoTI), a multiagent large language model framework designed to support manual thematic analysis by rapidly generating supporting excerpts, initial codes, and themes. Methods CoTI consis…
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.