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 ↗446 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.
- GitHub · Repository created · First archived
struklabs/harness-studio ↗
Run open AI models on your own computer — a friendly desktop app and local gateway for llama.cpp and more. Private, free, open source.
- GitHub · Repository created · First archived
BaronCyrus/dsh-packycode-api ↗
Use a PackyCode (PackyAPI) API key in DeepSeek Harness: built-in multi-protocol model route, ordered API-key rotation, and balance display
- GitHub · Repository created · First archived
luojuncheng0327-cell/CAgent ↗
本地优先（Local-First）的桌面 AI 工作台：对话、文件与文档协作整合在一起，数据默认保存在本机。Windows 桌面应用，Electron + TypeScript。
- OpenAlex · Published · First archived
Physics-Guided Multi-View Transformer with Block Attention Residuals for Cross-Condition Railway Bearing Fault Diagnosis ↗
Railway bearings experience speed- and load-dependent distribution shifts that complicate fault diagnosis. This study proposes a Physics-Guided Multi-View Transformer with Block Attention Residuals (PGMV-BAR). Characteristic-order prior tokens sequentially query envelope-order and time–frequency features and remain in the fusion sequence with a separate condition token. A two-stage strategy combines masked reconstruction, contrastive consistency, prior alignment, and supervised fine-tuning. Evaluation follows a source-only cross-condition protocol. Beijing Jiaotong University–Rail Autonomous O…
- OpenAlex · Published · First archived
High-Information-Density Knowledge Graph Retrieval Augmentation for Large Language Models ↗
Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in large language models (LLMs) by injecting external knowledge into the context window, yet its effectiveness is rigidly constrained by attention dilution and inference cost. Existing knowledge-graph-enhanced methods follow a sequential “retrieve-then-compress” paradigm in which retrieval and compression are optimized independently, preventing the compressor from rectifying redundancy and noise introduced during retrieval and making it difficult to achieve globally efficient information allocation under a lim…
- OpenAlex · Published · First archived
Research on the Evolution Characteristics and Collaborative Detection Strategies for Bottom Oil-Spill Fires in Oil-Immersed Transformers ↗
Conventional single-type detectors generally face difficulties in achieving both early warning and fire-source localization for rapidly developing bottom oil-spill fires occurring in large oil-immersed transformers. In this study, a 500 kV transformer bottom oil-spill fire model is established to analyze the evolution of temperature field, smoke density, CO and CO2 concentrations, and thermal radiation, and to compare the response characteristics of various detectors. A stable high-temperature zone forms within 30 s after ignition, exhibiting a central temperature of 950–1000 °C and a distinct…
- OpenAlex · Published · First archived
Hierarchical Safe and Robust UAV Path Planning Based on Large Language Models ↗
Unmanned aerial vehicle (UAV) path planning is widely applied in fields such as Internet of Things (IoT) environmental monitoring, intelligent transportation, low-altitude logistics, and autonomous inspection. With the rapid development of UAV intelligence, natural language task planning powered by Large Language Models (LLMs) has emerged as a promising research hotspot. However, in safety-critical flight missions, LLMs suffer from issues such as unstable structured outputs, insufficient understanding of complex constraints, and unreliable responses to dangerous inputs, which can jeopardize th…
- OpenAlex · Published · First archived
Transformer-Convolution Pyramid Network for Multi-Class Kidney, Tumor, and Cyst Segmentation ↗
Background/Objectives: Chronic kidney diseases are fatal disorders, and early treatment is crucial for reducing mortality. Segmenting kidneys, tumors, and cysts from computed tomography scans has a significant role in assessing these diseases’ progression, determining their severity, and planning surgeries. However, accurate segmentation is challenging for many reasons. The objective of this study is to develop a hybrid network that can overcome these challenges. Methods: The proposed network was designed using (i) a patch-joining and swin transformer block to capture global features efficient…
- OpenAlex · Published · First archived
Foundation Models and Vision-Language Models in Medical Imaging: A Review ↗
Foundation models (FMs) and vision-language models (VLMs) have emerged as a transformative paradigm in artificial intelligence, reshaping the landscape of medical image analysis and clinical decision support. Building upon large-scale pretraining on heterogeneous datasets, these models exhibit unprecedented generalization and zero-shot transfer capabilities, effectively overcoming the perennial bottleneck of annotated data scarcity that has historically constrained deep learning applications in healthcare. This review paper presents the state of the art in FMs and VLMs applied to medical imagi…
- OpenAlex · Published · First archived
ReViT-RF: A hybrid ResNet-50–Vision Transformer with a Radiomic Feature Fusion framework for lung tumor classification and TNM-based stage prediction using CT images ↗
Lung cancer is one of the leading causes of cancer-related mortality worldwide, emphasizing the need for accurate, automated, and clinically interpretable diagnostic systems. Although existing deep learning (DL) models have achieved promising performance in classifying lung nodules as benign or malignant, most approaches are limited to binary classification and provide insufficient support for detailed tumor characterization and TNM staging. Furthermore, conventional convolutional neural networks (CNNs) are effective in extracting local morphological features but often fail to capture long-ran…
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.