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 ↗449 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
jev-chat/jev-chat-jarvis-ios ↗
iOS 键盘：在任何聊天 App 里直接出意图、风险与候选回复——复制消息，键盘上见分晓。Swift / SwiftUI，中英双语。An iOS keyboard that drafts replies inside any chat app.
- OpenAlex · Published · First archived
Multi-Modal Deep Learning Approach for Comprehensive Pavement Condition Evaluation Using Vision-Language Models ↗
Timely and accurate assessment of pavement conditions is essential for roadway safety, infrastructure longevity, and cost-effective maintenance planning. Traditional methods rely heavily on manual inspections, which are labor-intensive, subjective, and limited in scalability. Recent advances in vision-language models (VLMs) offer a new opportunity to automate this process by integrating visual analysis with natural language generation. In this study, we propose a novel framework that leverages fine-tuned VLMs to automate pavement condition evaluation by analyzing visual inputs and generating d…
- OpenAlex · Published · First archived
White Blood Cell Classification with Data-Efficient Vision Transformer: A Multi-Dataset Evaluation on Raabin-WBC and PBC Repositories ↗
Traditional microscopic assessment of leukocyte morphology remains a labor-intensive workflow that is inherently vulnerable to inter-observer variability and subjective assessment risks. Automated classification systems are increasingly used as diagnostic aids for the identification and characterization of hematological samples. This study proposes a data-efficient transformer-based framework for white blood cell (WBC) classification under limited training data and computational constraints. The proposed system employs a DeiT-Tiny backbone with a transfer learning strategy. Contrast-Limited Ad…
- OpenAlex · Published · First archived
Enduring Strengths of Knowledge-Based Methods in the Era of Machine Learning and Large Language Models: A Task-and-Architecture Perspective ↗
Large language models have shifted AI toward statistical learning, but knowledge-based methods remain essential for tasks governed by combinatorial structure, declarative correctness, strong domain priors, and auditable reasoning. This paper treats the issue as one of task–architecture fit rather than paradigm competition. It surveys evidence across twelve problem classes, from satisfiability, constraint solving, planning, and formal mathematics to formal argumentation, answer set programming, knowledge graphs, and interpretable rule- and concept-based models, reporting concrete benchmark resu…
- OpenAlex · Published · First archived
A Frozen Plant DNA Language Model for Computational Prioritization and Functional Annotation of Melon (Cucumis melo) Variants ↗
Background/Objectives: Fruit quality in melon is determined by complex traits including sugar accumulation, aroma, flesh color, ripening behavior and disease resistance. Conventional genomic selection provides limited mechanistic interpretation, especially for regulatory and de novo variants. We adapted the EVEE interpretable embedding–probing framework to melon using PlantCAD2 as a frozen DNA language model backbone. Methods: The model was not fine-tuned or further pre-trained. Instead, lightweight probes were trained on fixed embeddings derived from sequence windows surrounding genetic varia…
- OpenAlex · Published · First archived
Integration of a large language model as an agent of the ChronobioticsDB pharmacological database ↗
Objective. To develop a methodologically rigorous approach for employing large language models as an interface for accessing data from pharmacological repositories (exemplified by ChronobioticsDB). Material and methods. A method for integrating a large language model as an intelligent access agent for the ChronobioticsDB pharmacological database was proposed. The approach is based on two-stage meta-prompting and does not require additional model training. Relational database data are pre-transformed into the structured text cards, which are used as a sole source of information for the model. A…
- OpenAlex · Published · First archived
SET-HOI: Skeleton-Enhanced Transformer with Parallel Fusion for HOI Detection ↗
Human–Object Interaction (HOI) detection seeks to identify the relationships between humans and objects in images that play a pivotal role in high-level vision tasks and biomimetic systems, such as biomimetic robotics, intelligent prosthetics, and embodied AI for intent understanding. However, existing approaches that rely solely on visual appearance features are susceptible to background interference, which adversely affects detection accuracy. Inspired by the biomimetic dual-stream mechanism of biological visual perception, we propose a Transformer-based HOI detection model with a dual-branc…
- OpenAlex · Published · First archived
Mission-Profile-Aware Physics-of-Failure Reliability Assessment and Quantitative FMEA of a 10 kW Solid-State Transformer ↗
Solid-state transformers (SSTs) are pivotal for next-generation power systems, yet their widespread adoption is hindered by reliability uncertainties under diverse operational conditions. This paper introduces a mission-profile-aware, physics-of-failure (PoF) reliability assessment framework that explicitly links operating conditions, degradation mechanisms, and statistical uncertainty. The approach combines PoF models for stress-sensitive components with handbook-based reliability models for passive elements, employing Joint Electron Device Engineering Council (JEDEC)-aligned statistical meth…
- OpenAlex · Published · First archived
From card catalogs to chatbots: envisioning academic library services in the era of AI and LLMs ↗
Purpose This article introduces the CARDLG framework: Collections, Access, Retrieval, Description, Literacy and Governance. The framework analyzes how generative artificial intelligence (AI) and large language models reconfigure recurring library infrastructural dimensions rather than representing wholly unprecedented disruption. Design/methodology/approach The analysis draws on library history from manuscript repositories through digital discovery systems, tracing how each CARDLG dimension evolved across technological eras. It identifies continuities, accelerations and ruptures in AI/large la…
- OpenAlex · Published · First archived
A Scalable Large Language Model‐Aided Approach for Mining Plant‐Compound Pairs From Scientific Literature ↗
Societal Impact Statement Understanding plant chemicals is vital for medicine and agriculture, but global data remain fragmented and biased. We developed an AI‐powered tool to automatically extract plant‐compound information from scientific literature at scale and low cost. Our analysis revealed significant knowledge gaps, particularly in the Southern Hemisphere. By efficiently uncovering thousands of potential new plant‐chemical links, this work provides a crucial resource for bioprospecting, taxonomy and conservation efforts, helping to ensure the benefits of nature's chemical diversity are…
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.