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 ↗441 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
--help on your CLI is all you need for LLM context until you don't ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Ask HN: Are you a subscribed LLM or a locally deployed open-source model? ↗
Could you briefly introduce the reason or what it's used for?
- GitHub · Repository created · First archived
tommy85/MirrorForce ↗
Yu-Gi-Oh! (YGO) AI trained by self-play reinforcement learning on the YGOPro engine; champion of the first YGO agent competition
- OpenAlex · Published · First archived
An Evidence-Based Knowledge Graph Framework with Large Language Models and Human-in-the-Loop for Ovarian Cancer Resistance ↗
The reciprocal relationship between large language models (LLMs) and knowledge graphs (KGs) opens new opportunities for knowledge discovery from scientific literature; however, most approaches address only one direction of this interaction. In complex biomedical domains, ensuring reliability, interpretability, and traceability remains challenging, making expert supervision essential. In this work, we propose a framework that integrates LLMs, KGs, and a Human-in-the-Loop scheme for constructing, evaluating, and reasoning over Evidence-based Knowledge Graphs (E-KGs), explicitly linking each extr…
- OpenAlex · Published · First archived
Spatial cognitive patterns of underground public spaces from a stimulus-organism-response perspective: evidence from LLM-empowered social media data mining ↗
Current underground public space (UPS) renewal prioritizes engineering-oriented physical upgrades, neglecting users’ multidimensional cognitive experiences. Existing studies on underground space perceptions rely on small-sample surveys and fail to capture joint co-occurrence patterns among multiple stimuli. This study integrated the Stimulus-Organism-Response framework with large language models to decode spatial cognitive patterns. It drew on 76,078 social media reviews from 64 UPSs in 19 Chinese cities (2005–2024). DeepSeek extracted 27 spatial stimuli and their sentiments, serving as public…
- OpenAlex · Published · First archived
LLM fine-tuning for international news style generation and cross-cultural dissemination quality assessment ↗
The rapid globalization of news media has heightened the demand for high-quality, culturally adapted international news content. However, generating news articles that faithfully conform to the stylistic conventions of diverse national media outlets while maintaining cross-cultural semantic fidelity remains a formidable challenge. This paper presents a novel framework that leverages fine-tuned large language models (LLMs) for international news style generation and introduces a comprehensive cross-cultural dissemination quality assessment (CDQA) methodology. Specifically, we construct a multil…
- OpenAlex · Published · First archived
Prompt-Shape- and Prefix-Cache-Aware CPU/NPU Routing for Large Language Model Inference on Edge SoCs ↗
Large language model (LLM) inference on edge systems must exploit heterogeneous central processing unit (CPU) and neural processing unit (NPU) resources under tight memory and latency constraints. Because prefilling and autoregressive decoding have different computational characteristics, the fastest backend depends on the request shape and prefix-cache reuse. This work proposes request-level CPU/NPU routing for the RK3588 system on chip (SoC). Prompt-shape-aware routing (PSR) uses prompt length and generation budget to select a backend for no-cache requests, while prefix-cache-aware routing (…
- OpenAlex · Published · First archived
Hybrid Transformer Architecture for Context-Aware Spam Email Classification ↗
Spam and phishing email remain a persistent cybersecurity threat and a primary delivery vector for credential theft, malware, and ransomware. Detection accuracies above 99% are routinely reported. Such figures are typically obtained on small, single-source, monolingual corpora in which near-duplicate campaign templates span the training and test partitions. This study re-examines what they measure. A corpus of 99,707 emails is assembled from four independent public collections spanning multiple languages, campaign-aware deduplication is applied before splitting, and nine models—classical, conv…
- OpenAlex · Published · First archived
Electronically Rotated Electrical Capacitance Tomography Sensing and Image Reconstruction Based on Transformer Model ↗
Electrical capacitance tomography (ECT) is a noninvasive imaging technology based on capacitance sensors mainly used for measuring and imaging nonconductive fluid in multiphase flow. However, ECT has underdetermined and nonlinear problems due to limited sensor electrodes, which pose challenges for image reconstruction. Therefore, this paper uses the sensing technology based on electronically rotated electrical capacitance tomography (ER-ECT) to increase the number of independent measurements by combined excitation to alleviate the underdetermined problem. At the same time, ER-ECT combined with…
- OpenAlex · Published · First archived
Modulation of Soft Magnetic Properties in Fe-Based Amorphous and Nanocrystalline Alloys for Power Transformers: A Review ↗
Fe-based amorphous and nanocrystalline alloys are essential core materials for high-efficiency distribution transformers, high-frequency transformers, and power electronic transformers, owing to their high saturation magnetic flux density (Bs), low coercivity (Hc), low core loss, and excellent high-frequency response. This review summarizes recent progress in the modulation of soft magnetic properties, covering composition design, heat treatments, structural engineering, and transformer applications. For compositional design, a central issue is how to achieve high Bs while retaining sufficient…
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.