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 ↗456 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
Exploring the key genes of colorectal “adenoma-cancer” based on graph transformer ↗
Colorectal cancer (CRC) is one of the most lethal malignancies worldwide, and the precise identification of biomarkers from colonic adenoma to cancer is of great significance for preventing the development of adenocarcinoma. Given that existing methods inadequately capture the topological network relationships among genes, this study proposes a graph neural network model based on multifeature learning, named ChebTs, to investigate the correlation between key genes involved in the colorectal “adenoma-cancer” transition. The GSE41657 and GSE31905 datasets from the GEO database were stratified in…
- OpenAlex · Published · First archived
Transformer based FinBERT framework with explainable artificial intelligence for money laundering detection ↗
The increasing complexity of suspicious financial activities has reduced the effectiveness of conventional rule-based monitoring for modern anti-money laundering (AML) applications. This study proposes FinBERT-AML, a transformer-based framework fine-tuned on transaction feature tokens to learn complex dependencies across heterogeneous financial attributes. Through self-attention-based representation learning, the framework jointly models categorical and continuous transaction characteristics while overcoming limitations associated with conventional machine learning and sequential architectures…
- OpenAlex · Published · First archived
Domain-adaptive Bengali text summarization: Harnessing transformer-based large language models in closed-set contexts ↗
This work aims to develop a domain-adapted Bengali text summarization model by training and fine-tuning on general and domain-specific datasets with categories such as state, international, and sports. Flan-T5 and mT5 LLMs were trained on the XLSUM Bengali dataset for text summarization, and they were trained on source domains and fine-tuned on the target domains for domain adaptation. In general-domain summarization on the XLSum Bengali dataset, mT5 achieved stronger overall performance than Flan-T5, with ROUGE-1 and BERTScore values of 0.21 and 0.72, respectively. The Flan-T5-XLSUM model out…
- OpenAlex · Published · First archived
A Cache-Aware Compression Framework: Deriving the Compression Target and Stopping Rule for Transformers on CPU-Class Hardware ↗
In post-training compression of Transformer models, the compression ratio or pruning rate is often predetermined and does not directly take into account the memory capabilities of the target hardware. This work introduces a cache-aware post-training compression framework for CPU-class hardware. The framework derives the minimum required compression ratio from the effective weight working set of the operator or layer and the effective level-3 (L3) cache budget. The cache budget is treated as a hardware resource shared with concurrent modules rather than as a latency heuristic. If functional red…
- OpenAlex · Published · First archived
A zero-shot LLM framework for analyzing user preference on product attributes: a case study of smartwatch reviews ↗
The rise of zero-shot learning through Large Language Models (LLMs) opens new opportunities for analyzing consumer feedback without relying on annotated data. This study proposes a zero-shot framework to uncover user preferences on product attributes, using 12,900 Amazon smartwatch reviews as a case study. The framework integrates semantic keyword extraction, LLM-based attribute classification, sentiment analysis, and Importance–Performance Analysis (IPA) to convert unstructured textual reviews into structured consumer preference insights. Validation against human annotations demonstrates stro…
- OpenAlex · Published · First archived
Correlation-Guided Graph Transformer Networks for Cold-Start Group Event Recommendation in Social Networks ↗
The emergence of social platforms has seen the importance of group event recommendation increase as a result of the fast rate of growth. In comparison to single-user recommendation, the group recommendation has to capture overall preferences and overcome the extreme sparsity, long-tail distributions, and cold-start problems. This paper suggests Correlation-Guided Graph Transformer Network (CG-GTN) to address these problems. The framework proposes the use of correlation to construct bi-partite graphs by using a convex combination of behavioral similarity, contextual similarity and time proximit…
- OpenAlex · Published · First archived
Federated knowledge-guided 3D Transformer learning for bone tumor segmentation from partially annotated computed tomography data ↗
Accurate 3D delineation of bone tumors and metastatic lesions from volumetric CT is essential for diagnosis, staging, radiotherapy planning, and treatment monitoring, yet manual contouring is time consuming and variable across observers. Although modern 3D CNN/Transformer segmenters achieve strong centralized performance, they typically assume pooled multi-institution data and consistent label definitions. In practice, clinical imaging archives are privacy-isolated, exhibit pronounced non-IID appearance shift (scanner/protocol and case-mix variation), and provide heterogeneous and partially an…
- Hacker News · Posted on Hacker News · First archived
Full-fabric VHDL LLM inference engine. Runs Qwen3.5-class transformer inference ↗
Hacker News discussion.
- GitHub · Repository created · First archived
justAnArthur/hackyeah-review ↗
HackYeah 2026 finalists and uploads, scored out of 100 by an AI council against each task's criteria
- Hacker News · Posted on Hacker News · First archived
Letting an LLM write executables byte by byte (hello world to playable Tetris) ↗
Hacker News discussion.
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.