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 ↗452 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
Scenic spot crowd flow prediction: Combining large language model semantic understanding and spatio-temporal network ↗
Accurate forecasting of tourist flows is crucial for urban planning, transportation management, and overcrowding prevention. Tourism demand is highly sensitive to external stimuli, often leading to abrupt and irregular fluctuations that are difficult to quantify using existing methods. To address this issue, we propose an event-aware dynamic spatiotemporal network (EAD-STN) that integrates large language model embeddings with dynamic spatiotemporal graph modeling. External factors are encoded into high-dimensional representations to capture their impacts on visitor demand. The model further in…
- OpenAlex · Published · First archived
Can Zero-Shot Large Language Models Be Trusted for Credit-Risk Prediction? An Explainability Audit Against LightGBM on Loan Default Data ↗
Zero-shot large language models (LLMs) offer a low-barrier route to credit-risk prediction, but regulated use requires evidence on discrimination, probability reliability, and auditable decision patterns. We compare four open-source LLMs (Gemma-2-9B, Llama-3.2-3B, Mistral-7B-v0.3, and Qwen2.5-7B) with LightGBM on 396,030 U.S. LendingClub loans issued from 2007 to 2016. Treating loans as independent and identically distributed observations from this pooled cross-sectional population, we evaluate every model on the same random 20% holdout. All models receive the same 21 structured predictors and…
- OpenAlex · Published · First archived
A hybrid framework of LLM-based interaction generation and adaptive sampler for recommendation enhancement ↗
Data augmentation (DA) is a critical technique for addressing data sparsity. Existing DA methods suffer from several limitations: extensive parameter tuning, dependency on specific types of data, and the tightly coupled DA network in the backbone recommendation model. Consequently, there remains a notable absence of universal data augmentation frameworks capable of adapting to diverse recommendation tasks and backbone models. To address these issues, we propose a hybrid framework to mitigate data sparsity via DA in a more flexible and universal paradigm. Notably, we disentangle the data augmen…
- OpenAlex · Published · First archived
Dynamically perturbed Ruppell Fox optimization with a context aware transformer for coherent document level English to Chinese translation ↗
Document-level English–Chinese neural machine translation requires consistent handling of lexical choices, entities, anaphora, and discourse relations across sentence boundaries. Existing context-aware models partially improve cross-sentence consistency, but many rely on fixed context windows, manually selected configurations, or single-path document representations, limiting their adaptability to domains with different discourse structures and terminology densities. This study proposes a unified framework that integrates a Context-Aware Transformer (CAT) with dynamically perturbed Rüppell’s F…
- OpenAlex · Published · First archived
Governing Large Language Model Services for Confidential Microdata: A Decision Framework for National Statistical Offices ↗
National statistical offices increasingly face requests to provide large language model (LLM) capabilities in secure research environments. The governance problem is to determine which service configurations, if any, can be supported safely on confidential microdata. These services challenge traditional statistical disclosure control because interaction is adaptive, systems may retrieve documents or call analytical tools, and outputs may appear plausible without being grounded in approved data. This paper proposes a governance framework that organizes each request as a sequence of decisions: w…
- OpenAlex · Published · First archived
A Domain-Adapted Multilingual Large Language Model for Mining Safety in African Languages ↗
The African mining industry continues to face a serious communication gap between technical safety documentation and the language used by the workforce. Safety manuals, operating procedures, and regulatory guidance are often produced in English or French, while many workers communicate in isiZulu, chiShona, and other local languages. This mismatch is not just inconvenient; it can be dangerous in safety-critical settings where misunderstandings may contribute to preventable incidents. This paper reports on Talk MINING, a domain-adapted multilingual large language model built on InkubaLM and tra…
- OpenAlex · Published · First archived
EgoTokens: Egocentric 3D human reconstruction and language-guided shape editing via quantized position tokens in vision-language models ↗
3D human body reconstruction from egocentric images is a challenging task because of environmental and self-occlusion. Downward viewpoints and scale ambiguity can also hinder precise 3D estimation. Current methods mainly rely on specialized regression networks to reconstruct 3D meshes that often lack structural guidance from high-dimensional SMPL-X parameters. In the proposed work, we introduce EgoTokens, a framework that estimate egocentric SMPL-X parameters as a discrete sequence-generation task. Our end-to-end system employs vision-language models (VLMs) to predict SMPL-X body parameters di…
- OpenAlex · Published · First archived
DPCformer: Dual-Prior Calibration Transformer for low-light image enhancement ↗
Low-light image enhancement (LLIE) remains challenging because low-light degradation usually exhibits complex and coupled characteristics, including uneven illumination, weakened structures, and amplified noise. The aim of this paper is to develop an effective and efficient LLIE framework for coordinated exposure correction, structure preservation, and noise-aware detail recovery under complex low-light conditions. To this end, this paper proposes a Dual-Prior Calibration Transformer (DPCformer), which jointly exploits illumination-aware and content-aware priors in a unified restoration framew…
- OpenAlex · Published · First archived
MCI-DETR: A Multi-Level Context Interaction Transformer for Small-Object Detection in UAV Imagery ↗
Small objects in UAV imagery often exhibit weak visual representations, suffer from background clutter, and receive insufficient cross-scale feature interaction. To address these challenges, we develop MCI-DETR, a multi-level contextual interaction detector built upon RT-DETR. First, a Local-Context Modulated Interaction Module (LCMI) is designed to selectively modulate contextual features using local structural responses, thereby suppressing irrelevant background responses while expanding the effective receptive field. Second, CATM is incorporated into the high-level feature interaction stage…
- OpenAlex · Published · First archived
Explainable Emergency Response Recommendation for Foundation Pit Collapse Accidents: An LLM-Enabled E/B/R Ontology-Driven Hybrid Reasoning Framework ↗
Foundation pit collapse accidents require rapid identification of accident conditions and appropriate emergency measures. Accident investigation reports contain valuable response knowledge, but their unstructured format limits direct reuse. This study develops an LLM-enabled E/B/R ontology-driven hybrid reasoning framework for explainable emergency response recommendations. Accident knowledge is organized as Event (E), Bearing (B), and Response (R). The resulting ontology contains 51 subclasses, and 69 foundation pit collapse reports were retained from 1110 collected construction collapse repo…
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.