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 ↗459 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
Property‐Conditioned Transformer Language Model for De Novo Molecular Generation Using Self‐Referencing Embedded Strings ↗
Transformer-based molecular language models have demonstrated strong capabilities for de novo molecular generation by modeling chemical structures as token sequences. However, controllable generation of molecules with desired physicochemical properties remains challenging without reinforcement learning (RL) or post-generation filtering. In this study, we propose a property-conditioned autoregressive transformer framework for molecular generation using the SELFIES representation. Continuous molecular descriptors, including logP, quantitative estimate of drug-likeness, and molecular weight (MolW…
- OpenAlex · Published · First archived
NetFormer: A Dual-Stream Interpretable Transformer Autoencoder for Unsupervised Network Intrusion Detection ↗
Background The growing complexity and frequency of cyberattacks demand intrusion detection systems (IDS) that accurately identify malicious activity with very low false-positive rates and minimal latency. Traditional rule-based and classical machine learning methods are unable to capture the long-range temporal dependencies inherent in multi-stage attacks, and even recurrent neural networks struggle with vanishing gradients over long sequences. Transformers, with self-attention, can model such dependencies, but their application to unsupervised network anomaly detection with mixed data types r…
- OpenAlex · Published · First archived
A method for generating urban flood control emergency plans based on large language models and graph retrieval enhancement ↗
ABSTRACT Urban flood control emergency plans are crucial for addressing flood disasters and are essential for safeguarding lives and property as well as ensuring high-quality urban development. Existing generation methods often rely on shallow retrieval, which can lead to fragmented knowledge; moreover, the generation of long texts lacks structural constraints, frequently resulting in the omission of key elements. To address this, this study proposes a framework for generating urban flood control emergency plans that integrates LLMs with graph retrieval. First, a flood control knowledge graph…
- OpenAlex · Published · First archived
Intelligent Agents Based on Large Language Models in Transport Management: A Comparative Analysis of Approaches to Development and Implementation ↗
The paper addresses the “information gap” between objective telemetry data and primary documentation in logistics and road construction, which arises from the growing volume of unstructured information and a shortage of qualified personnel. Two projects aimed at creating intelligent agents to bridge this gap in transport management are examined. Based on a comparative analysis of two implemented solutions, the study identifies common architectural principles. The first project (technical proposal stage) develops an AI‑powered dispatcher assistant that automatically collects and matches request…
- OpenAlex · Published · First archived
Fine-GrainedEnergy Assessment of Vision Transformer Operators on Hybrid SoC Platforms: A CPU, iGPU, and NPU Case Study ↗
As CPUs alone are often insufficiently efficient for running Vision Transformers (ViTs), contemporary computing platforms, particularly edge systems, increasingly adopt heterogeneous architectures that combine CPUs with GPUs and Neural Processing Units (NPUs). This paper presents a detailed energy assessment of individual ViT functions running on a modern hybrid processor, the AMD Ryzen AI 9 HX 370, which features a CPU, an integrated GPU (iGPU), and a dedicated Neural Processing Unit (NPU). Unlike macro-level benchmarks, our analysis takes a fine-grained approach by focusing on the most widel…
- OpenAlex · Published · First archived
A tri-axial MFL GADF representation and axis-weighted Swin transformer approach for pipeline defect identification ↗
Magnetic flux leakage (MFL) measurements contain coupled directional responses that are affected by defect morphology, magnetisation conditions, sensor position, and measurement noise. Consequently, conventional handcrafted-feature methods and single-axis deep-learning models may not fully exploit the complementary information contained in tri-axial MFL signals. This study proposes AW-SwinT-Cal, a pipeline-defect classification framework combining per-axis Gramian Angular Difference Field (GADF) encoding, a shared Swin Transformer backbone, global axis-weighted feature fusion, test-time augmen…
- OpenAlex · Published · First archived
Mitigating Hallucinations in Finance-Based Multi-Agent Large Language Model Systems ↗
Large language models are increasingly used for financial question answering, while they are prone to generating hallucinated content. In this research, we propose a multi-signal framework for hallucination detection and mitigation. Our framework combines six signals (entailment, semantic similarity, claim verification, numeric consistency, token overlap and confidence calibration techniques) to identify hallucination type and severity. We evaluated our framework using multiple language models across three financial QA benchmark datasets (FinQA, FinanceQA, and FinDER). Our proposed framework c…
- OpenAlex · Published · First archived
Model-Based Scenario Engineering Using Large Language Models for Vehicle Concept Development ↗
Future-oriented requirements are difficult to capture during the early phases of vehicle concept development because conventional requirements engineering primarily considers current stakeholder needs and system environments. This paper proposes an evidence-based Model-Based Scenario Engineering approach that integrates Large Language Models (LLMs) into Model-Based Systems Engineering (MBSE) methodology to systematically incorporate future developments into early requirements engineering. The proposed method combines three complementary models: a stakeholder model, a system model, and a future…
- OpenAlex · Published · First archived
Hybrid RLHF-AIF: Uncertainty-Guided Routing of Human and AI Feedback for Cost-Efficient Safety Alignment of Large Language Models ↗
Safety alignment of large language models faces a feedback dilemma: human judgment is reliable but costly to scale; automated judgment is cheap but less trustworthy. Existing methods commit to one source per run, so misjudged responses are never corrected. This paper proposes Hybrid RLHF-AIF, which picks the feedback source for each sample online. First, a multi-label DistilBERT discriminator scores every response across 19 harm categories, reporting confidence through Monte Carlo dropout. Second, an uncertainty-aware scheduler sends only ambiguous or low-confidence responses to the reliable r…
- OpenAlex · Published · First archived
ChemE-MTDS:Multi-Turn Dialogue Data Synthesis and Quality-Controlled Fine-Tuning for Chemical Engineering Large Language Models ↗
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and reasoning. However, their performance in multi-turn dialogues within specialized domains, such as chemical engineering, remains limited due to the lack of high-quality, context-rich instruction datasets. In this paper, we propose ChemE-MTDS, a multi-turn dialogue data synthesis and quality-controlled fine-tuning framework specifically tailored for the chemical engineering domain. The framework integrates four complementary Question–Answering (QA) synthesis strategies: Continuous Scenari…
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.