THE INTERNET IS THINKING
Earlier sources: Artificial Intelligence
Artificial intelligence covers systems that learn from data, generate content, perceive their surroundings, or act toward a goal. Follow model research, agent tooling, evaluation, and the infrastructure used to build and run these systems.
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 ↗5986 classified signals in the fourteen-day window. Recent momentum: steady. 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.
- arXiv · Published · First archived
Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation ↗
Safe reinforcement learning seeks policies that maximise task performance while satisfying safety constraints. In driving benchmarks, however, collision costs typically appear only at the time of collision, providing no advance warning of an approaching hazard. Frozen vision--language models can provide dense semantic feedback, yet it remains unclear whether their scores anticipate collisions and which component drives an observed safety improvement. Episodic cost can also favour policies that make little task progress. To address these gaps, we propose VLM-Safe-RL, a framework that integrates…
- arXiv · Published · First archived
Large Language Models for Structured Clinical Data Analysis: Dual-Agent Grounding and Validation ↗
Objective: To develop and characterize CLEAR-Med, a dual-agent framework for natural-language analysis of structured clinical data that separates SQL-based invocation from independent validation. Methods: CLEAR-Med uses one agent to translate a question into executable Structured Query Language (SQL), retain the executed query and database result, and produce a draft. Deterministic checks and a separately invoked cross-provider Validation Agent then accept the draft, request one bounded repair, or abstain. We formalized the system as a bounded selective pipeline and evaluated CLEAR-Med's confi…
- 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
Machine Learning‐Enabled Occupancy Modelling for Energy‐Efficient and Sustainable Building Operations: A Critical Review of Strategies and Future Directions ↗
ABSTRACT The study of occupancy behaviour (OB) and prediction of building energy consumption is an important topic, while machine learning (ML) with the use of real‐time data and adaptive algorithms has become more relevant. Although research in this area is rapidly expanding, each of the models developed so far still presents limitations in scalability and transferability to various building environments attributed to the differences in modelling strategies, data inputs, sensing approaches and evaluation methods. The current review studies have tended to be limited to a specific aspect of occ…
- OpenAlex · Published · First archived
Neural network-based study of thermal behaviour in radiative magnetized Casson micropolar nanofluid flow between two disks ↗
This work examines thermally radiative Casson nanofluid flow through the variable porous space between two circular disks. The flow is subjected to the micro-rotation theory with effects of magnetohydrodynamics in the normal direction of the flow system. The governing equations are first solved using the bvp4c numerical solver to generate accurate reference solutions. These solutions subsequently serve as the foundational training dataset for the artificial neural network (ANN), providing a reliable basis for model training, prediction, and performance validation. This work shows that error hi…
- OpenAlex · Published · First archived
Procedural Modelling and Generative AI for Augmented Contextual 3D Visualisation of Planned Urban Change ↗
Street-level visualisations play an important role in urban street redesign by helping stakeholders and non-specialist audiences understand proposed spatial transformations. However, conventional image-editing workflows are often time-consuming, while purely image-based generative AI approaches provide limited control over object position, scale, and spatial relationships. This study presents a novel, highly automated workflow combining georeferenced street-level smartphone imagery, procedural 3D modelling, semantic image segmentation, and controlled generative AI to produce realistic visualis…
- 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
From Trial-and-Error to Learn-by-Experiment: The Future of Materials Research in Perovskite and Organic Photovoltaics ↗
The next major change in perovskite and organic photovoltaic research may not come from a new material or device architecture, but from a new way of doing and analyzing experiments. Conventional trial-and-error optimization, often a onevariable-at-a-time (OVAT) approach, typically varies a limited number of parameters sequentially, making it difficult to resolve interactions within the increasingly complex processing spaces of complex, multilayer solar cells and demands a large number of experiments. We argue that robotic experimentation combined with machine learning can fundamentally alter t…
- OpenAlex · Published · First archived
EWCMD: real-time attack detection using ensemble weighted combination machine learning and deep learning methods ↗
Abstract The evolving IoT threat landscape makes Distributed Denial-of-Service (DDoS) attacks a persistent security concern. This paper proposes a five-stage ensemble intrusion detection framework combining machine learning and deep learning. The first four stages train and evaluate seven machine learning classifiers and a convolutional neural network (CNN) on the NSL-KDD and UNSW-NB15 datasets, incorporating feature selection and hyperparameter optimization to improve accuracy and reduce computational cost. The fifth stage introduces two final prediction strategies: a weighted roulette-wheel…
- OpenAlex · Published · First archived
Fatigue Life Evaluation of a Steel–Prestressed Concrete Hybrid Tower Under Prestress Relaxation Using a Bidirectionally Coupled Damage Model and Neural Network Surrogate ↗
This study investigates the long-term fatigue performance of an in-service 4.55 MW steel–prestressed concrete hybrid wind turbine tower under different tendon relaxation scenarios. The fatigue lives of prestressing tendons and concrete are calculated from finite element stress responses obtained in ABAQUS. A bidirectionally coupled damage model then updates the damage and stiffness of the two materials to determine the overall coupled fatigue life. Based on these results, a Spatial-Topology and Physics-Informed Cascade Network (STPI-Net) is developed for life prediction. The results show that…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Artificial Intelligence
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 ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.