Skip to content

Research separate from news

What could become important next

A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.

1381 published research events

Latest work

A significant claim from a single source is published only after further confirmation.

Research only one source so far

RED-PIM: Reducing transformer data movement through processing in memory

RED-PIM research optimizes transformer processing through algorithm–architecture co-design. The method reduces inter-bank data movement from O(N²) to O(N) and shrinks cache matrices from N×N to d×d. On real data, it improves inference by 99.60 % for long documents and 13.44 % for shorter…

arXiv cs.LG (Machine Learning) Original source ↗
Research only one source so far

Trajectory-aware agents for temporal decision-making

Researchers introduced TLM for processing long, temporally structured texts using LLM agents. Traditional RAG fragments chronological context; TLM preserves it through LGCM and SHAP feedback. It was tested on medical questions and financial event prediction, with better results.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Research into toxic behavior in the Mastodon community

A scientific paper from arXiv uses machine learning to examine how toxic behavior develops and spreads in the decentralized social network Mastodon, which has no uniform moderation standards. The goal is to understand toxicity trends and their impact on community health.

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Industrial tokenization for diagnostics: A federated architecture for integrating heterogeneous data into LLMs

The research paper presents the concept of Industrial Tokenization — a way of structuring heterogeneous industrial data from sensors, maintenance and diagnostic systems into standardized units for interpretation using large language models. The pilot implementation includes vibration diagnostics.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Multi-horizon consistency as the geometry of latent dynamics

An arXiv preprint examines how the weight of multi-horizon latent consistency affects video predictor geometry. On Moving-MNIST, increasing lambda from 0 to 0.8 reduced latent-space expansivity (L20 from 4.96 to 1.01) and prediction error. The same effect does not hold in other domains (Pendulum…

arXiv cs.LG (Machine Learning) Original source ↗
Research only one source so far

From frame recognition to event-level confirmation: Failure analysis of gesture interaction in public spaces

The research analyzes 8 records from deployments of gesture interaction in kiosks. It identifies 20 failures arising from the difference between individual-frame recognition and the stability of interaction events. It defines 6 failure classes and proposes a runtime abstraction for event confirmation.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Patient-aware pretraining of foundation models for health records

A study introduces Patient Sampling for pretraining autoregressive electronic health record models. The standard approach concatenates data from all patients into a single stream, introducing biases. The new method controls the distribution of signal across patients and improves performance on datasets…

arXiv cs.LG (Machine Learning) Original source ↗