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

DocSkill framework improved question answering across document pages in a study

The study introduces the DocSkill framework and the MMHop-DocBench dataset with 60 thousand question-answer pairs in 10 languages. Using Qwen3-VL-8B, the framework achieved an accuracy of 41.0 and an F1 score of 49.2, according to the authors, exceeding the best-performing baseline evaluated by 5.5 and 6.3 points, respectively.

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

Study introduces OA-RAG for ontology-supported answers

The OA-RAG method combines formal reasoning over ontologies with LLMs and provides evidence alongside a model-based assessment of how well answers are supported. According to the authors, it achieved the best overall results among the methods compared in tests involving three ontologies and six medical tasks.

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

Study shows how to adjust uncertainty in world model predictions when the control policy changes

The study proposes weighted uncertainty calibration when the control policy changes, without modifying the model. In an experiment using trajectories from a Franka robot, prediction set coverage at a nominal level of 90 % reached 90.9 %, according to the authors, while standard calibration achieved 55 %.

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

OmniBrain-0 unifies planning for robotic manipulation and navigation

The authors introduce OmniBrain-0, a model that combines planning, task tracking and error recovery in robotic manipulation and navigation. It uses distillation from multiple teacher models; according to the authors, it has lower operational overhead than the closed teacher model.

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

Study presents a speech language model for Basque

The authors present a speech language model for Basque based on the LLaMA-Omni architecture and the Latxa model. They used translated data and synthetic speech for training. They report a content rating of 3.86/5, a transcription word error rate (WER) of 9.94 % and a UTMOS audio quality score of 3.07.

arXiv cs.CL (Computation and Language / NLP) Original source ↗