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

Pegasus: Turning human videos into training data for robots

Pegasus is a framework for transforming human manipulation videos into data for robot learning. It bridges the gap between human and robot morphology (embodiment gap) through structured knowledge transfer via Task, Affordance and Constraint Graphs with physics-based verification. Evaluation on GTEA Gaze+ and…

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

AgentMap: Multi-agent framework for hybrid ontology matching

Scientific research introduces AgentMap, an LLM-based multi-agent framework for ontology matching that combines the identification of equivalent concepts and subsumption. It uses semantic search and hierarchical search. It outperforms baseline methods on four OM datasets in hybrid, equivalence-only…

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

MoMo: Motion mode control in robotic manipulation

A research paper from Apple Machine Learning Research introduces the MoMo framework. A two-stage imitation learning model with a transformer enables robots to perform manipulation tasks with variable motion modes. Across six tasks, they achieved generalization to unseen combinations of tasks and motion modes.

Apple Machine Learning Research Original source ↗
Research only one source so far

Auditing data pipelines for language model alignment and evaluation

The arXiv study introduces an efficient method for auditing LLM training data through data influence scoring without retraining. The authors applied the approach to HelpSteer2 and Anthropic HH-RLHF datasets, identifying types of labeling errors and safety problems in benchmarks.

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

Dynamic fact-checking evaluation remains contaminated by claims after models' cutoff dates

An arXiv preprint shows that dynamic benchmarks for multimodal fact-checking are less uncontaminated than assumed. Approximately 17–29% of claims published after models' cutoff dates contain previously available knowledge, increasing system performance by up to 11 points and distorting evaluation.

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