arXiv Artificial IntelligenceSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding
arXiv:2609.05141v1 Announce Type: new Abstract: Scientific papers require models to reason jointly over text…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2609.05141v1 Announce Type: new Abstract: Scientific papers require models to reason jointly over text…
arXiv Artificial IntelligencearXiv:2609.05111v1 Announce Type: new Abstract: Large language models are now trained and evaluated under a…
arXiv Artificial IntelligencearXiv:2609.05104v1 Announce Type: new Abstract: Biological agents navigate familiar environments not by…
arXiv Artificial IntelligencearXiv:2609.05094v1 Announce Type: new Abstract: Electroencephalogram (EEG) visual decoding aims to recover…
arXiv Artificial IntelligencearXiv:2609.05093v1 Announce Type: new Abstract: We present Discovery Loop, a lightweight system that uses a…
arXiv Artificial IntelligencearXiv:2609.05090v1 Announce Type: new Abstract: Evaluation of medical artificial intelligence agents remains…
arXiv Artificial IntelligencearXiv:2609.05088v1 Announce Type: new Abstract: AI oversight methods rely on ground truth for validation, but…
arXiv Artificial IntelligencearXiv:2609.05075v1 Announce Type: new Abstract: General continual learning (GCL) aims to learn from evolving…
arXiv Artificial IntelligencearXiv:2609.05040v1 Announce Type: new Abstract: As evolutionary transfer optimization (ETO) scales to larger…
arXiv Artificial IntelligencearXiv:2609.05036v1 Announce Type: new Abstract: AI alignment requires AI systems to adhere to human norms…
arXiv Artificial IntelligencearXiv:2609.05019v1 Announce Type: new Abstract: Agents tend to optimize, select, or constrain execution…
arXiv Artificial IntelligencearXiv:2609.05009v1 Announce Type: new Abstract: Safety evaluations can mischaracterize deployed behaviour if…