…functional metacognitive reasoning — not just "can the model solve it," but "does the model know when, why, and how it solves it." 100 tasks across 15 domains, built on the TICOS framework…
…These vectors are then merged with pretrained parameters to form a capability-enhanced meta model . Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss , the merged model attains performance…
…autonomous agents learn to reflect on their own epistemic trajectory? Inspired by the need for cognitive scaffolding, I’ve built MarCognity-AI https://huggingface.co/elly99/MarCognity-AI — a metacognitive framework that…
…Kirscher , , , , , , , , , , , , , , , , , Abstract Researchers developed a new dataset and challenge for pancreatic cancer staging that emphasizes uncertainty-aware AI models capable of handling ambiguous tumor-vessel interfaces, revealing that traditional segmentation metrics fail…
…NSF-SciFy enables new research directions in large-scale claim verification, scientific discovery tracking, and meta-scientific analysis. Code and data are available at https://github.com/darpa-scify/NSFSciFy. View arXiv…
…We then build a large-scale metadata construction pipeline that converts mixed-source ERP panoramas into geometry-aware , language-grounded , and depth-aware supervision , and instantiate these signals as capability-aligned instruction…
…clinical records with X-rays, real-estate metadata with street-view photos, product listings with descriptions and images. But current approaches usually force one side to adapt: either LLMs/VLMs handle the…
…AI-generated summary Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.