9 stories curated by AInformed
Pramana is a novel approach to fine-tune large language models for epistemic reasoning. It teaches LLMs to ground claims in traceable evidence, addressing the epistemic gap in AI reliability.
MegaTrain enables full precision training of large language models on a single GPU. It achieves this by storing parameters in host memory and using GPUs as compute engines.
A new mathematical theory models the evolution of self-designing AIs. This theory differs from biological evolution due to directed descendant design.
PaperOrchestra is a new multi-agent framework for automated AI research paper writing. It transforms unstructured materials into submission-ready manuscripts, including literature synthesis and generated visuals.
Pramana is a novel approach to teach large language models epistemological metacognition. It aims to improve systematic reasoning and reduce hallucinations in AI-generated text.
Phase-Associative Memory (PAM) is a new sequence model using complex-valued representations. It achieves 30.0 validation perplexity on WikiText-103, close to a matched transformer's 27.1.
PaperOrchestra is a multi-agent framework that automates AI research paper writing. It transforms unstructured materials into submission-ready manuscripts, including literature synthesis and generated visuals.
MegaTrain enables full precision training of large language models on a single GPU. It stores parameters in host memory and uses GPUs as compute engines.
A new mathematical theory models the evolution of self-designing AIs. This theory differs from biological evolution due to the directed nature of AI design.