Preprint proposes matrix compression method that matches or improves standard approximation
Researchers report a matrix compression method that matches or improves truncated singular value decomposition, which represents data with a smaller low-rank approximation, at equal parameter cost. Their preprint tests the method ...
Nullify preprint reports selective LLM forgetting without weight updates
Researchers report in a preprint that Nullify, a method designed to suppress specific memorized information in large language models, matches or surpasses established forgetting baselines on TOFU and MUSE while preserving model ut...
NEMORA preprint reports long-range atomistic learning at hundreds of thousands of atoms
Researchers report in a preprint that NEMORA, a method for learning interactions between atoms over long distances, handles systems containing hundreds of thousands of atoms with computation time and memory that scale linearly wit...
Preprint reports schema-free generation of valid enterprise test data
Researchers report in an arXiv preprint that their Generalist Populator agent generated enterprise data with 100% constraint satisfaction and 0.88 average marginal fidelity across ten simulated environments without accessing datab...
Preprint reports task-completion gains from agent-generated interfaces
Researchers report in an arXiv preprint that training an agent to generate interactive interfaces improved a 4B model's Pass@3 task-completion score from 9.33% to 58.00%. Their GenUI-Harness pairs an agent that retrieves informati...
Google launches Gemini agent for business tasks across internal systems
Google announced a unified Gemini agent for businesses that can plan work and act across internal systems, TechCrunch reported. The company will bring the agent to businesses before rolling it out to consumers. Google says users ...
