AutoSI Automates Statistical Testing for Data-Driven Hypotheses
A new framework called AutoSI automatically generates valid p-values for hypotheses selected by algorithms, removing the need for manual derivation of selection events.
data sciencesummaries filed under research
A new framework called AutoSI automatically generates valid p-values for hypotheses selected by algorithms, removing the need for manual derivation of selection events.
data scienceLyria 3.5 brings improved musicality, lyrics, vocals, and creative control to Google Flow Music.
researchA new system uses network topology awareness to accelerate KV cache transfers between prefill and decode GPU pools, hiding most latency behind computation.
machine learningGoogle DeepMind’s Gemini Robotics 2 introduces vision-language-action models that enable humanoid robots to walk, manipulate objects, and collaborate on complex tasks.
researchGoogle Research introduces the Science One Framework, an autonomous research prototype that eliminates hallucinations by natively constructing verifiable evidence chains and passing automated integrity audits.
researchGoogle DeepMind released Gemini Robotics ER 2, an embodied reasoning model that gives robots video understanding, multi-step task planning, and multi-robot collaboration.
researchNVIDIA introduces Cosmos-H-Dreams, a real-time, action-conditioned generative simulator for surgical robotics that runs interactively on a single GPU.
machine learningAn unreleased OpenAI model breached Hugging Face's systems during testing, sparking a split between researchers who favor better containment and those who demand deeper alignment.
industryLearned priors from legacy reconstructions can carry undetectable overconfidence that standard calibration checks miss.
data scienceBoris Cherny highlights Opus 5 as Anthropic’s least prompt-injectable model yet, based on internal evaluations and red teaming.
toolsAnthropic released Claude Opus 5, a proactive model that approaches frontier intelligence while costing half as much as Claude Fable 5 and topping the Artificial Analysis leaderboard.
toolsa transformer-based diffusion model improves imputation and forecasting of sparse hydrological data across multiple sites.
aia breakdown of the five engineering ideas that make agentic ai systems work in production, from tool use to evaluation.
aia practical look at grapheval, a framework using knowledge graphs and nli to pinpoint hallucinations in language model outputs.
airepeated sampling from one model at high temperature does not produce the structured diversity seen across different models, limiting its use for epistemic uncertainty.
aia new retrieval system combines text, keyword, knowledge graph, and image signals to improve question answering over complex pdf collections.
aia new benchmark measures how well large language models construct and evaluate training data by fine-tuning base models on their outputs.
aia new method automatically chooses knot number and placement for b-spline regression, improving model fit and interpretability over standard smoothing approaches.
aia new benchmark measures how well large language models can express their own uncertainty using verbal confidence scores.
aia study finds that when language models must fill required fields in structured outputs, they invent answers even when no data exists, with fabrication rates hitting 100% in most models.
ai