conformal prediction fails minority classes in drug screening
standard conformal prediction under-covers rare classes in imbalanced drug discovery data, but a class-conditional fix restores coverage.
aisummaries filed under machine learning
standard conformal prediction under-covers rare classes in imbalanced drug discovery data, but a class-conditional fix restores coverage.
aipytorch 2.13 brings flexattention to mps, a fused linear and cross-entropy loss, a new torchcomms backend, and more.
aia single lightweight controller coordinates attention mode, expert selection, and cache bit-width per token to reduce inference cost without losing quality.
aithe transformers modeling backend in vllm now achieves throughput equal to or better than hand-written native implementations for many large language models.
ainvidia nemotron releases open datasets and a prompt atlas to help developers build inspectable, reliable ai agents using synthetic data.
aia new mathematical model uses fiber bundles to detect when machine learning systems discover causal laws instead of interpolating data.
aifiner temporal disaggregation inflates in-sample fit but degrades out-of-sample accuracy due to recursive error compounding.
aihugging face and amazon sagemaker ai now offer a deep-link integration that lets developers move from model discovery to fine-tuning or deployment in sagemaker studio with a single click.
aisqlite-utils 4.0 introduces database schema migrations, nested transactions, and compound foreign keys for sqlite databases.
aimount hugging face buckets and repos into skypilot jobs on any cloud with no egress fees for reads, using one hf:// url and your existing token.
aia comparison of sql, pandas, and a claude agent on three analytics problems across speed, accuracy, and other dimensions.
aimicrosoft foundry now offers a curated catalog of open-weight hugging face models deployable with one click onto managed compute, refreshed weekly and pre-staged in azure.
airender pdf pages to images and use gemma 4 to extract structured data without ocr or layout parsers.
aia plain-language guide to ten essential probability ideas that make machine learning work, from random variables to entropy.
aia study shows that perturbation-based construct-validity audits can produce misleading conclusions due to hidden pipeline failures, and proposes a due-diligence gate to catch them.
aia new method lets text-to-speech models pronounce tricky words correctly by using short audio hints, without changing the speaker's voice.
aipytorch monarch now supports amd instinct gpus with rocm, enabling single-controller distributed training that recovers from node failures without full restarts.
aiphotoroom details its data strategy for the prx text-to-image model, covering dataset assembly, captioning, and storage formats.
aidata scientists now spend more time managing ai systems than building models, with new roles in governance, prompt engineering, and agent supervision.
aia cli agent that automates machine learning tasks from plain english descriptions, handling coding, training, and model publishing.
ai