profiling attention in pytorch
a walkthrough of profiling different attention implementations in pytorch, from naive to fused kernels, using torch.profiler to spot performance differences.
aitag machine learning
summaries filed under machine learning
explaining temporal graph networks via memory backtracking
a new method explains temporal graph network predictions by tracing how past events shape node memory vectors through backtracking and topological attribution.
aiwho gets missed in chest x-ray ai decisions
study shows how threshold choices in long-tailed chest x-ray models can miss rare-positive patients, especially in subgroups, and how tail-aware methods reduce underdiagnosis.
airecolora keeps llm fine-tuning from forgetting past tasks
a new spectrum-aware method recursively consolidates low-rank adapters so each task builds on previous ones without overwriting them.
aiautomate descriptive statistics in python
learn to build a repeatable pipeline for generating publication-ready summary tables from raw data using python tools.
airun openclaw with ollama for private ai assistant
set up a private ai research assistant on telegram using openclaw and ollama, with web search and docker deployment.
aiconformal 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.
aipytorch 2.13: flexattention on apple silicon, fused loss, new distributed backend
pytorch 2.13 brings flexattention to mps, a fused linear and cross-entropy loss, a new torchcomms backend, and more.
aitriroute jointly routes attention, experts, and kv-cache
a single lightweight controller coordinates attention mode, expert selection, and cache bit-width per token to reduce inference cost without losing quality.
aivllm transformers backend now matches native speed
the transformers modeling backend in vllm now achieves throughput equal to or better than hand-written native implementations for many large language models.
aiopen data and synthetic data for ai agents
nvidia nemotron releases open datasets and a prompt atlas to help developers build inspectable, reliable ai agents using synthetic data.
aigeometry framework tests if ai learns or just memorizes
a new mathematical model uses fiber bundles to detect when machine learning systems discover causal laws instead of interpolating data.
aithe granularity paradox in time-series forecasting
finer temporal disaggregation inflates in-sample fit but degrades out-of-sample accuracy due to recursive error compounding.
aione-click from hugging face to sagemaker studio
hugging 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 adds schema migrations
sqlite-utils 4.0 introduces database schema migrations, nested transactions, and compound foreign keys for sqlite databases.
aizero-egress ai storage with skypilot and hugging face
mount 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.
aisql vs pandas vs ai agents for analytics
a comparison of sql, pandas, and a claude agent on three analytics problems across speed, accuracy, and other dimensions.
aihugging face models on foundry managed compute
microsoft 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.
aitreat pdfs as images for zero-shot parsing with gemma 4
render pdf pages to images and use gemma 4 to extract structured data without ocr or layout parsers.
ai10 probability concepts for machine learning
a plain-language guide to ten essential probability ideas that make machine learning work, from random variables to entropy.
ai