topological features as survival data for testing and learning
a new method treats persistence diagrams as survival data, enabling hypothesis testing, effect sizes, and stable feature vectors for machine learning.
topic
machine learning
prohiflo: hierarchical flow matching for protein generation
a new hierarchical flow matching framework generates proteins with functional guidance and fewer sampling steps.
boltzmann margin gives knn near-exponential convergence
a new margin condition bridges the gap between polynomial and exponential rates for knn classifiers.
python scripts to automate pdf tasks
five python scripts that merge, split, extract, stamp, redact, and inventory pdfs from the command line.
local agentic coding with claude code, ollama, and gemma 4
a guide to building a local agentic programming stack using ollama, gemma 4, and claude code, with setup steps and verification.
helion kernels speed up vllm fp8 inference
helion, a pytorch-native kernel dsl, improves vllm inference throughput for qwen3 models with fp8 quantization on nvidia gpus.
synib: training objective for multimodal synergy
a new training objective called synergistic information bottleneck targets task-relevant information that only emerges from combining multiple modalities.
conformal risk prediction for fatty liver disease
a machine learning framework combines gradient boosting with conformal prediction to give reliable individual risk estimates for non-alcoholic fatty liver disease.
uncertainty-aware subspace rectification for trustworthy mllm decoding
a new training-free method reduces hallucinations in multimodal language models by adaptively projecting hidden states onto a language-prior subspace, preserving helpful priors while suppressing harmful ones.
asr models struggle with bilingual code-switching
a new benchmark reveals how top automatic speech recognition systems handle mixed-language speech, with english segments causing the most errors.
run github ci on hugging face jobs
a step-by-step guide to replacing github-hosted runners with hugging face jobs for faster cpu and gpu ci.
cohere releases north mini code for agentic coding
cohere's north mini code is a 30b mixture-of-experts model with 3b active parameters, optimized for agentic software engineering tasks and available under apache 2.0.
seven free image generators on hugging face worth using in 2026
a curated list of seven free, high-quality text-to-image models available on hugging face, with details on licensing, use cases, and hardware requirements.
spin: swarm control via tensorized policy coordination
a new framework uses tensor networks to make decentralized multi-agent swarm control scalable on edge devices.
agent builds 3d paris gallery by chaining two spaces
a coding agent created a 3d gallery of paris monuments by calling two hugging face spaces for image generation and 3d reconstruction, then assembled them into a viewer.
why llms corrupt documents during delegation
a study finds that large language models silently corrupt documents over multiple edits, with smarter models fabricating plausible but false content.
anthropic's guide to building claude skills
a practical walkthrough for creating reusable instruction folders that give claude domain expertise across sessions.
why a market crash vanished when models changed
a bank run simulation that reliably crashed prices with one model stopped working when five different small models ran the same economy, revealing that emergent behavior is fragile and control requires authoring outcomes at settlement seams.