Feyn Introduces Pulpie: Pareto-Optimal Models for Efficient HTML Content Extraction

POPSICLE: A Benchmark Suite for Machine Learning in Cryo-Electron Tomography

This article introduces POPSICLE, a benchmark suite for cryo-electron tomography (cryoET) segmentation and macromolecular localization. Buil

Google's DiffusionGemma achieves 4x faster text generation using diffusion-based approach

DiffusionGemma is a new text generation model from Google that achieves up to 4x faster inference speeds compared to traditional autoregress

Building a Minimal RAG System from Scratch: PDF to Highlighted Answers in ~100 Lines of Python

A hands-on tutorial that builds the smallest functional RAG (Retrieval-Augmented Generation) system from scratch using about 100 lines of Py

Surge's GDP.pdf Benchmark Shows Frontier Models Need Structured Retrieval for Enterprise PDFs

Surge released GDP.pdf, a benchmark designed to test frontier AI models on real-world professional PDFs like claims packets, technical manua

Roofline Model for Estimating Speculative Decoding Speedup in LLM Inference

This article presents a roofline model for estimating speedup ratios from speculative decoding in large language model (LLM) inference. It a

ParseBench — Document Parsing Benchmark for AI Agents