Velox accelerates long video rollouts by routing attention via geometric frustum slabs, reducing latency while preserving ...

The method converts pre-trained transformers into elastic models that adapt continuously to varying computational budgets by ...

We introduce UltraText Bench, a bilingual benchmark for dense text rendering with 432 prompts across 24 real-world scene categories. Evaluating 24 model configurations reveals a key challenge: ...

We introduce CheckerBench, an executable benchmark for evaluating whether coding agents can turn real-world vulnerabilities into reusable static-analysis checkers. CheckerBench contains 300 tasks ...

Author here. WebFovea is a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 (57.0/100). It works on live websites through their own UI: screenshots in, clicks and keystrokes ...

ConceptCLIP is a large-scale vision-language pre-training model enhanced with medical concepts for diverse medical image modalities. It enables robust performance across multiple medical imaging tasks ...

A Blog post by Microsoft on Hugging Face ...

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

TripoSF is a state-of-the-art 3D shape modeling framework that enables differentiable mesh reconstruction at resolutions up to $1024^3$ directly from rendering losses. This repository contains the ...

A Blog post by Multiverse Computing on Hugging Face ...

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.