Tag
A comprehensive list of all 15 CVPR 2026 paper finalists is now available on PapersWithCode, with links to GitHub repos, Hugging Face artifacts, and evaluation results.
Jerry Liu's team is presenting ParseBench, a comprehensive document understanding benchmark for VLMs, at CVPR 2026. The benchmark includes 2,000 pages of real-world enterprise documents with evaluation metrics for tables, charts, and visual grounding.
Meta's FAIR team released the code for Flowception, a CVPR 2026 paper presenting a non-autoregressive video generation framework that interleaves frame insertion with continuous denoising to reduce error accumulation and computational cost.
Meta AI and Oxford VGG released VGGT-Omega, a foundation model for 3D vision, with project page and GitHub repository.