PP-OCRv6 Collection From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks ⢠19 items ⢠Updated 10 days ago ⢠94
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper ⢠2605.12882 ⢠Published May 13 ⢠274
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper ⢠2605.07755 ⢠Published May 8 ⢠24
view article Article How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas nvidia ⢠Apr 21 ⢠26
EXAONE 4.5 Collection LG's First Open-Weight Vision-Language Model for Industrial Intelligence ⢠5 items ⢠Updated Apr 22 ⢠45
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning Paper ⢠2601.23224 ⢠Published Jan 30 ⢠4
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding Paper ⢠2603.22458 ⢠Published Mar 23 ⢠138
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs Paper ⢠2603.16932 ⢠Published Mar 14 ⢠91
Grounding World Simulation Models in a Real-World Metropolis Paper ⢠2603.15583 ⢠Published Mar 16 ⢠155
ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors Paper ⢠2603.04338 ⢠Published Mar 4 ⢠24
Cosmos Policy Collection ā ļø This collection is archived. š https://huggingface.co/collections/nvidia/c ⢠7 items ⢠Updated 14 days ago ⢠11
K-EXAONE Collection First journey to foundation models with frontier-level performance. ⢠4 items ⢠Updated Jan 9 ⢠36