HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models Paper • 2608.07003 • Published Aug 7 • 2
SWE-Explore: Benchmarking How Coding Agents Explore Repositories Paper • 2606.07297 • Published Jun 5 • 123
WorldVLA Collection https://github.com/alibaba-damo-academy/WorldVLA • 8 items • Updated Jun 25, 2025 • 1
JinaVDR (Visual Document Retrieval) Collection max. ~1000 images and OCR text included • 42 items • Updated Sep 17 • 9
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning Paper • 2505.04601 • Published May 7, 2025 • 27
SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding Paper • 2505.17012 • Published May 22, 2025 • 12
Cosmos-Transfer1 Collection ⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 5 items • Updated 9 days ago • 31
Cosmos-Preidct1 Collection ⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 14 items • Updated 9 days ago • 299
PixMo Collection A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated Mar 2 • 93
LLM-Neo Collection Model hub for LLM-Neo, including Llama3.1-Neo-1B-100w and Minitron-4B-Depth-Neo-10w. • 3 items • Updated Nov 20, 2024 • 6
VLM Judge Distillation Collection Distilling the 13B SpaceLLaVA VLM-as-a-Judge into a Florence-2 model to efficiently quality filter spatialVQA datasets like OpenSpaces • 4 items • Updated Nov 14, 2024 • 1
DepthPro Models Collection Depth Pro: Sharp Monocular Metric Depth in Less Than a Second • 9 items • Updated 3 days ago • 17
Molmo Collection Artifacts for open multimodal language models. • 5 items • Updated Dec 23, 2025 • 312
SpaceVLMs Collection Features VLMs fine-tuned for enhanced spatial reasoning using a synthetic data pipeline similar to Spatial VLM. • 14 items • Updated 5 days ago • 7
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities Paper • 2401.12168 • Published Jan 22, 2024 • 30