view article Article cocogold: training Marigold for text-grounded segmentation By pcuenq • 15 days ago • 27
PS3: Scaling Vision Pre-Training to 4K Resolution Collection Enabling 4k resolution for VLMs, CVPR 2025, https://nvlabs.github.io/PS3/ • 4 items • Updated 1 day ago • 2
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language Paper • 2506.20920 • Published 27 days ago • 61
view article Article Training and Finetuning Sparse Embedding Models with Sentence Transformers v5 By tomaarsen and 1 other • 22 days ago • 105
V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 151
view article Article Explore, Build, and Innovate AI Reasoning with NVIDIA’s Open Models and Recipes By nvidia and 2 others • Jun 4 • 21
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published Feb 4 • 236
Jan 17 Releases ❄️ Collection Models and datasets of the second week of Jan 2025. • 23 items • Updated Jan 17 • 11
view article Article Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference By mfuntowicz and 1 other • Jan 16 • 75