ML Foundations

mlfoundations's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

jieyuz2 

authored a paper 1 day ago

Vision-Language Grounding as Bidirectional Concept Correspondence

Paper • 2608.07886 • Published 5 days ago • 5

adhirajghosh 

authored 2 papers 8 days ago

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Paper • 2606.28551 • Published Jun 26 • 54

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Paper • 2511.20643 • Published Nov 25, 2025 • 4

vishaal27 

updated a dataset 10 days ago

mlfoundations/dcvlm_pool_medium

Updated 10 days ago • 403

vishaal27 

updated a dataset 12 days ago

mlfoundations/dcvlm-balanced-200b

Viewer • Updated 11 days ago • 10k • 30.2k • 1

vishaal27 

updated a dataset 14 days ago

mlfoundations/dcvlm_pool_small

Updated 14 days ago • 4.37k

vishaal27 

updated a collection 17 days ago

DCVLM

Collection

Raw data pools, pre-mixed ready-to-train datasets and checkpoints for DataComp-VLM. • 14 items • Updated 17 days ago • 6

vishaal27 

updated a dataset 17 days ago

mlfoundations/dcvlm_pool_small_annotations

Updated 17 days ago • 9.93k

vishaal27 

published a dataset 17 days ago

mlfoundations/dcvlm_pool_small_annotations

Updated 17 days ago • 9.93k

vishaal27 

updated 4 models 17 days ago

mlfoundations/dcvlm-8b-model

Image-Text-to-Text • 8B • Updated 17 days ago • 44

mlfoundations/dcvlm-4b-model

Image-Text-to-Text • 4B • Updated 17 days ago • 35

mlfoundations/dcvlm-2b-model

Image-Text-to-Text • 2B • Updated 17 days ago • 36

mlfoundations/dcvlm-1b-model

Image-Text-to-Text • 0.9B • Updated 17 days ago • 57

vishaal27 

updated a collection 17 days ago

DCVLM

Collection

Raw data pools, pre-mixed ready-to-train datasets and checkpoints for DataComp-VLM. • 14 items • Updated 17 days ago • 6

vishaal27 

published 3 models 17 days ago

mlfoundations/dcvlm-8b-model

Image-Text-to-Text • 8B • Updated 17 days ago • 44

mlfoundations/dcvlm-4b-model

Image-Text-to-Text • 4B • Updated 17 days ago • 35

mlfoundations/dcvlm-2b-model

Image-Text-to-Text • 2B • Updated 17 days ago • 36