DataComp-VLM: Improved Open Datasets for Vision-Language Models
Paper • 2606.28551 • Published • 49
Matteo Farins
farinamatteo
AI & ML interests
multimodal learning
Recent Activity
upvoted a paper 5 days ago
DataComp-VLM: Improved Open Datasets for Vision-Language Models upvoted a paper 4 months ago
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models upvoted a paper 4 months ago
TerraScope: Pixel-Grounded Visual Reasoning for Earth ObservationOrganizations
upvoted a paper 5 days ago
upvoted 3
papers 4 months ago
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Paper • 2603.19028 • Published • 18
TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
Paper • 2603.19039 • Published • 51
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Paper • 2603.19466 • Published • 41