jun's picture

1 1

jun

longjun1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

new activity 5 months ago

nvidia/Llama-Nemotron-VLM-Dataset-v1:The images in the ocr_1 dataset do not match the text content

View all activity

Organizations

None yet

upvoted a paper 1 day ago

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

Paper • 2601.06874 • Published 5 days ago • 10

New activity in nvidia/Llama-Nemotron-VLM-Dataset-v1 5 months ago

The images in the ocr_1 dataset do not match the text content

#6 opened 5 months ago by