FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
Paper
•
2512.01540
•
Published
•
3
Nathan Guilhot
nguilhot
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
upvoted
a
paper
about 1 month ago
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
upvoted
a
paper
about 1 month ago
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Organizations
None yet
upvoted
4
papers
about 1 month ago
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
Paper
•
2512.03000
•
Published
•
36
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Paper
•
2512.01030
•
Published
•
19
Multi-view Pyramid Transformer: Look Coarser to See Broader
Paper
•
2512.07806
•
Published
•
20