Cambrian-S: Towards Spatial Supersensing in Video
Paper
•
2511.04670
•
Published
•
34
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding
Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts
Add pipeline tag and update model card content
1
#1 opened 2 days ago
by
nielsr
jihanyang
authored
2
papers
3 days ago
sainx
authored
17
papers
9 days ago
Deeply-Supervised Nets
Paper
•
1409.5185
•
Published
Holistically-Nested Edge Detection
Paper
•
1504.06375
•
Published
•
1
Aggregated Residual Transformations for Deep Neural Networks
Paper
•
1611.05431
•
Published
•
2
Demystifying CLIP Data
Paper
•
2309.16671
•
Published
•
20
Sample-Efficient Neural Architecture Search by Learning Action Space
Paper
•
1906.06832
•
Published
Momentum Contrast for Unsupervised Visual Representation Learning
Paper
•
1911.05722
•
Published
•
1
Going Denser with Open-Vocabulary Part Segmentation
Paper
•
2305.11173
•
Published
•
2
Image Sculpting: Precise Object Editing with 3D Geometry Control
Paper
•
2401.01702
•
Published
•
20
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
Paper
•
2401.06209
•
Published
Masked Autoencoders Are Scalable Vision Learners
Paper
•
2111.06377
•
Published
•
5
V-IRL: Grounding Virtual Intelligence in Real Life
Paper
•
2402.03310
•
Published
•
16
Masked Feature Prediction for Self-Supervised Visual Pre-Training
Paper
•
2112.09133
•
Published
SLIP: Self-supervision meets Language-Image Pre-training
Paper
•
2112.12750
•
Published
•
1
A ConvNet for the 2020s
Paper
•
2201.03545
•
Published
•
1
Scalable Diffusion Models with Transformers
Paper
•
2212.09748
•
Published
•
18
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Paper
•
2301.00808
•
Published
CiT: Curation in Training for Effective Vision-Language Data
Paper
•
2301.02241
•
Published