Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
Mamba: Linear-time sequence modeling with selective state spaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
RAVEN introduces a chirp-wise streaming radar perception network with MIMO-preserving encoders, learnable cross-antenna mixing, and early-exit to deliver competitive detection and BEV segmentation at reduced compute and latency.
citing papers explorer
-
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
-
RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation
RAVEN introduces a chirp-wise streaming radar perception network with MIMO-preserving encoders, learnable cross-antenna mixing, and early-exit to deliver competitive detection and BEV segmentation at reduced compute and latency.