SSMoE uses eigenvectors of expert weights via SVD to build training-free non-collapsing routers for SMoE models in language and vision tasks.
In: 2015 IEEE International Conference on Computer Vision (ICCV)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Empirical study finds OV-OD robustness driven by vision backbone and image domain via layer-wise feature collapse analysis, validated with a low-parameter robustness improvement on real data.
citing papers explorer
-
Eigenvectors of Experts are Training-free Non-collapsing Routers
SSMoE uses eigenvectors of expert weights via SVD to build training-free non-collapsing routers for SMoE models in language and vision tasks.
-
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
Empirical study finds OV-OD robustness driven by vision backbone and image domain via layer-wise feature collapse analysis, validated with a low-parameter robustness improvement on real data.