Multinex introduces a multi-prior Retinex residual framework that produces lightweight (45K params) and nano (0.7K params) models for low-light image enhancement, outperforming other lightweight methods while approaching heavy-model performance.
Pytorch: An imperative style, high-performance deep learning library
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
citing papers explorer
-
Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
Multinex introduces a multi-prior Retinex residual framework that produces lightweight (45K params) and nano (0.7K params) models for low-light image enhancement, outperforming other lightweight methods while approaching heavy-model performance.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.