DTG-FF reaches 91.8% on CIFAR-10 and 49.4% on ImageNet-100 224x224 but BP baselines beat it by 2.4-5.93 pp with gaps widening by class count on real data while reversing the synthetic trend.
Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Applies causal inference to PCs from MD trajectories of two proteins to construct directed influence networks complementary to PCA and TICA.
citing papers explorer
-
Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training
DTG-FF reaches 91.8% on CIFAR-10 and 49.4% on ImageNet-100 224x224 but BP baselines beat it by 2.4-5.93 pp with gaps widening by class count on real data while reversing the synthetic trend.
-
Investigating causality between principal components in protein dynamics
Applies causal inference to PCs from MD trajectories of two proteins to construct directed influence networks complementary to PCA and TICA.