Adaptive 3D-RoPE adapts rotary positional encoding to wireless channel physics via learnable 3D frequencies and dynamic CSI control, yielding up to 10.7 dB NMSE gains in scale extrapolation and 1 dB in zero-shot tasks.
Masked au- toencoders are scalable vision learners
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Multi-source MAE pretraining on PANDA+CAMELYON17+BRACS tiles yields higher frozen linear-probe ISUP QWK than vanilla MAE under one disjoint PANDA split.
DualOpt decouples optimization by using real-time layer-wise weight decay for scratch training and weight rollback for fine-tuning to improve convergence, generalization, and reduce knowledge forgetting.
citing papers explorer
-
Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
Adaptive 3D-RoPE adapts rotary positional encoding to wireless channel physics via learnable 3D frequencies and dynamic CSI control, yielding up to 10.7 dB NMSE gains in scale extrapolation and 1 dB in zero-shot tasks.
-
ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification
Multi-source MAE pretraining on PANDA+CAMELYON17+BRACS tiles yields higher frozen linear-probe ISUP QWK than vanilla MAE under one disjoint PANDA split.
-
Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning
DualOpt decouples optimization by using real-time layer-wise weight decay for scratch training and weight rollback for fine-tuning to improve convergence, generalization, and reduce knowledge forgetting.