ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
The impact of positional encoding on length generalization in transformers.Advances in Neural Information Processing Systems, 36:24892–24928
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.
citing papers explorer
-
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
-
Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction
A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.