DepthVAR adaptively allocates per-token computational depth in VAR models using a cyclic rotated scheduler and dynamic layer masking to achieve 2.3-3.1x inference speedup with minimal quality loss.
Early exit is a nat- ural capability in transformer-based models: An empirical study on early exit without joint optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
N-vium achieves 57.9% wall-clock speedup over matched standard transformers at no perplexity cost by mixing exact predictions from multiple model depths.
citing papers explorer
-
Depth Adaptive Efficient Visual Autoregressive Modeling
DepthVAR adaptively allocates per-token computational depth in VAR models using a cyclic rotated scheduler and dynamic layer masking to achieve 2.3-3.1x inference speedup with minimal quality loss.
-
N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
N-vium achieves 57.9% wall-clock speedup over matched standard transformers at no perplexity cost by mixing exact predictions from multiple model depths.