LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
arXiv preprint arXiv:2506.08908 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
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.
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.
citing papers explorer
-
Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
-
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.
-
Visual Implicit Autoregressive Modeling
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.