OScaR mitigates token norm imbalance via canalized rotation and omni-token scaling to enable near-lossless INT2 KV cache quantization with up to 3x decoding speedup and 5.3x memory reduction.
Memory-efficient visual au- toregressive modeling with scale-aware kv cache compression
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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
-
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
OScaR mitigates token norm imbalance via canalized rotation and omni-token scaling to enable near-lossless INT2 KV cache quantization with up to 3x decoding speedup and 5.3x memory reduction.
-
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.