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 implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.
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 implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.