Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces Quantizer‑Aligned Recalibration (QuAR), a single‑pass test‑time adaptation technique for quantized vision transformers that does not require backpropagation or parameter updates. QuAR recalibrates activations at the input of frozen quantizers by aligning per‑channel statistics with the source calibration, thereby correcting the distorted code distribution caused by distribution shift. On ImageNet‑C, QuAR outperforms state‑of‑the‑art backprop‑free methods across 3‑, 4‑, 6‑, and 8‑bit precisions, achieving higher accuracy, lower latency, and minimal memory overhead while maintaining performance across diverse shift scenarios.
arXiv:2610.16368v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) improve parameter efficiency by recursively reusing shared Transformer modules, yet their repeated computation over...
arXiv:2606. 18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment.
arXiv:2605.16343v2 Announce Type: replace-cross Abstract: Looped language models (LoopLMs) increase effective computational depth by repeatedly applying shared Transformer blocks without increasing t...
arXiv:2610.15139v2 Announce Type: replace Abstract: Linear-attention and state-space LLMs carry long context in a fixed-size recurrent state, and quantizing that state is the natural way to cut its c...
The paper investigates how to quantize recurrent language models, which use linear recurrences instead of softmax attention. It distinguishes between extra‑state quantization (weights and activations outside the recurrent state) and intra‑state quantization (the recurrent state itself during decoding). The authors introduce LoReS, a quantization pipeline that applies value‑axis scale grouping, decay‑based mixed precision, and stochastic rounding, enabling robust 8‑bit state quantization for large models such as Qwen‑3.5, Nemotron‑H, and Kimi‑Linear, and achieving decode speedups when integrated into vLLM.